From 7b3e459e29e88e3dd626ea7a558df3ee7bdfff5a Mon Sep 17 00:00:00 2001 From: hyukjinkwon Date: Mon, 9 Jul 2018 23:18:32 +0800 Subject: [PATCH] Fix signature description broken in PySpark API documentation in 2.2.2 --- site/docs/2.2.2/api/python/pyspark.html | 22 +- site/docs/2.2.2/api/python/pyspark.ml.html | 156 +++++------ site/docs/2.2.2/api/python/pyspark.mllib.html | 28 +- site/docs/2.2.2/api/python/pyspark.sql.html | 264 +++++++++--------- .../2.2.2/api/python/pyspark.streaming.html | 3 +- site/docs/2.2.2/api/python/searchindex.js | 2 +- 6 files changed, 238 insertions(+), 237 deletions(-) diff --git a/site/docs/2.2.2/api/python/pyspark.html b/site/docs/2.2.2/api/python/pyspark.html index b82ee143d4..85d8922e49 100644 --- a/site/docs/2.2.2/api/python/pyspark.html +++ b/site/docs/2.2.2/api/python/pyspark.html @@ -264,7 +264,7 @@

Subpackages
>>> sc.applicationId  
-u'local-...'
+'local-...'
@@ -743,7 +743,7 @@

Subpackages... _ = testFile.write("Hello world!") >>> textFile = sc.textFile(path) >>> textFile.collect() -[u'Hello world!'] +['Hello world!'] @@ -766,10 +766,10 @@

Subpackages... _ = testFile.write("Hello") >>> textFile = sc.textFile(path) >>> textFile.collect() -[u'Hello'] +['Hello'] >>> parallelized = sc.parallelize(["World!"]) >>> sorted(sc.union([textFile, parallelized]).collect()) -[u'Hello', 'World!'] +['Hello', 'World!'] @@ -819,7 +819,7 @@

Subpackages... _ = file2.write("2") >>> textFiles = sc.wholeTextFiles(dirPath) >>> sorted(textFiles.collect()) -[(u'.../1.txt', u'1'), (u'.../2.txt', u'2')] +[('.../1.txt', '1'), ('.../2.txt', '2')] @@ -1684,7 +1684,7 @@

Subpackagespipe(command, env=None, checkCode=False)[source]

Return an RDD created by piping elements to a forked external process.

>>> sc.parallelize(['1', '2', '', '3']).pipe('cat').collect()
-[u'1', u'2', u'', u'3']
+['1', '2', '', '3']
@@ -1799,7 +1799,7 @@

Subpackages
-repartitionAndSortWithinPartitions(numPartitions=None, partitionFunc=<function portable_hash>, ascending=True, keyfunc=<function <lambda>>)[source]
+repartitionAndSortWithinPartitions(numPartitions=None, partitionFunc=<function portable_hash>, ascending=True, keyfunc=<function RDD.<lambda>>)[source]

Repartition the RDD according to the given partitioner and, within each resulting partition, sort records by their keys.

>>> rdd = sc.parallelize([(0, 5), (3, 8), (2, 6), (0, 8), (3, 8), (1, 3)])
@@ -2089,7 +2089,7 @@ 
Subpackages>>> from fileinput import input, hook_compressed
 >>> result = sorted(input(glob(tempFile3.name + "/part*.gz"), openhook=hook_compressed))
 >>> b''.join(result).decode('utf-8')
-u'bar\nfoo\n'
+'bar\nfoo\n'
@@ -2100,7 +2100,7 @@

Subpackages
>>> rdd1 = sc.parallelize([1, 2])
 >>> rdd1.setName('RDD1').name()
-u'RDD1'
+'RDD1'
@@ -2120,7 +2120,7 @@

Subpackages
-sortByKey(ascending=True, numPartitions=None, keyfunc=<function <lambda>>)[source]
+sortByKey(ascending=True, numPartitions=None, keyfunc=<function RDD.<lambda>>)[source]

Sorts this RDD, which is assumed to consist of (key, value) pairs. # noqa

>>> tmp = [('a', 1), ('b', 2), ('1', 3), ('d', 4), ('2', 5)]
@@ -2664,7 +2664,7 @@ 
Subpackages
 

-loads(obj, encoding=None)[source]

+loads(obj, encoding='bytes')[source]
 
Deserialize an object from a byte array.

 

 
diff --git a/site/docs/2.2.2/api/python/pyspark.ml.html b/site/docs/2.2.2/api/python/pyspark.ml.html
index 1ba048c0af..d653dfe1cd 100644
--- a/site/docs/2.2.2/api/python/pyspark.ml.html
+++ b/site/docs/2.2.2/api/python/pyspark.ml.html
@@ -456,7 +456,7 @@ 
pyspark.ml package
 

-class pyspark.ml.Pipeline(*args, **kwargs)[source]

+class pyspark.ml.Pipeline(stages=None)[source]
 
A simple pipeline, which acts as an estimator. A Pipeline consists
 of a sequence of stages, each of which is either an
 Estimator or a Transformer. When
@@ -1046,7 +1046,7 @@ 
pyspark.ml package
pyspark.ml.feature module

 

 

-class pyspark.ml.feature.Binarizer(*args, **kwargs)[source]

+class pyspark.ml.feature.Binarizer(threshold=0.0, inputCol=None, outputCol=None)[source]
 
Binarize a column of continuous features given a threshold.

 
>>> df = spark.createDataFrame([(0.5,)], ["values"])
 >>> binarizer = Binarizer(threshold=1.0, inputCol="values", outputCol="features")
@@ -1286,7 +1286,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.BucketedRandomProjectionLSH(*args, **kwargs)[source]

+class pyspark.ml.feature.BucketedRandomProjectionLSH(inputCol=None, outputCol=None, seed=None, numHashTables=1, bucketLength=None)[source]
 

 
Note

 
Experimental

@@ -1829,7 +1829,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.Bucketizer(*args, **kwargs)[source]

+class pyspark.ml.feature.Bucketizer(splits=None, inputCol=None, outputCol=None, handleInvalid='error')[source]
 
Maps a column of continuous features to a column of feature buckets.

 
>>> values = [(0.1,), (0.4,), (1.2,), (1.5,), (float("nan"),), (float("nan"),)]
 >>> df = spark.createDataFrame(values, ["values"])
@@ -2103,7 +2103,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.ChiSqSelector(*args, **kwargs)[source]

+class pyspark.ml.feature.ChiSqSelector(numTopFeatures=50, featuresCol='features', outputCol=None, labelCol='label', selectorType='numTopFeatures', percentile=0.1, fpr=0.05, fdr=0.05, fwe=0.05)[source]
 

 
Note

 
Experimental

@@ -2683,7 +2683,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.CountVectorizer(*args, **kwargs)[source]

+class pyspark.ml.feature.CountVectorizer(minTF=1.0, minDF=1.0, vocabSize=262144, binary=False, inputCol=None, outputCol=None)[source]
 
Extracts a vocabulary from document collections and generates a CountVectorizerModel.

 
>>> df = spark.createDataFrame(
 ...    [(0, ["a", "b", "c"]), (1, ["a", "b", "b", "c", "a"])],
@@ -3176,7 +3176,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.DCT(*args, **kwargs)[source]

+class pyspark.ml.feature.DCT(inverse=False, inputCol=None, outputCol=None)[source]
 
A feature transformer that takes the 1D discrete cosine transform
 of a real vector. No zero padding is performed on the input vector.
 It returns a real vector of the same length representing the DCT.
@@ -3424,7 +3424,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.ElementwiseProduct(*args, **kwargs)[source]

+class pyspark.ml.feature.ElementwiseProduct(scalingVec=None, inputCol=None, outputCol=None)[source]
 
Outputs the Hadamard product (i.e., the element-wise product) of each input vector
 with a provided “weight” vector. In other words, it scales each column of the dataset
 by a scalar multiplier.

@@ -3665,7 +3665,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.HashingTF(*args, **kwargs)[source]

+class pyspark.ml.feature.HashingTF(numFeatures=262144, binary=False, inputCol=None, outputCol=None)[source]
 
Maps a sequence of terms to their term frequencies using the hashing trick.
 Currently we use Austin Appleby’s MurmurHash 3 algorithm (MurmurHash3_x86_32)
 to calculate the hash code value for the term object.
@@ -3927,7 +3927,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.IDF(*args, **kwargs)[source]

+class pyspark.ml.feature.IDF(minDocFreq=0, inputCol=None, outputCol=None)[source]
 
Compute the Inverse Document Frequency (IDF) given a collection of documents.

 
>>> from pyspark.ml.linalg import DenseVector
 >>> df = spark.createDataFrame([(DenseVector([1.0, 2.0]),),
@@ -4346,7 +4346,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.Imputer(*args, **kwargs)[source]

+class pyspark.ml.feature.Imputer(strategy='mean', missingValue=nan, inputCols=None, outputCols=None)[source]
 

 
Note

 
Experimental

@@ -4823,7 +4823,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.IndexToString(*args, **kwargs)[source]

+class pyspark.ml.feature.IndexToString(inputCol=None, outputCol=None, labels=None)[source]
 
A Transformer that maps a column of indices back to a new column of
 corresponding string values.
 The index-string mapping is either from the ML attributes of the input column,
@@ -5051,7 +5051,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.MaxAbsScaler(*args, **kwargs)[source]

+class pyspark.ml.feature.MaxAbsScaler(inputCol=None, outputCol=None)[source]
 
Rescale each feature individually to range [-1, 1] by dividing through the largest maximum
 absolute value in each feature. It does not shift/center the data, and thus does not destroy
 any sparsity.

@@ -5449,7 +5449,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.MinHashLSH(*args, **kwargs)[source]

+class pyspark.ml.feature.MinHashLSH(inputCol=None, outputCol=None, seed=None, numHashTables=1)[source]
 

 
Note

 
Experimental

@@ -5969,7 +5969,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.MinMaxScaler(*args, **kwargs)[source]

+class pyspark.ml.feature.MinMaxScaler(min=0.0, max=1.0, inputCol=None, outputCol=None)[source]
 
Rescale each feature individually to a common range [min, max] linearly using column summary
 statistics, which is also known as min-max normalization or Rescaling. The rescaled value for
 feature E is calculated as,

@@ -6435,7 +6435,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.NGram(*args, **kwargs)[source]

+class pyspark.ml.feature.NGram(n=2, inputCol=None, outputCol=None)[source]
 
A feature transformer that converts the input array of strings into an array of n-grams. Null
 values in the input array are ignored.
 It returns an array of n-grams where each n-gram is represented by a space-separated string of
@@ -6446,15 +6446,15 @@ 
pyspark.ml package
>>> df = spark.createDataFrame([Row(inputTokens=["a", "b", "c", "d", "e"])])
 >>> ngram = NGram(n=2, inputCol="inputTokens", outputCol="nGrams")
 >>> ngram.transform(df).head()
-Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], nGrams=[u'a b', u'b c', u'c d', u'd e'])
+Row(inputTokens=['a', 'b', 'c', 'd', 'e'], nGrams=['a b', 'b c', 'c d', 'd e'])
 >>> # Change n-gram length
 >>> ngram.setParams(n=4).transform(df).head()
-Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], nGrams=[u'a b c d', u'b c d e'])
+Row(inputTokens=['a', 'b', 'c', 'd', 'e'], nGrams=['a b c d', 'b c d e'])
 >>> # Temporarily modify output column.
 >>> ngram.transform(df, {ngram.outputCol: "output"}).head()
-Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], output=[u'a b c d', u'b c d e'])
+Row(inputTokens=['a', 'b', 'c', 'd', 'e'], output=['a b c d', 'b c d e'])
 >>> ngram.transform(df).head()
-Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], nGrams=[u'a b c d', u'b c d e'])
+Row(inputTokens=['a', 'b', 'c', 'd', 'e'], nGrams=['a b c d', 'b c d e'])
 >>> # Must use keyword arguments to specify params.
 >>> ngram.setParams("text")
 Traceback (most recent call last):
@@ -6689,7 +6689,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.Normalizer(*args, **kwargs)[source]

+class pyspark.ml.feature.Normalizer(p=2.0, inputCol=None, outputCol=None)[source]
 

 
Normalize a vector to have unit norm using the given p-norm.

 
>>> from pyspark.ml.linalg import Vectors
@@ -6932,7 +6932,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.OneHotEncoder(*args, **kwargs)[source]

+class pyspark.ml.feature.OneHotEncoder(dropLast=True, inputCol=None, outputCol=None)[source]
 
A one-hot encoder that maps a column of category indices to a
 column of binary vectors, with at most a single one-value per row
 that indicates the input category index.
@@ -7192,7 +7192,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.PCA(*args, **kwargs)[source]

+class pyspark.ml.feature.PCA(k=None, inputCol=None, outputCol=None)[source]
 
PCA trains a model to project vectors to a lower dimensional space of the
 top k principal components.

 
>>> from pyspark.ml.linalg import Vectors
@@ -7622,7 +7622,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.PolynomialExpansion(*args, **kwargs)[source]

+class pyspark.ml.feature.PolynomialExpansion(degree=2, inputCol=None, outputCol=None)[source]
 
Perform feature expansion in a polynomial space. As said in wikipedia of Polynomial Expansion, “In mathematics, an
 expansion of a product of sums expresses it as a sum of products by using the fact that
 multiplication distributes over addition”. Take a 2-variable feature vector as an example:
@@ -7863,7 +7863,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.QuantileDiscretizer(*args, **kwargs)[source]

+class pyspark.ml.feature.QuantileDiscretizer(numBuckets=2, inputCol=None, outputCol=None, relativeError=0.001, handleInvalid='error')[source]
 

 
Note

 
Experimental

@@ -8179,7 +8179,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.RegexTokenizer(*args, **kwargs)[source]

+class pyspark.ml.feature.RegexTokenizer(minTokenLength=1, gaps=True, pattern='\s+', inputCol=None, outputCol=None, toLowercase=True)[source]
 
A regex based tokenizer that extracts tokens either by using the
 provided regex pattern (in Java dialect) to split the text
 (default) or repeatedly matching the regex (if gaps is false).
@@ -8189,15 +8189,15 @@ 
pyspark.ml package
>>> df = spark.createDataFrame([("A B  c",)], ["text"])
 >>> reTokenizer = RegexTokenizer(inputCol="text", outputCol="words")
 >>> reTokenizer.transform(df).head()
-Row(text=u'A B  c', words=[u'a', u'b', u'c'])
+Row(text='A B  c', words=['a', 'b', 'c'])
 >>> # Change a parameter.
 >>> reTokenizer.setParams(outputCol="tokens").transform(df).head()
-Row(text=u'A B  c', tokens=[u'a', u'b', u'c'])
+Row(text='A B  c', tokens=['a', 'b', 'c'])
 >>> # Temporarily modify a parameter.
 >>> reTokenizer.transform(df, {reTokenizer.outputCol: "words"}).head()
-Row(text=u'A B  c', words=[u'a', u'b', u'c'])
+Row(text='A B  c', words=['a', 'b', 'c'])
 >>> reTokenizer.transform(df).head()
-Row(text=u'A B  c', tokens=[u'a', u'b', u'c'])
+Row(text='A B  c', tokens=['a', 'b', 'c'])
 >>> # Must use keyword arguments to specify params.
 >>> reTokenizer.setParams("text")
 Traceback (most recent call last):
@@ -8503,7 +8503,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.RFormula(*args, **kwargs)[source]

+class pyspark.ml.feature.RFormula(formula=None, featuresCol='features', labelCol='label', forceIndexLabel=False)[source]
 

 
Note

 
Experimental

@@ -8975,7 +8975,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.SQLTransformer(*args, **kwargs)[source]

+class pyspark.ml.feature.SQLTransformer(statement=None)[source]
 
Implements the transforms which are defined by SQL statement.
 Currently we only support SQL syntax like ‘SELECT … FROM __THIS__’
 where ‘__THIS__’ represents the underlying table of the input dataset.

@@ -9179,7 +9179,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.StandardScaler(*args, **kwargs)[source]

+class pyspark.ml.feature.StandardScaler(withMean=False, withStd=True, inputCol=None, outputCol=None)[source]
 
Standardizes features by removing the mean and scaling to unit variance using column summary
 statistics on the samples in the training set.

 
The “unit std” is computed using the corrected sample standard deviation,
@@ -9633,7 +9633,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.StopWordsRemover(*args, **kwargs)[source]

+class pyspark.ml.feature.StopWordsRemover(inputCol=None, outputCol=None, stopWords=None, caseSensitive=False)[source]
 
A feature transformer that filters out stop words from input.

 

 
Note

@@ -9908,7 +9908,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.StringIndexer(*args, **kwargs)[source]

+class pyspark.ml.feature.StringIndexer(inputCol=None, outputCol=None, handleInvalid='error')[source]
 
A label indexer that maps a string column of labels to an ML column of label indices.
 If the input column is numeric, we cast it to string and index the string values.
 The indices are in [0, numLabels), ordered by label frequencies.
@@ -10326,21 +10326,21 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.Tokenizer(*args, **kwargs)[source]

+class pyspark.ml.feature.Tokenizer(inputCol=None, outputCol=None)[source]
 
A tokenizer that converts the input string to lowercase and then
 splits it by white spaces.

 
>>> df = spark.createDataFrame([("a b c",)], ["text"])
 >>> tokenizer = Tokenizer(inputCol="text", outputCol="words")
 >>> tokenizer.transform(df).head()
-Row(text=u'a b c', words=[u'a', u'b', u'c'])
+Row(text='a b c', words=['a', 'b', 'c'])
 >>> # Change a parameter.
 >>> tokenizer.setParams(outputCol="tokens").transform(df).head()
-Row(text=u'a b c', tokens=[u'a', u'b', u'c'])
+Row(text='a b c', tokens=['a', 'b', 'c'])
 >>> # Temporarily modify a parameter.
 >>> tokenizer.transform(df, {tokenizer.outputCol: "words"}).head()
-Row(text=u'a b c', words=[u'a', u'b', u'c'])
+Row(text='a b c', words=['a', 'b', 'c'])
 >>> tokenizer.transform(df).head()
-Row(text=u'a b c', tokens=[u'a', u'b', u'c'])
+Row(text='a b c', tokens=['a', 'b', 'c'])
 >>> # Must use keyword arguments to specify params.
 >>> tokenizer.setParams("text")
 Traceback (most recent call last):
@@ -10552,7 +10552,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.VectorAssembler(*args, **kwargs)[source]

+class pyspark.ml.feature.VectorAssembler(inputCols=None, outputCol=None)[source]
 
A feature transformer that merges multiple columns into a vector column.

 
>>> df = spark.createDataFrame([(1, 0, 3)], ["a", "b", "c"])
 >>> vecAssembler = VectorAssembler(inputCols=["a", "b", "c"], outputCol="features")
@@ -10769,7 +10769,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.VectorIndexer(*args, **kwargs)[source]

+class pyspark.ml.feature.VectorIndexer(maxCategories=20, inputCol=None, outputCol=None)[source]
 
Class for indexing categorical feature columns in a dataset of Vector.

 

 
This has 2 usage modes:

@@ -11274,7 +11274,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.VectorSlicer(*args, **kwargs)[source]

+class pyspark.ml.feature.VectorSlicer(inputCol=None, outputCol=None, indices=None, names=None)[source]
 
This class takes a feature vector and outputs a new feature vector with a subarray
 of the original features.

 
The subset of features can be specified with either indices (setIndices())
@@ -11503,7 +11503,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(inputCol=None, outputCol=None, indices=None, names=None)[source]
 
setParams(self, inputCol=None, outputCol=None, indices=None, names=None):
 Sets params for this VectorSlicer.

 

@@ -11545,7 +11545,7 @@ 
pyspark.ml package
 

-class pyspark.ml.feature.Word2Vec(*args, **kwargs)[source]

+class pyspark.ml.feature.Word2Vec(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, seed=None, inputCol=None, outputCol=None, windowSize=5, maxSentenceLength=1000)[source]
 
Word2Vec trains a model of Map(String, Vector), i.e. transforms a word into a code for further
 natural language processing or machine learning process.

 
>>> sent = ("a b " * 100 + "a c " * 10).split(" ")
@@ -12140,7 +12140,7 @@ 
pyspark.ml package
pyspark.ml.classification module

 

 

-class pyspark.ml.classification.LinearSVC(*args, **kwargs)[source]

+class pyspark.ml.classification.LinearSVC(featuresCol='features', labelCol='label', predictionCol='prediction', maxIter=100, regParam=0.0, tol=1e-06, rawPredictionCol='rawPrediction', fitIntercept=True, standardization=True, threshold=0.0, weightCol=None, aggregationDepth=2)[source]
 

 
Note

 
Experimental

@@ -12475,7 +12475,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(featuresCol='features', labelCol='label', predictionCol='prediction', maxIter=100, regParam=0.0, tol=1e-06, rawPredictionCol='rawPrediction', fitIntercept=True, standardization=True, threshold=0.0, weightCol=None, aggregationDepth=2)[source]
 
setParams(self, featuresCol=”features”, labelCol=”label”, predictionCol=”prediction”,                   maxIter=100, regParam=0.0, tol=1e-6, rawPredictionCol=”rawPrediction”,                   fitIntercept=True, standardization=True, threshold=0.0, weightCol=None,                   aggregationDepth=2):
 Sets params for Linear SVM Classifier.

 

@@ -12753,7 +12753,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.LogisticRegression(*args, **kwargs)[source]

+class pyspark.ml.classification.LogisticRegression(featuresCol='features', labelCol='label', predictionCol='prediction', maxIter=100, regParam=0.0, elasticNetParam=0.0, tol=1e-06, fitIntercept=True, threshold=0.5, thresholds=None, probabilityCol='probability', rawPredictionCol='rawPrediction', standardization=True, weightCol=None, aggregationDepth=2, family='auto')[source]
 
Logistic regression.
 This class supports multinomial logistic (softmax) and binomial logistic regression.

 
>>> from pyspark.sql import Row
@@ -13981,7 +13981,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.DecisionTreeClassifier(*args, **kwargs)[source]

+class pyspark.ml.classification.DecisionTreeClassifier(featuresCol='features', labelCol='label', predictionCol='prediction', probabilityCol='probability', rawPredictionCol='rawPrediction', maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity='gini', seed=None)[source]
 
Decision tree
 learning algorithm for classification.
 It supports both binary and multiclass labels, as well as both continuous and categorical
@@ -14679,7 +14679,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.GBTClassifier(*args, **kwargs)[source]

+class pyspark.ml.classification.GBTClassifier(featuresCol='features', labelCol='label', predictionCol='prediction', maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType='logistic', maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0)[source]
 
Gradient-Boosted Trees (GBTs)
 learning algorithm for classification.
 It supports binary labels, as well as both continuous and categorical features.

@@ -15404,7 +15404,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.RandomForestClassifier(*args, **kwargs)[source]

+class pyspark.ml.classification.RandomForestClassifier(featuresCol='features', labelCol='label', predictionCol='prediction', probabilityCol='probability', rawPredictionCol='rawPrediction', maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity='gini', numTrees=20, featureSubsetStrategy='auto', seed=None, subsamplingRate=1.0)[source]
 
Random Forest
 learning algorithm for classification.
 It supports both binary and multiclass labels, as well as both continuous and categorical
@@ -16178,7 +16178,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.NaiveBayes(*args, **kwargs)[source]

+class pyspark.ml.classification.NaiveBayes(featuresCol='features', labelCol='label', predictionCol='prediction', probabilityCol='probability', rawPredictionCol='rawPrediction', smoothing=1.0, modelType='multinomial', thresholds=None, weightCol=None)[source]
 
Naive Bayes Classifiers.
 It supports both Multinomial and Bernoulli NB. Multinomial NB
 can handle finitely supported discrete data. For example, by converting documents into
@@ -16753,7 +16753,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.MultilayerPerceptronClassifier(*args, **kwargs)[source]

+class pyspark.ml.classification.MultilayerPerceptronClassifier(featuresCol='features', labelCol='label', predictionCol='prediction', maxIter=100, tol=1e-06, seed=None, layers=None, blockSize=128, stepSize=0.03, solver='l-bfgs', initialWeights=None)[source]
 
Classifier trainer based on the Multilayer Perceptron.
 Each layer has sigmoid activation function, output layer has softmax.
 Number of inputs has to be equal to the size of feature vectors.
@@ -17370,7 +17370,7 @@ 
pyspark.ml package
 

-class pyspark.ml.classification.OneVsRest(*args, **kwargs)[source]

+class pyspark.ml.classification.OneVsRest(featuresCol='features', labelCol='label', predictionCol='prediction', classifier=None, weightCol=None)[source]
 

 
Note

 
Experimental

@@ -17646,7 +17646,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(featuresCol=None, labelCol=None, predictionCol=None, classifier=None, weightCol=None)[source]
 
setParams(self, featuresCol=None, labelCol=None, predictionCol=None,                   classifier=None, weightCol=None):
 Sets params for OneVsRest.

 

@@ -17957,7 +17957,7 @@ 
pyspark.ml package
pyspark.ml.clustering module

 

 

-class pyspark.ml.clustering.BisectingKMeans(*args, **kwargs)[source]

+class pyspark.ml.clustering.BisectingKMeans(featuresCol='features', predictionCol='prediction', maxIter=20, seed=None, k=4, minDivisibleClusterSize=1.0)[source]
 
A bisecting k-means algorithm based on the paper “A comparison of document clustering
 techniques” by Steinbach, Karypis, and Kumar, with modification to fit Spark.
 The algorithm starts from a single cluster that contains all points.
@@ -18550,7 +18550,7 @@ 
pyspark.ml package
 

-class pyspark.ml.clustering.KMeans(*args, **kwargs)[source]

+class pyspark.ml.clustering.KMeans(featuresCol='features', predictionCol='prediction', k=2, initMode='k-means||', initSteps=2, tol=0.0001, maxIter=20, seed=None)[source]
 
K-means clustering with a k-means++ like initialization mode
 (the k-means|| algorithm by Bahmani et al).

 
>>> from pyspark.ml.linalg import Vectors
@@ -19110,7 +19110,7 @@ 
pyspark.ml package
 

-class pyspark.ml.clustering.GaussianMixture(*args, **kwargs)[source]

+class pyspark.ml.clustering.GaussianMixture(featuresCol='features', predictionCol='prediction', k=2, probabilityCol='probability', tol=0.01, maxIter=100, seed=None)[source]
 
GaussianMixture clustering.
 This class performs expectation maximization for multivariate Gaussian
 Mixture Models (GMMs).  A GMM represents a composite distribution of
@@ -19767,7 +19767,7 @@ 
pyspark.ml package
 

-class pyspark.ml.clustering.LDA(*args, **kwargs)[source]

+class pyspark.ml.clustering.LDA(featuresCol='features', maxIter=20, seed=None, checkpointInterval=10, k=10, optimizer='online', learningOffset=1024.0, learningDecay=0.51, subsamplingRate=0.05, optimizeDocConcentration=True, docConcentration=None, topicConcentration=None, topicDistributionCol='topicDistribution', keepLastCheckpoint=True)[source]
 
Latent Dirichlet Allocation (LDA), a topic model designed for text documents.

 
Terminology:

 

@@ -20258,7 +20258,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(featuresCol='features', maxIter=20, seed=None, checkpointInterval=10, k=10, optimizer='online', learningOffset=1024.0, learningDecay=0.51, subsamplingRate=0.05, optimizeDocConcentration=True, docConcentration=None, topicConcentration=None, topicDistributionCol='topicDistribution', keepLastCheckpoint=True)[source]
 
setParams(self, featuresCol=”features”, maxIter=20, seed=None, checkpointInterval=10,                  k=10, optimizer=”online”, learningOffset=1024.0, learningDecay=0.51,                  subsamplingRate=0.05, optimizeDocConcentration=True,                  docConcentration=None, topicConcentration=None,                  topicDistributionCol=”topicDistribution”, keepLastCheckpoint=True):

 
Sets params for LDA.

 

@@ -21493,7 +21493,7 @@ 
pyspark.ml package
pyspark.ml.recommendation module

 

 

-class pyspark.ml.recommendation.ALS(*args, **kwargs)[source]

+class pyspark.ml.recommendation.ALS(rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, implicitPrefs=False, alpha=1.0, userCol='user', itemCol='item', seed=None, ratingCol='rating', nonnegative=False, checkpointInterval=10, intermediateStorageLevel='MEMORY_AND_DISK', finalStorageLevel='MEMORY_AND_DISK', coldStartStrategy='nan')[source]
 
Alternating Least Squares (ALS) matrix factorization.

 
ALS attempts to estimate the ratings matrix R as the product of
 two lower-rank matrices, X and Y, i.e. X * Yt = R. Typically
@@ -22330,7 +22330,7 @@ 
pyspark.ml package
pyspark.ml.regression module

 

 

-class pyspark.ml.regression.AFTSurvivalRegression(*args, **kwargs)[source]

+class pyspark.ml.regression.AFTSurvivalRegression(featuresCol='features', labelCol='label', predictionCol='prediction', fitIntercept=True, maxIter=100, tol=1e-06, censorCol='censor', quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99], quantilesCol=None, aggregationDepth=2)[source]
 

 
Note

 
Experimental

@@ -22679,7 +22679,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(featuresCol='features', labelCol='label', predictionCol='prediction', fitIntercept=True, maxIter=100, tol=1e-06, censorCol='censor', quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99], quantilesCol=None, aggregationDepth=2)[source]
 
setParams(self, featuresCol=”features”, labelCol=”label”, predictionCol=”prediction”,                   fitIntercept=True, maxIter=100, tol=1E-6, censorCol=”censor”,                   quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99],                   quantilesCol=None, aggregationDepth=2):

 

 
New in version 1.6.0.

@@ -22938,7 +22938,7 @@ 
pyspark.ml package
 

-class pyspark.ml.regression.DecisionTreeRegressor(*args, **kwargs)[source]

+class pyspark.ml.regression.DecisionTreeRegressor(featuresCol='features', labelCol='label', predictionCol='prediction', maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity='variance', seed=None, varianceCol=None)[source]
 
Decision tree
 learning algorithm for regression.
 It supports both continuous and categorical features.

@@ -23598,7 +23598,7 @@ 
pyspark.ml package
 

-class pyspark.ml.regression.GBTRegressor(*args, **kwargs)[source]

+class pyspark.ml.regression.GBTRegressor(featuresCol='features', labelCol='label', predictionCol='prediction', maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0, checkpointInterval=10, lossType='squared', maxIter=20, stepSize=0.1, seed=None, impurity='variance')[source]
 
Gradient-Boosted Trees (GBTs)
 learning algorithm for regression.
 It supports both continuous and categorical features.

@@ -24335,7 +24335,7 @@ 
pyspark.ml package
 

-class pyspark.ml.regression.GeneralizedLinearRegression(*args, **kwargs)[source]

+class pyspark.ml.regression.GeneralizedLinearRegression(labelCol='label', featuresCol='features', predictionCol='prediction', family='gaussian', link=None, fitIntercept=True, maxIter=25, tol=1e-06, regParam=0.0, weightCol=None, solver='irls', linkPredictionCol=None, variancePower=0.0, linkPower=None)[source]
 

 
Note

 
Experimental

@@ -25371,7 +25371,7 @@ 
pyspark.ml package
 

-class pyspark.ml.regression.IsotonicRegression(*args, **kwargs)[source]

+class pyspark.ml.regression.IsotonicRegression(featuresCol='features', labelCol='label', predictionCol='prediction', weightCol=None, isotonic=True, featureIndex=0)[source]
 
Currently implemented using parallelized pool adjacent violators algorithm.
 Only univariate (single feature) algorithm supported.

 
>>> from pyspark.ml.linalg import Vectors
@@ -25634,7 +25634,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(featuresCol='features', labelCol='label', predictionCol='prediction', weightCol=None, isotonic=True, featureIndex=0)[source]
 
setParams(self, featuresCol=”features”, labelCol=”label”, predictionCol=”prediction”,                  weightCol=None, isotonic=True, featureIndex=0):
 Set the params for IsotonicRegression.

 

@@ -25843,7 +25843,7 @@ 
pyspark.ml package
 

-class pyspark.ml.regression.LinearRegression(*args, **kwargs)[source]

+class pyspark.ml.regression.LinearRegression(featuresCol='features', labelCol='label', predictionCol='prediction', maxIter=100, regParam=0.0, elasticNetParam=0.0, tol=1e-06, fitIntercept=True, standardization=True, solver='auto', weightCol=None, aggregationDepth=2)[source]
 
Linear regression.

 
The learning objective is to minimize the squared error, with regularization.
 The specific squared error loss function used is: L = 1/2n ||A coefficients - y||^2^

@@ -26969,7 +26969,7 @@ 
pyspark.ml package
 

-class pyspark.ml.regression.RandomForestRegressor(*args, **kwargs)[source]

+class pyspark.ml.regression.RandomForestRegressor(featuresCol='features', labelCol='label', predictionCol='prediction', maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity='variance', subsamplingRate=1.0, seed=None, numTrees=20, featureSubsetStrategy='auto')[source]
 
Random Forest
 learning algorithm for regression.
 It supports both continuous and categorical features.

@@ -27887,7 +27887,7 @@ 
pyspark.ml package
 

-class pyspark.ml.tuning.CrossValidator(*args, **kwargs)[source]

+class pyspark.ml.tuning.CrossValidator(estimator=None, estimatorParamMaps=None, evaluator=None, numFolds=3, seed=None)[source]
 
K-fold cross validation performs model selection by splitting the dataset into a set of
 non-overlapping randomly partitioned folds which are used as separate training and test datasets
 e.g., with k=3 folds, K-fold cross validation will generate 3 (training, test) dataset pairs,
@@ -28132,7 +28132,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(estimator=None, estimatorParamMaps=None, evaluator=None, numFolds=3, seed=None)[source]
 
setParams(self, estimator=None, estimatorParamMaps=None, evaluator=None, numFolds=3,                  seed=None):
 Sets params for cross validator.

 

@@ -28369,7 +28369,7 @@ 
pyspark.ml package
 

-class pyspark.ml.tuning.TrainValidationSplit(*args, **kwargs)[source]

+class pyspark.ml.tuning.TrainValidationSplit(estimator=None, estimatorParamMaps=None, evaluator=None, trainRatio=0.75, seed=None)[source]
 

 
Note

 
Experimental

@@ -28600,7 +28600,7 @@ 
pyspark.ml package
 

-setParams(*args, **kwargs)[source]

+setParams(estimator=None, estimatorParamMaps=None, evaluator=None, trainRatio=0.75, seed=None)[source]
 
setParams(self, estimator=None, estimatorParamMaps=None, evaluator=None, trainRatio=0.75,                  seed=None):
 Sets params for the train validation split.

 

@@ -29004,7 +29004,7 @@ 
pyspark.ml package
 

-class pyspark.ml.evaluation.BinaryClassificationEvaluator(*args, **kwargs)[source]

+class pyspark.ml.evaluation.BinaryClassificationEvaluator(rawPredictionCol='rawPrediction', labelCol='label', metricName='areaUnderROC')[source]
 

 
Note

 
Experimental

@@ -29264,7 +29264,7 @@ 
pyspark.ml package
 

-class pyspark.ml.evaluation.RegressionEvaluator(*args, **kwargs)[source]

+class pyspark.ml.evaluation.RegressionEvaluator(predictionCol='prediction', labelCol='label', metricName='rmse')[source]
 

 
Note

 
Experimental

@@ -29524,7 +29524,7 @@ 
pyspark.ml package
 

-class pyspark.ml.evaluation.MulticlassClassificationEvaluator(*args, **kwargs)[source]

+class pyspark.ml.evaluation.MulticlassClassificationEvaluator(predictionCol='prediction', labelCol='label', metricName='f1')[source]
 

 
Note

 
Experimental

@@ -29785,7 +29785,7 @@ 
pyspark.ml package
pyspark.ml.fpm module

 

 

-class pyspark.ml.fpm.FPGrowth(*args, **kwargs)[source]

+class pyspark.ml.fpm.FPGrowth(minSupport=0.3, minConfidence=0.8, itemsCol='items', predictionCol='prediction', numPartitions=None)[source]
 

 
Note

 
Experimental

diff --git a/site/docs/2.2.2/api/python/pyspark.mllib.html b/site/docs/2.2.2/api/python/pyspark.mllib.html
index bba22cd228..dc1aafa86c 100644
--- a/site/docs/2.2.2/api/python/pyspark.mllib.html
+++ b/site/docs/2.2.2/api/python/pyspark.mllib.html
@@ -2624,7 +2624,7 @@ 
pyspark.mllib packageQuerying for synonyms of a word will not return that word:

 
>>> syms = model.findSynonyms("a", 2)
 >>> [s[0] for s in syms]
-[u'b', u'c']
+['b', 'c']
 

 

 
But querying for synonyms of a vector may return the word whose
@@ -2632,7 +2632,7 @@ 
pyspark.mllib package
>>> vec = model.transform("a")
 >>> syms = model.findSynonyms(vec, 2)
 >>> [s[0] for s in syms]
-[u'a', u'b']
+['a', 'b']
 

 

 
>>> import os, tempfile
@@ -2643,7 +2643,7 @@ 
pyspark.mllib packageTrue
 >>> syms = sameModel.findSynonyms("a", 2)
 >>> [s[0] for s in syms]
-[u'b', u'c']
+['b', 'c']
 >>> from shutil import rmtree
 >>> try:
 ...     rmtree(path)
@@ -3064,7 +3064,7 @@ 
pyspark.mllib package>>> rdd = sc.parallelize(data, 2)
 >>> model = FPGrowth.train(rdd, 0.6, 2)
 >>> sorted(model.freqItemsets().collect())
-[FreqItemset(items=[u'a'], freq=4), FreqItemset(items=[u'c'], freq=3), ...
+[FreqItemset(items=['a'], freq=4), FreqItemset(items=['c'], freq=3), ...
 >>> model_path = temp_path + "/fpm"
 >>> model.save(sc, model_path)
 >>> sameModel = FPGrowthModel.load(sc, model_path)
@@ -3162,7 +3162,7 @@ 
pyspark.mllib package>>> rdd = sc.parallelize(data, 2)
 >>> model = PrefixSpan.train(rdd)
 >>> sorted(model.freqSequences().collect())
-[FreqSequence(sequence=[[u'a']], freq=3), FreqSequence(sequence=[[u'a'], [u'a']], freq=1), ...
+[FreqSequence(sequence=[['a']], freq=3), FreqSequence(sequence=[['a'], ['a']], freq=1), ...
 

 

 

@@ -5169,7 +5169,7 @@ 
pyspark.mllib package
 

-static exponentialVectorRDD(sc, *a, **kw)[source]

+static exponentialVectorRDD(sc, mean, numRows, numCols, numPartitions=None, seed=None)[source]
 
Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the Exponential distribution with the input mean.

@@ -5255,7 +5255,7 @@

pyspark.mllib package
-static gammaVectorRDD(sc, *a, **kw)[source]
+static gammaVectorRDD(sc, shape, scale, numRows, numCols, numPartitions=None, seed=None)[source]

Generates an RDD comprised of vectors containing i.i.d. samples drawn from the Gamma distribution.

@@ -5345,7 +5345,7 @@

pyspark.mllib package
-static logNormalVectorRDD(sc, *a, **kw)[source]
+static logNormalVectorRDD(sc, mean, std, numRows, numCols, numPartitions=None, seed=None)[source]

Generates an RDD comprised of vectors containing i.i.d. samples drawn from the log normal distribution.

@@ -5431,7 +5431,7 @@

pyspark.mllib package
-static normalVectorRDD(sc, *a, **kw)[source]
+static normalVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None)[source]

Generates an RDD comprised of vectors containing i.i.d. samples drawn from the standard normal distribution.

@@ -5509,7 +5509,7 @@

pyspark.mllib package
-static poissonVectorRDD(sc, *a, **kw)[source]
+static poissonVectorRDD(sc, mean, numRows, numCols, numPartitions=None, seed=None)[source]

Generates an RDD comprised of vectors containing i.i.d. samples drawn from the Poisson distribution with the input mean.

@@ -5593,7 +5593,7 @@

pyspark.mllib package
-static uniformVectorRDD(sc, *a, **kw)[source]
+static uniformVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None)[source]

Generates an RDD comprised of vectors containing i.i.d. samples drawn from the uniform distribution U(0.0, 1.0).

@@ -6864,9 +6864,9 @@

pyspark.mllib package>>> print(round(pearson.pValue, 4)) 0.8187 >>> pearson.method -u'pearson' +'pearson' >>> pearson.nullHypothesis -u'observed follows the same distribution as expected.' +'observed follows the same distribution as expected.' 
>>> observed = Vectors.dense([21, 38, 43, 80])
@@ -7046,7 +7046,7 @@ 
pyspark.mllib package>>> print(round(ksmodel.statistic, 3))
 0.175
 >>> ksmodel.nullHypothesis
-u'Sample follows theoretical distribution'
+'Sample follows theoretical distribution'
 
>>> data = sc.parallelize([2.0, 3.0, 4.0])
diff --git a/site/docs/2.2.2/api/python/pyspark.sql.html b/site/docs/2.2.2/api/python/pyspark.sql.html
index ef4555bb38..3204eee23b 100644
--- a/site/docs/2.2.2/api/python/pyspark.sql.html
+++ b/site/docs/2.2.2/api/python/pyspark.sql.html
@@ -271,22 +271,22 @@ 
pyspark.sql module
>>> l = [('Alice', 1)]
 >>> spark.createDataFrame(l).collect()
-[Row(_1=u'Alice', _2=1)]
+[Row(_1='Alice', _2=1)]
 >>> spark.createDataFrame(l, ['name', 'age']).collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 

 
>>> d = [{'name': 'Alice', 'age': 1}]
 >>> spark.createDataFrame(d).collect()
-[Row(age=1, name=u'Alice')]
+[Row(age=1, name='Alice')]
 
>>> rdd = sc.parallelize(l)
 >>> spark.createDataFrame(rdd).collect()
-[Row(_1=u'Alice', _2=1)]
+[Row(_1='Alice', _2=1)]
 >>> df = spark.createDataFrame(rdd, ['name', 'age'])
 >>> df.collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 
>>> from pyspark.sql import Row
@@ -294,7 +294,7 @@ 
pyspark.sql module>>> person = rdd.map(lambda r: Person(*r))
 >>> df2 = spark.createDataFrame(person)
 >>> df2.collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 
>>> from pyspark.sql.types import *
@@ -303,17 +303,17 @@ 
pyspark.sql module...    StructField("age", IntegerType(), True)])
 >>> df3 = spark.createDataFrame(rdd, schema)
 >>> df3.collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 
>>> spark.createDataFrame(df.toPandas()).collect()  
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 >>> spark.createDataFrame(pandas.DataFrame([[1, 2]])).collect()  
 [Row(0=1, 1=2)]
 
>>> spark.createDataFrame(rdd, "a: string, b: int").collect()
-[Row(a=u'Alice', b=1)]
+[Row(a='Alice', b=1)]
 >>> rdd = rdd.map(lambda row: row[1])
 >>> spark.createDataFrame(rdd, "int").collect()
 [Row(value=1)]
@@ -440,7 +440,7 @@ 
pyspark.sql module
>>> df.createOrReplaceTempView("table1")
 >>> df2 = spark.sql("SELECT field1 AS f1, field2 as f2 from table1")
 >>> df2.collect()
-[Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
+[Row(f1=1, f2='row1'), Row(f1=2, f2='row2'), Row(f1=3, f2='row3')]
@@ -621,22 +621,22 @@

pyspark.sql module
>>> l = [('Alice', 1)]
 >>> sqlContext.createDataFrame(l).collect()
-[Row(_1=u'Alice', _2=1)]
+[Row(_1='Alice', _2=1)]
 >>> sqlContext.createDataFrame(l, ['name', 'age']).collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 

>>> d = [{'name': 'Alice', 'age': 1}]
 >>> sqlContext.createDataFrame(d).collect()
-[Row(age=1, name=u'Alice')]
+[Row(age=1, name='Alice')]
 
>>> rdd = sc.parallelize(l)
 >>> sqlContext.createDataFrame(rdd).collect()
-[Row(_1=u'Alice', _2=1)]
+[Row(_1='Alice', _2=1)]
 >>> df = sqlContext.createDataFrame(rdd, ['name', 'age'])
 >>> df.collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 
>>> from pyspark.sql import Row
@@ -644,7 +644,7 @@ 
pyspark.sql module>>> person = rdd.map(lambda r: Person(*r))
 >>> df2 = sqlContext.createDataFrame(person)
 >>> df2.collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 
>>> from pyspark.sql.types import *
@@ -653,17 +653,17 @@ 
pyspark.sql module...    StructField("age", IntegerType(), True)])
 >>> df3 = sqlContext.createDataFrame(rdd, schema)
 >>> df3.collect()
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 
>>> sqlContext.createDataFrame(df.toPandas()).collect()  
-[Row(name=u'Alice', age=1)]
+[Row(name='Alice', age=1)]
 >>> sqlContext.createDataFrame(pandas.DataFrame([[1, 2]])).collect()  
 [Row(0=1, 1=2)]
 
>>> sqlContext.createDataFrame(rdd, "a: string, b: int").collect()
-[Row(a=u'Alice', b=1)]
+[Row(a='Alice', b=1)]
 >>> rdd = rdd.map(lambda row: row[1])
 >>> sqlContext.createDataFrame(rdd, "int").collect()
 [Row(value=1)]
@@ -722,12 +722,12 @@ 
pyspark.sql module
>>> sqlContext.getConf("spark.sql.shuffle.partitions")
-u'200'
+'200'
 >>> sqlContext.getConf("spark.sql.shuffle.partitions", u"10")
-u'10'
+'10'
 >>> sqlContext.setConf("spark.sql.shuffle.partitions", u"50")
 >>> sqlContext.getConf("spark.sql.shuffle.partitions", u"10")
-u'50'
+'50'
@@ -881,7 +881,7 @@

pyspark.sql module
>>> sqlContext.registerFunction("stringLengthString", lambda x: len(x))
 >>> sqlContext.sql("SELECT stringLengthString('test')").collect()
-[Row(stringLengthString(test)=u'4')]
+[Row(stringLengthString(test)='4')]
 

>>> from pyspark.sql.types import IntegerType
@@ -949,7 +949,7 @@ 
pyspark.sql module
>>> sqlContext.registerDataFrameAsTable(df, "table1")
 >>> df2 = sqlContext.sql("SELECT field1 AS f1, field2 as f2 from table1")
 >>> df2.collect()
-[Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
+[Row(f1=1, f2='row1'), Row(f1=2, f2='row2'), Row(f1=3, f2='row3')]
@@ -1040,7 +1040,7 @@

pyspark.sql module
>>> sqlContext.registerDataFrameAsTable(df, "table1")
 >>> df2 = sqlContext.tables()
 >>> df2.filter("tableName = 'table1'").first()
-Row(database=u'', tableName=u'table1', isTemporary=True)
+Row(database='', tableName='table1', isTemporary=True)

@@ -1138,7 +1138,7 @@

pyspark.sql module
>>> sqlContext.registerFunction("stringLengthString", lambda x: len(x))
 >>> sqlContext.sql("SELECT stringLengthString('test')").collect()
-[Row(stringLengthString(test)=u'4')]
+[Row(stringLengthString(test)='4')]
 

>>> from pyspark.sql.types import IntegerType
@@ -1213,7 +1213,7 @@ 
pyspark.sql module>>> df_as2 = df.alias("df_as2")
 >>> joined_df = df_as1.join(df_as2, col("df_as1.name") == col("df_as2.name"), 'inner')
 >>> joined_df.select("df_as1.name", "df_as2.name", "df_as2.age").collect()
-[Row(name=u'Bob', name=u'Bob', age=5), Row(name=u'Alice', name=u'Alice', age=2)]
+[Row(name='Bob', name='Bob', age=5), Row(name='Alice', name='Alice', age=2)]
@@ -1340,7 +1340,7 @@

pyspark.sql modulecollect()[source]

Returns all the records as a list of Row.

>>> df.collect()
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
@@ -1519,12 +1519,12 @@

pyspark.sql module
>>> df.select("age", "name").collect()
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
 >>> df2.select("name", "height").collect()
-[Row(name=u'Tom', height=80), Row(name=u'Bob', height=85)]
+[Row(name='Tom', height=80), Row(name='Bob', height=85)]
 >>> df.crossJoin(df2.select("height")).select("age", "name", "height").collect()
-[Row(age=2, name=u'Alice', height=80), Row(age=2, name=u'Alice', height=85),
- Row(age=5, name=u'Bob', height=80), Row(age=5, name=u'Bob', height=85)]
+[Row(age=2, name='Alice', height=80), Row(age=2, name='Alice', height=85),
+ Row(age=5, name='Bob', height=80), Row(age=5, name='Bob', height=85)]

@@ -1651,23 +1651,23 @@

pyspark.sql module
>>> df.drop('age').collect()
-[Row(name=u'Alice'), Row(name=u'Bob')]
+[Row(name='Alice'), Row(name='Bob')]
 

>>> df.drop(df.age).collect()
-[Row(name=u'Alice'), Row(name=u'Bob')]
+[Row(name='Alice'), Row(name='Bob')]
 
>>> df.join(df2, df.name == df2.name, 'inner').drop(df.name).collect()
-[Row(age=5, height=85, name=u'Bob')]
+[Row(age=5, height=85, name='Bob')]
 
>>> df.join(df2, df.name == df2.name, 'inner').drop(df2.name).collect()
-[Row(age=5, name=u'Bob', height=85)]
+[Row(age=5, name='Bob', height=85)]
 
>>> df.join(df2, 'name', 'inner').drop('age', 'height').collect()
-[Row(name=u'Bob')]
+[Row(name='Bob')]
@@ -1869,15 +1869,15 @@

pyspark.sql module
>>> df.filter(df.age > 3).collect()
-[Row(age=5, name=u'Bob')]
+[Row(age=5, name='Bob')]
 >>> df.where(df.age == 2).collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]
 

>>> df.filter("age > 3").collect()
-[Row(age=5, name=u'Bob')]
+[Row(age=5, name='Bob')]
 >>> df.where("age = 2").collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]
@@ -1890,7 +1890,7 @@

pyspark.sql modulefirst()[source]

Returns the first row as a Row.

>>> df.first()
-Row(age=2, name=u'Alice')
+Row(age=2, name='Alice')
@@ -1979,11 +1979,11 @@

pyspark.sql module
>>> df.groupBy().avg().collect()
 [Row(avg(age)=3.5)]
 >>> sorted(df.groupBy('name').agg({'age': 'mean'}).collect())
-[Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)]
+[Row(name='Alice', avg(age)=2.0), Row(name='Bob', avg(age)=5.0)]
 >>> sorted(df.groupBy(df.name).avg().collect())
-[Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)]
+[Row(name='Alice', avg(age)=2.0), Row(name='Bob', avg(age)=5.0)]
 >>> sorted(df.groupBy(['name', df.age]).count().collect())
-[Row(name=u'Alice', age=2, count=1), Row(name=u'Bob', age=5, count=1)]
+[Row(name='Alice', age=2, count=1), Row(name='Bob', age=5, count=1)]

@@ -2021,9 +2021,9 @@

pyspark.sql module
>>> df.head()
-Row(age=2, name=u'Alice')
+Row(age=2, name='Alice')
 >>> df.head(1)
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]

@@ -2126,24 +2126,24 @@

pyspark.sql moduledf1 and df2.

>>> df.join(df2, df.name == df2.name, 'outer').select(df.name, df2.height).collect()
-[Row(name=None, height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)]
+[Row(name=None, height=80), Row(name='Bob', height=85), Row(name='Alice', height=None)]
 
>>> df.join(df2, 'name', 'outer').select('name', 'height').collect()
-[Row(name=u'Tom', height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)]
+[Row(name='Tom', height=80), Row(name='Bob', height=85), Row(name='Alice', height=None)]
 
>>> cond = [df.name == df3.name, df.age == df3.age]
 >>> df.join(df3, cond, 'outer').select(df.name, df3.age).collect()
-[Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)]
+[Row(name='Alice', age=2), Row(name='Bob', age=5)]
 
>>> df.join(df2, 'name').select(df.name, df2.height).collect()
-[Row(name=u'Bob', height=85)]
+[Row(name='Bob', height=85)]
 
>>> df.join(df4, ['name', 'age']).select(df.name, df.age).collect()
-[Row(name=u'Bob', age=5)]
+[Row(name='Bob', age=5)]
@@ -2156,7 +2156,7 @@

pyspark.sql modulelimit(num)[source]

Limits the result count to the number specified.

>>> df.limit(1).collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]
 >>> df.limit(0).collect()
 []
@@ -2194,18 +2194,18 @@

pyspark.sql module
>>> df.sort(df.age.desc()).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> df.sort("age", ascending=False).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> df.orderBy(df.age.desc()).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> from pyspark.sql.functions import *
 >>> df.sort(asc("age")).collect()
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
 >>> df.orderBy(desc("age"), "name").collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> df.orderBy(["age", "name"], ascending=[0, 1]).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]

@@ -2528,11 +2528,11 @@

pyspark.sql module
>>> df.select('*').collect()
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
 >>> df.select('name', 'age').collect()
-[Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)]
+[Row(name='Alice', age=2), Row(name='Bob', age=5)]
 >>> df.select(df.name, (df.age + 10).alias('age')).collect()
-[Row(name=u'Alice', age=12), Row(name=u'Bob', age=15)]
+[Row(name='Alice', age=12), Row(name='Bob', age=15)]

@@ -2614,18 +2614,18 @@

pyspark.sql module
>>> df.sort(df.age.desc()).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> df.sort("age", ascending=False).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> df.orderBy(df.age.desc()).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> from pyspark.sql.functions import *
 >>> df.sort(asc("age")).collect()
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
 >>> df.orderBy(desc("age"), "name").collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]
 >>> df.orderBy(["age", "name"], ascending=[0, 1]).collect()
-[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
+[Row(age=5, name='Bob'), Row(age=2, name='Alice')]

@@ -2707,7 +2707,7 @@

pyspark.sql moduletake(num)[source]

Returns the first num rows as a list of Row.

>>> df.take(2)
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
@@ -2728,7 +2728,7 @@

pyspark.sql module
>>> df.toDF('f1', 'f2').collect()
-[Row(f1=2, f2=u'Alice'), Row(f1=5, f2=u'Bob')]
+[Row(f1=2, f2='Alice'), Row(f1=5, f2='Bob')]

@@ -2739,7 +2739,7 @@

pyspark.sql moduleDataFrame into a RDD of string.

Each row is turned into a JSON document as one element in the returned RDD.

>>> df.toJSON().first()
-u'{"age":2,"name":"Alice"}'
+'{"age":2,"name":"Alice"}'
@@ -2753,7 +2753,7 @@

pyspark.sql moduleDataFrame. The iterator will consume as much memory as the largest partition in this DataFrame.

>>> list(df.toLocalIterator())
-[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
+[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
@@ -2851,7 +2851,7 @@

pyspark.sql module
>>> df.withColumn('age2', df.age + 2).collect()
-[Row(age=2, name=u'Alice', age2=4), Row(age=5, name=u'Bob', age2=7)]
+[Row(age=2, name='Alice', age2=4), Row(age=5, name='Bob', age2=7)]

@@ -2877,7 +2877,7 @@

pyspark.sql module
>>> df.withColumnRenamed('age', 'age2').collect()
-[Row(age2=2, name=u'Alice'), Row(age2=5, name=u'Bob')]
+[Row(age2=2, name='Alice'), Row(age2=5, name='Bob')]

@@ -3004,12 +3004,12 @@

pyspark.sql module
>>> gdf = df.groupBy(df.name)
 >>> sorted(gdf.agg({"*": "count"}).collect())
-[Row(name=u'Alice', count(1)=1), Row(name=u'Bob', count(1)=1)]
+[Row(name='Alice', count(1)=1), Row(name='Bob', count(1)=1)]
 

>>> from pyspark.sql import functions as F
 >>> sorted(gdf.agg(F.min(df.age)).collect())
-[Row(name=u'Alice', min(age)=2), Row(name=u'Bob', min(age)=5)]
+[Row(name='Alice', min(age)=2), Row(name='Bob', min(age)=5)]
@@ -3282,9 +3282,9 @@

pyspark.sql modulecast(dataType)[source]

Convert the column into type dataType.

>>> df.select(df.age.cast("string").alias('ages')).collect()
-[Row(ages=u'2'), Row(ages=u'5')]
+[Row(ages='2'), Row(ages='5')]
 >>> df.select(df.age.cast(StringType()).alias('ages')).collect()
-[Row(ages=u'2'), Row(ages=u'5')]
+[Row(ages='2'), Row(ages='5')]
@@ -3317,7 +3317,7 @@

pyspark.sql module
>>> df.filter(df.name.endswith('ice')).collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]
 >>> df.filter(df.name.endswith('ice$')).collect()
 []
@@ -3380,9 +3380,9 @@

pyspark.sql moduleDataFrame.filter() to select rows with non-null values.

>>> from pyspark.sql import Row
->>> df2 = sc.parallelize([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)]).toDF()
+>>> df2 = sc.parallelize([Row(name='Tom', height=80), Row(name='Alice', height=None)]).toDF()
 >>> df2.filter(df2.height.isNotNull()).collect()
-[Row(height=80, name=u'Tom')]
+[Row(height=80, name='Tom')]

@@ -3393,9 +3393,9 @@

pyspark.sql moduleDataFrame.filter() to select rows with null values.

>>> from pyspark.sql import Row
->>> df2 = sc.parallelize([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)]).toDF()
+>>> df2 = sc.parallelize([Row(name='Tom', height=80), Row(name='Alice', height=None)]).toDF()
 >>> df2.filter(df2.height.isNull()).collect()
-[Row(height=None, name=u'Alice')]
+[Row(height=None, name='Alice')]

@@ -3406,9 +3406,9 @@

pyspark.sql module
>>> df[df.name.isin("Bob", "Mike")].collect()
-[Row(age=5, name=u'Bob')]
+[Row(age=5, name='Bob')]
 >>> df[df.age.isin([1, 2, 3])].collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]

@@ -3430,7 +3430,7 @@

pyspark.sql modulerlike() for a regex version

>>> df.filter(df.name.like('Al%')).collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]

@@ -3511,7 +3511,7 @@

pyspark.sql module
>>> df.filter(df.name.rlike('ice$')).collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]

@@ -3529,7 +3529,7 @@

pyspark.sql module
>>> df.filter(df.name.startswith('Al')).collect()
-[Row(age=2, name=u'Alice')]
+[Row(age=2, name='Alice')]
 >>> df.filter(df.name.startswith('^Al')).collect()
 []
@@ -3553,7 +3553,7 @@

pyspark.sql module
>>> df.select(df.name.substr(1, 3).alias("col")).collect()
-[Row(col=u'Ali'), Row(col=u'Bob')]
+[Row(col='Ali'), Row(col='Bob')]

@@ -4134,12 +4134,12 @@

pyspark.sql module
-unboundedFollowing = 9223372036854775807L
+unboundedFollowing = 9223372036854775807
-unboundedPreceding = -9223372036854775808L
+unboundedPreceding = -9223372036854775808
@@ -4676,7 +4676,7 @@

pyspark.sql module
>>> df = spark.read.text('python/test_support/sql/text-test.txt')
 >>> df.collect()
-[Row(value=u'hello'), Row(value=u'this')]
+[Row(value='hello'), Row(value='this')]

@@ -5794,7 +5794,7 @@

pyspark.sql modulepyspark.sql.functions.bin(col)[source]

Returns the string representation of the binary value of the given column.

>>> df.select(bin(df.age).alias('c')).collect()
-[Row(c=u'10'), Row(c=u'101')]
+[Row(c='10'), Row(c='101')]
@@ -5934,7 +5934,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('abcd','123')], ['s', 'd'])
 >>> df.select(concat(df.s, df.d).alias('s')).collect()
-[Row(s=u'abcd123')]
+[Row(s='abcd123')]

@@ -5949,7 +5949,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('abcd','123')], ['s', 'd'])
 >>> df.select(concat_ws('-', df.s, df.d).alias('s')).collect()
-[Row(s=u'abcd-123')]
+[Row(s='abcd-123')]

@@ -5963,7 +5963,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([("010101",)], ['n'])
 >>> df.select(conv(df.n, 2, 16).alias('hex')).collect()
-[Row(hex=u'15')]
+[Row(hex='15')]

@@ -6094,9 +6094,9 @@

pyspark.sql module
>>> df.select(create_map('name', 'age').alias("map")).collect()
-[Row(map={u'Alice': 2}), Row(map={u'Bob': 5})]
+[Row(map={'Alice': 2}), Row(map={'Bob': 5})]
 >>> df.select(create_map([df.name, df.age]).alias("map")).collect()
-[Row(map={u'Alice': 2}), Row(map={u'Bob': 5})]
+[Row(map={'Alice': 2}), Row(map={'Bob': 5})]

@@ -6157,7 +6157,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
 >>> df.select(date_format('a', 'MM/dd/yyy').alias('date')).collect()
-[Row(date=u'04/08/2015')]
+[Row(date='04/08/2015')]

@@ -6380,7 +6380,7 @@

pyspark.sql module
>>> spark.createDataFrame([(5,)], ['a']).select(format_number('a', 4).alias('v')).collect()
-[Row(v=u'5.0000')]
+[Row(v='5.0000')]

@@ -6406,7 +6406,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([(5, "hello")], ['a', 'b'])
 >>> df.select(format_string('%d %s', df.a, df.b).alias('v')).collect()
-[Row(v=u'5 hello')]
+[Row(v='5 hello')]

@@ -6498,7 +6498,7 @@

pyspark.sql module>>> df = spark.createDataFrame(data, ("key", "jstring")) >>> df.select(df.key, get_json_object(df.jstring, '$.f1').alias("c0"), \ ... get_json_object(df.jstring, '$.f2').alias("c1") ).collect() -[Row(key=u'1', c0=u'value1', c1=u'value2'), Row(key=u'2', c0=u'value12', c1=None)] +[Row(key='1', c0='value1', c1='value2'), Row(key='2', c0='value12', c1=None)]

@@ -6587,7 +6587,7 @@

pyspark.sql modulepyspark.sql.types.BinaryType, pyspark.sql.types.IntegerType or pyspark.sql.types.LongType.

>>> spark.createDataFrame([('ABC', 3)], ['a', 'b']).select(hex('a'), hex('b')).collect()
-[Row(hex(a)=u'414243', hex(b)=u'3')]
+[Row(hex(a)='414243', hex(b)='3')]
@@ -6623,7 +6623,7 @@

pyspark.sql modulepyspark.sql.functions.initcap(col)[source]

Translate the first letter of each word to upper case in the sentence.

>>> spark.createDataFrame([('ab cd',)], ['a']).select(initcap("a").alias('v')).collect()
-[Row(v=u'Ab Cd')]
+[Row(v='Ab Cd')]
@@ -6707,7 +6707,7 @@

pyspark.sql module
>>> data = [("1", '''{"f1": "value1", "f2": "value2"}'''), ("2", '''{"f1": "value12"}''')]
 >>> df = spark.createDataFrame(data, ("key", "jstring"))
 >>> df.select(df.key, json_tuple(df.jstring, 'f1', 'f2')).collect()
-[Row(key=u'1', c0=u'value1', c1=u'value2'), Row(key=u'2', c0=u'value12', c1=None)]
+[Row(key='1', c0='value1', c1='value2'), Row(key='2', c0='value12', c1=None)]

@@ -6946,7 +6946,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('abcd',)], ['s',])
 >>> df.select(lpad(df.s, 6, '#').alias('s')).collect()
-[Row(s=u'##abcd')]
+[Row(s='##abcd')]

@@ -6977,7 +6977,7 @@

pyspark.sql modulepyspark.sql.functions.md5(col)[source]

Calculates the MD5 digest and returns the value as a 32 character hex string.

>>> spark.createDataFrame([('ABC',)], ['a']).select(md5('a').alias('hash')).collect()
-[Row(hash=u'902fbdd2b1df0c4f70b4a5d23525e932')]
+[Row(hash='902fbdd2b1df0c4f70b4a5d23525e932')]
@@ -7228,13 +7228,13 @@

pyspark.sql module
>>> df = spark.createDataFrame([('100-200',)], ['str'])
 >>> df.select(regexp_extract('str', '(\d+)-(\d+)', 1).alias('d')).collect()
-[Row(d=u'100')]
+[Row(d='100')]
 >>> df = spark.createDataFrame([('foo',)], ['str'])
 >>> df.select(regexp_extract('str', '(\d+)', 1).alias('d')).collect()
-[Row(d=u'')]
+[Row(d='')]
 >>> df = spark.createDataFrame([('aaaac',)], ['str'])
 >>> df.select(regexp_extract('str', '(a+)(b)?(c)', 2).alias('d')).collect()
-[Row(d=u'')]
+[Row(d='')]

@@ -7248,7 +7248,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('100-200',)], ['str'])
 >>> df.select(regexp_replace('str', '(\d+)', '--').alias('d')).collect()
-[Row(d=u'-----')]
+[Row(d='-----')]

@@ -7262,7 +7262,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('ab',)], ['s',])
 >>> df.select(repeat(df.s, 3).alias('s')).collect()
-[Row(s=u'ababab')]
+[Row(s='ababab')]

@@ -7317,7 +7317,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('abcd',)], ['s',])
 >>> df.select(rpad(df.s, 6, '#').alias('s')).collect()
-[Row(s=u'abcd##')]
+[Row(s='abcd##')]

@@ -7353,7 +7353,7 @@

pyspark.sql modulepyspark.sql.functions.sha1(col)[source]

Returns the hex string result of SHA-1.

>>> spark.createDataFrame([('ABC',)], ['a']).select(sha1('a').alias('hash')).collect()
-[Row(hash=u'3c01bdbb26f358bab27f267924aa2c9a03fcfdb8')]
+[Row(hash='3c01bdbb26f358bab27f267924aa2c9a03fcfdb8')]
@@ -7369,9 +7369,9 @@

pyspark.sql module
>>> digests = df.select(sha2(df.name, 256).alias('s')).collect()
 >>> digests[0]
-Row(s=u'3bc51062973c458d5a6f2d8d64a023246354ad7e064b1e4e009ec8a0699a3043')
+Row(s='3bc51062973c458d5a6f2d8d64a023246354ad7e064b1e4e009ec8a0699a3043')
 >>> digests[1]
-Row(s=u'cd9fb1e148ccd8442e5aa74904cc73bf6fb54d1d54d333bd596aa9bb4bb4e961')
+Row(s='cd9fb1e148ccd8442e5aa74904cc73bf6fb54d1d54d333bd596aa9bb4bb4e961')

@@ -7508,7 +7508,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([("Peters",),("Uhrbach",)], ['name'])
 >>> df.select(soundex(df.name).alias("soundex")).collect()
-[Row(soundex=u'P362'), Row(soundex=u'U612')]
+[Row(soundex='P362'), Row(soundex='U612')]

@@ -7543,7 +7543,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('ab12cd',)], ['s',])
 >>> df.select(split(df.s, '[0-9]+').alias('s')).collect()
-[Row(s=[u'ab', u'cd'])]
+[Row(s=['ab', 'cd'])]

@@ -7600,9 +7600,9 @@

pyspark.sql module
>>> df.select(struct('age', 'name').alias("struct")).collect()
-[Row(struct=Row(age=2, name=u'Alice')), Row(struct=Row(age=5, name=u'Bob'))]
+[Row(struct=Row(age=2, name='Alice')), Row(struct=Row(age=5, name='Bob'))]
 >>> df.select(struct([df.age, df.name]).alias("struct")).collect()
-[Row(struct=Row(age=2, name=u'Alice')), Row(struct=Row(age=5, name=u'Bob'))]
+[Row(struct=Row(age=2, name='Alice')), Row(struct=Row(age=5, name='Bob'))]

@@ -7618,7 +7618,7 @@

pyspark.sql module
>>> df = spark.createDataFrame([('abcd',)], ['s',])
 >>> df.select(substring(df.s, 1, 2).alias('s')).collect()
-[Row(s=u'ab')]
+[Row(s='ab')]

@@ -7635,9 +7635,9 @@

pyspark.sql module
>>> df = spark.createDataFrame([('a.b.c.d',)], ['s'])
 >>> df.select(substring_index(df.s, '.', 2).alias('s')).collect()
-[Row(s=u'a.b')]
+[Row(s='a.b')]
 >>> df.select(substring_index(df.s, '.', -3).alias('s')).collect()
-[Row(s=u'b.c.d')]
+[Row(s='b.c.d')]

@@ -7750,11 +7750,11 @@

pyspark.sql module>>> data = [(1, Row(name='Alice', age=2))] >>> df = spark.createDataFrame(data, ("key", "value")) >>> df.select(to_json(df.value).alias("json")).collect() -[Row(json=u'{"age":2,"name":"Alice"}')] +[Row(json='{"age":2,"name":"Alice"}')] >>> data = [(1, [Row(name='Alice', age=2), Row(name='Bob', age=3)])] >>> df = spark.createDataFrame(data, ("key", "value")) >>> df.select(to_json(df.value).alias("json")).collect() -[Row(json=u'[{"age":2,"name":"Alice"},{"age":3,"name":"Bob"}]')] +[Row(json='[{"age":2,"name":"Alice"},{"age":3,"name":"Bob"}]')]

@@ -7809,7 +7809,7 @@

pyspark.sql module
>>> spark.createDataFrame([('translate',)], ['a']).select(translate('a', "rnlt", "123") \
 ...     .alias('r')).collect()
-[Row(r=u'1a2s3ae')]
+[Row(r='1a2s3ae')]

@@ -8033,7 +8033,7 @@

pyspark.sql module>>> w = df.groupBy(window("date", "5 seconds")).agg(sum("val").alias("sum")) >>> w.select(w.window.start.cast("string").alias("start"), ... w.window.end.cast("string").alias("end"), "sum").collect() -[Row(start=u'2016-03-11 09:00:05', end=u'2016-03-11 09:00:10', sum=1)] +[Row(start='2016-03-11 09:00:05', end='2016-03-11 09:00:10', sum=1)]

@@ -8258,7 +8258,7 @@

pyspark.sql module>>> sqm = spark.streams >>> # get the list of active streaming queries >>> [q.name for q in sqm.active] -[u'this_query'] +['this_query'] >>> sq.stop()

@@ -8297,7 +8297,7 @@

pyspark.sql module
>>> sq = sdf.writeStream.format('memory').queryName('this_query').start()
 >>> sq.name
-u'this_query'
+'this_query'
 >>> sq = spark.streams.get(sq.id)
 >>> sq.isActive
 True
@@ -8942,14 +8942,14 @@ 
pyspark.sql module>>> sq.isActive
 True
 >>> sq.name
-u'this_query'
+'this_query'
 >>> sq.stop()
 >>> sq.isActive
 False
 >>> sq = sdf.writeStream.trigger(processingTime='5 seconds').start(
 ...     queryName='that_query', outputMode="append", format='memory')
 >>> sq.name
-u'that_query'
+'that_query'
 >>> sq.isActive
 True
 >>> sq.stop()
@@ -8962,7 +8962,7 @@ 
pyspark.sql module
 

-trigger(*args, **kwargs)[source]

+trigger(processingTime=None, once=None)[source]
 
Set the trigger for the stream query. If this is not set it will run the query as fast
 as possible, which is equivalent to setting the trigger to processingTime='0 seconds'.

 

diff --git a/site/docs/2.2.2/api/python/pyspark.streaming.html b/site/docs/2.2.2/api/python/pyspark.streaming.html
index 530b54a1d6..ed35209fc8 100644
--- a/site/docs/2.2.2/api/python/pyspark.streaming.html
+++ b/site/docs/2.2.2/api/python/pyspark.streaming.html
@@ -754,7 +754,8 @@ 
pyspark.streaming module
 

 class Java[source]

-

+
Bases: object

+

 

 implements = ['org.apache.spark.streaming.api.java.PythonStreamingListener']

 

diff --git a/site/docs/2.2.2/api/python/searchindex.js b/site/docs/2.2.2/api/python/searchindex.js
index be694ad9f8..650ee97d8f 100644
--- a/site/docs/2.2.2/api/python/searchindex.js
+++ b/site/docs/2.2.2/api/python/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["index","pyspark","pyspark.ml","pyspark.mllib","pyspark.sql","pyspark.streaming"],envversion:52,filenames:["index.rst","pyspark.rst","pyspark.ml.rst","pyspark.mllib.rst","pyspark.sql.rst","pyspark.streaming.rst"],objects:{"":{pyspark:[1,0,0,"-"]},"pyspark.Accumulator":{add:[1,2,1,""],value:[1,3,1,""]},"pyspark.AccumulatorParam":{addInPlace:[1,2,1,""],zero:[1,2,1,""]},"pyspark.BasicProfiler":{profile:[1,2,1,""],stats:[1,2,1,""]},"pyspark.Broadcast":{destroy:[1,2,1,""],dump:[1,2,1,""],load:[1,2,1,""],unpersist:[1,2,1,""],value:[1,3,1,""]},"pyspark.MarshalSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.PickleSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.Profiler":{dump:[1,2,1,""],profile:[1,2,1,""],show:[1,2,1,""],stats:[1,2,1,""]},"pyspark.RDD":{aggregate:[1,2,1,""],aggregateByKey:[1,2,1,""],cache:[1,2,1,""],cartesian:[1,2,1,""],checkpoint:[1,2,1,""],coalesce:[1,2,1,""],cogroup:[1,2,1,""],collect:[1,2,1,""],collectAsMap:[1,2,1,""],combineByKey:[1,2,1,""],context:[1,3,1,""],count:[1,2,1,""],countApprox:[1,2,1,""],countApproxDistinct:[1,2,1,""],countByKey:[1,2,1,""],countByValue:[1,2,1,""],distinct:[1,2,1,""],filter:[1,2,1,""],first:[1,2,1,""],flatMap:[1,2,1,""],flatMapValues:[1,2,1,""],fold:[1,2,1,""],foldByKey:[1,2,1,""],foreach:[1,2,1,""],foreachPartition:[1,2,1,""],fullOuterJoin:[1,2,1,""],getCheckpointFile:[1,2,1,""],getNumPartitions:[1,2,1,""],getStorageLevel:[1,2,1,""],glom:[1,2,1,""],groupBy:[1,2,1,""],groupByKey:[1,2,1,""],groupWith:[1,2,1,""],histogram:[1,2,1,""],id:[1,2,1,""],intersection:[1,2,1,""],isCheckpointed:[1,2,1,""],isEmpty:[1,2,1,""],isLocallyCheckpointed:[1,2,1,""],join:[1,2,1,""],keyBy:[1,2,1,""],keys:[1,2,1,""],leftOuterJoin:[1,2,1,""],localCheckpoint:[1,2,1,""],lookup:[1,2,1,""],map:[1,2,1,""],mapPartitions:[1,2,1,""],mapPartitionsWithIndex:[1,2,1,""],mapPartitionsWithSplit:[1,2,1,""],mapValues:[1,2,1,""],max:[1,2,1,""],mean:[1,2,1,""],meanApprox:[1,2,1,""],min:[1,2,1,""],name:[1,2,1,""],partitionBy:[1,2,1,""],persist:[1,2,1,""],pipe:[1,2,1,""],randomSplit:[1,2,1,""],reduce:[1,2,1,""],reduceByKey:[1,2,1,""],reduceByKeyLocally:[1,2,1,""],repartition:[1,2,1,""],repartitionAndSortWithinPartitions:[1,2,1,""],rightOuterJoin:[1,2,1,""],sample:[1,2,1,""],sampleByKey:[1,2,1,""],sampleStdev:[1,2,1,""],sampleVariance:[1,2,1,""],saveAsHadoopDataset:[1,2,1,""],saveAsHadoopFile:[1,2,1,""],saveAsNewAPIHadoopDataset:[1,2,1,""],saveAsNewAPIHadoopFile:[1,2,1,""],saveAsPickleFile:[1,2,1,""],saveAsSequenceFile:[1,2,1,""],saveAsTextFile:[1,2,1,""],setName:[1,2,1,""],sortBy:[1,2,1,""],sortByKey:[1,2,1,""],stats:[1,2,1,""],stdev:[1,2,1,""],subtract:[1,2,1,""],subtractByKey:[1,2,1,""],sum:[1,2,1,""],sumApprox:[1,2,1,""],take:[1,2,1,""],takeOrdered:[1,2,1,""],takeSample:[1,2,1,""],toDebugString:[1,2,1,""],toLocalIterator:[1,2,1,""],top:[1,2,1,""],treeAggregate:[1,2,1,""],treeReduce:[1,2,1,""],union:[1,2,1,""],unpersist:[1,2,1,""],values:[1,2,1,""],variance:[1,2,1,""],zip:[1,2,1,""],zipWithIndex:[1,2,1,""],zipWithUniqueId:[1,2,1,""]},"pyspark.SparkConf":{contains:[1,2,1,""],get:[1,2,1,""],getAll:[1,2,1,""],set:[1,2,1,""],setAll:[1,2,1,""],setAppName:[1,2,1,""],setExecutorEnv:[1,2,1,""],setIfMissing:[1,2,1,""],setMaster:[1,2,1,""],setSparkHome:[1,2,1,""],toDebugString:[1,2,1,""]},"pyspark.SparkContext":{PACKAGE_EXTENSIONS:[1,3,1,""],accumulator:[1,2,1,""],addFile:[1,2,1,""],addPyFile:[1,2,1,""],applicationId:[1,3,1,""],binaryFiles:[1,2,1,""],binaryRecords:[1,2,1,""],broadcast:[1,2,1,""],cancelAllJobs:[1,2,1,""],cancelJobGroup:[1,2,1,""],defaultMinPartitions:[1,3,1,""],defaultParallelism:[1,3,1,""],dump_profiles:[1,2,1,""],emptyRDD:[1,2,1,""],getConf:[1,2,1,""],getLocalProperty:[1,2,1,""],getOrCreate:[1,4,1,""],hadoopFile:[1,2,1,""],hadoopRDD:[1,2,1,""],newAPIHadoopFile:[1,2,1,""],newAPIHadoopRDD:[1,2,1,""],parallelize:[1,2,1,""],pickleFile:[1,2,1,""],range:[1,2,1,""],runJob:[1,2,1,""],sequenceFile:[1,2,1,""],setCheckpointDir:[1,2,1,""],setJobGroup:[1,2,1,""],setLocalProperty:[1,2,1,""],setLogLevel:[1,2,1,""],setSystemProperty:[1,4,1,""],show_profiles:[1,2,1,""],sparkUser:[1,2,1,""],startTime:[1,3,1,""],statusTracker:[1,2,1,""],stop:[1,2,1,""],textFile:[1,2,1,""],uiWebUrl:[1,3,1,""],union:[1,2,1,""],version:[1,3,1,""],wholeTextFiles:[1,2,1,""]},"pyspark.SparkFiles":{get:[1,4,1,""],getRootDirectory:[1,4,1,""]},"pyspark.StatusTracker":{getActiveJobsIds:[1,2,1,""],getActiveStageIds:[1,2,1,""],getJobIdsForGroup:[1,2,1,""],getJobInfo:[1,2,1,""],getStageInfo:[1,2,1,""]},"pyspark.StorageLevel":{DISK_ONLY:[1,3,1,""],DISK_ONLY_2:[1,3,1,""],MEMORY_AND_DISK:[1,3,1,""],MEMORY_AND_DISK_2:[1,3,1,""],MEMORY_AND_DISK_SER:[1,3,1,""],MEMORY_AND_DISK_SER_2:[1,3,1,""],MEMORY_ONLY:[1,3,1,""],MEMORY_ONLY_2:[1,3,1,""],MEMORY_ONLY_SER:[1,3,1,""],MEMORY_ONLY_SER_2:[1,3,1,""],OFF_HEAP:[1,3,1,""]},"pyspark.TaskContext":{attemptNumber:[1,2,1,""],get:[1,4,1,""],partitionId:[1,2,1,""],stageId:[1,2,1,""],taskAttemptId:[1,2,1,""]},"pyspark.ml":{Estimator:[2,1,1,""],Model:[2,1,1,""],Pipeline:[2,1,1,""],PipelineModel:[2,1,1,""],Transformer:[2,1,1,""],classification:[2,0,0,"-"],clustering:[2,0,0,"-"],evaluation:[2,0,0,"-"],feature:[2,0,0,"-"],fpm:[2,0,0,"-"],linalg:[2,0,0,"-"],param:[2,0,0,"-"],recommendation:[2,0,0,"-"],regression:[2,0,0,"-"],stat:[2,0,0,"-"],tuning:[2,0,0,"-"],util:[2,0,0,"-"]},"pyspark.ml.Estimator":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.Model":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],transform:[2,2,1,""]},"pyspark.ml.Pipeline":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getStages:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setParams:[2,2,1,""],setStages:[2,2,1,""],stages:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.PipelineModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.Transformer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],transform:[2,2,1,""]},"pyspark.ml.classification":{BinaryLogisticRegressionSummary:[2,1,1,""],BinaryLogisticRegressionTrainingSummary:[2,1,1,""],DecisionTreeClassificationModel:[2,1,1,""],DecisionTreeClassifier:[2,1,1,""],GBTClassificationModel:[2,1,1,""],GBTClassifier:[2,1,1,""],LinearSVC:[2,1,1,""],LinearSVCModel:[2,1,1,""],LogisticRegression:[2,1,1,""],LogisticRegressionModel:[2,1,1,""],LogisticRegressionSummary:[2,1,1,""],LogisticRegressionTrainingSummary:[2,1,1,""],MultilayerPerceptronClassificationModel:[2,1,1,""],MultilayerPerceptronClassifier:[2,1,1,""],NaiveBayes:[2,1,1,""],NaiveBayesModel:[2,1,1,""],OneVsRest:[2,1,1,""],OneVsRestModel:[2,1,1,""],RandomForestClassificationModel:[2,1,1,""],RandomForestClassifier:[2,1,1,""]},"pyspark.ml.classification.BinaryLogisticRegressionSummary":{areaUnderROC:[2,3,1,""],fMeasureByThreshold:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],pr:[2,3,1,""],precisionByThreshold:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],recallByThreshold:[2,3,1,""],roc:[2,3,1,""]},"pyspark.ml.classification.BinaryLogisticRegressionTrainingSummary":{areaUnderROC:[2,3,1,""],fMeasureByThreshold:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],objectiveHistory:[2,3,1,""],pr:[2,3,1,""],precisionByThreshold:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],recallByThreshold:[2,3,1,""],roc:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.classification.DecisionTreeClassificationModel":{copy:[2,2,1,""],depth:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.DecisionTreeClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.GBTClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.GBTClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getLossType:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setLossType:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setSubsamplingRate:[2,2,1,""],stepSize:[2,3,1,""],subsamplingRate:[2,3,1,""],supportedLossTypes:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LinearSVC":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getStandardization:[2,2,1,""],getThreshold:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setStandardization:[2,2,1,""],setThreshold:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],standardization:[2,3,1,""],threshold:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LinearSVCModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegression":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],elasticNetParam:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],family:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getElasticNetParam:[2,2,1,""],getFamily:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getStandardization:[2,2,1,""],getThreshold:[2,2,1,""],getThresholds:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setElasticNetParam:[2,2,1,""],setFamily:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setStandardization:[2,2,1,""],setThreshold:[2,2,1,""],setThresholds:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],standardization:[2,3,1,""],threshold:[2,3,1,""],thresholds:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegressionModel":{coefficientMatrix:[2,3,1,""],coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],interceptVector:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegressionSummary":{featuresCol:[2,3,1,""],labelCol:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""]},"pyspark.ml.classification.LogisticRegressionTrainingSummary":{featuresCol:[2,3,1,""],labelCol:[2,3,1,""],objectiveHistory:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.classification.MultilayerPerceptronClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],layers:[2,3,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],weights:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.MultilayerPerceptronClassifier":{blockSize:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getBlockSize:[2,2,1,""],getFeaturesCol:[2,2,1,""],getInitialWeights:[2,2,1,""],getLabelCol:[2,2,1,""],getLayers:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSolver:[2,2,1,""],getStepSize:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],initialWeights:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],layers:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBlockSize:[2,2,1,""],setFeaturesCol:[2,2,1,""],setInitialWeights:[2,2,1,""],setLabelCol:[2,2,1,""],setLayers:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSolver:[2,2,1,""],setStepSize:[2,2,1,""],setTol:[2,2,1,""],solver:[2,3,1,""],stepSize:[2,3,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.NaiveBayes":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getModelType:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSmoothing:[2,2,1,""],getThresholds:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],modelType:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setModelType:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSmoothing:[2,2,1,""],setThresholds:[2,2,1,""],setWeightCol:[2,2,1,""],smoothing:[2,3,1,""],thresholds:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.NaiveBayesModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],pi:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],theta:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.OneVsRest":{classifier:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getClassifier:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setClassifier:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.OneVsRestModel":{classifier:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],getClassifier:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setClassifier:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],transform:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.RandomForestClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.RandomForestClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatureSubsetStrategy:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getNumTrees:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],numTrees:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeatureSubsetStrategy:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setNumTrees:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],subsamplingRate:[2,3,1,""],supportedFeatureSubsetStrategies:[2,3,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering":{BisectingKMeans:[2,1,1,""],BisectingKMeansModel:[2,1,1,""],BisectingKMeansSummary:[2,1,1,""],DistributedLDAModel:[2,1,1,""],GaussianMixture:[2,1,1,""],GaussianMixtureModel:[2,1,1,""],GaussianMixtureSummary:[2,1,1,""],KMeans:[2,1,1,""],KMeansModel:[2,1,1,""],LDA:[2,1,1,""],LDAModel:[2,1,1,""],LocalLDAModel:[2,1,1,""]},"pyspark.ml.clustering.BisectingKMeans":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getMinDivisibleClusterSize:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],minDivisibleClusterSize:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setMinDivisibleClusterSize:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.BisectingKMeansModel":{clusterCenters:[2,2,1,""],computeCost:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.BisectingKMeansSummary":{cluster:[2,3,1,""],clusterSizes:[2,3,1,""],featuresCol:[2,3,1,""],k:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""]},"pyspark.ml.clustering.DistributedLDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getCheckpointFiles:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],logPrior:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toLocal:[2,2,1,""],topicsMatrix:[2,2,1,""],trainingLogLikelihood:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixture":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getSeed:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setSeed:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixtureModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],gaussiansDF:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],weights:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixtureSummary":{cluster:[2,3,1,""],clusterSizes:[2,3,1,""],featuresCol:[2,3,1,""],k:[2,3,1,""],logLikelihood:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],probability:[2,3,1,""],probabilityCol:[2,3,1,""]},"pyspark.ml.clustering.KMeans":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getInitMode:[2,2,1,""],getInitSteps:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],initMode:[2,3,1,""],initSteps:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setInitMode:[2,2,1,""],setInitSteps:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.KMeansModel":{clusterCenters:[2,2,1,""],computeCost:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.LDA":{checkpointInterval:[2,3,1,""],copy:[2,2,1,""],docConcentration:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getDocConcentration:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getKeepLastCheckpoint:[2,2,1,""],getLearningDecay:[2,2,1,""],getLearningOffset:[2,2,1,""],getMaxIter:[2,2,1,""],getOptimizeDocConcentration:[2,2,1,""],getOptimizer:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],getTopicConcentration:[2,2,1,""],getTopicDistributionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],keepLastCheckpoint:[2,3,1,""],learningDecay:[2,3,1,""],learningOffset:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],optimizeDocConcentration:[2,3,1,""],optimizer:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCheckpointInterval:[2,2,1,""],setDocConcentration:[2,2,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setKeepLastCheckpoint:[2,2,1,""],setLearningDecay:[2,2,1,""],setLearningOffset:[2,2,1,""],setMaxIter:[2,2,1,""],setOptimizeDocConcentration:[2,2,1,""],setOptimizer:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],setTopicConcentration:[2,2,1,""],setTopicDistributionCol:[2,2,1,""],subsamplingRate:[2,3,1,""],topicConcentration:[2,3,1,""],topicDistributionCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.LDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],topicsMatrix:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""]},"pyspark.ml.clustering.LocalLDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],topicsMatrix:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation":{BinaryClassificationEvaluator:[2,1,1,""],Evaluator:[2,1,1,""],MulticlassClassificationEvaluator:[2,1,1,""],RegressionEvaluator:[2,1,1,""]},"pyspark.ml.evaluation.BinaryClassificationEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getRawPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setRawPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation.Evaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.evaluation.MulticlassClassificationEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation.RegressionEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature":{Binarizer:[2,1,1,""],BucketedRandomProjectionLSH:[2,1,1,""],BucketedRandomProjectionLSHModel:[2,1,1,""],Bucketizer:[2,1,1,""],ChiSqSelector:[2,1,1,""],ChiSqSelectorModel:[2,1,1,""],CountVectorizer:[2,1,1,""],CountVectorizerModel:[2,1,1,""],DCT:[2,1,1,""],ElementwiseProduct:[2,1,1,""],HashingTF:[2,1,1,""],IDF:[2,1,1,""],IDFModel:[2,1,1,""],Imputer:[2,1,1,""],ImputerModel:[2,1,1,""],IndexToString:[2,1,1,""],MaxAbsScaler:[2,1,1,""],MaxAbsScalerModel:[2,1,1,""],MinHashLSH:[2,1,1,""],MinHashLSHModel:[2,1,1,""],MinMaxScaler:[2,1,1,""],MinMaxScalerModel:[2,1,1,""],NGram:[2,1,1,""],Normalizer:[2,1,1,""],OneHotEncoder:[2,1,1,""],PCA:[2,1,1,""],PCAModel:[2,1,1,""],PolynomialExpansion:[2,1,1,""],QuantileDiscretizer:[2,1,1,""],RFormula:[2,1,1,""],RFormulaModel:[2,1,1,""],RegexTokenizer:[2,1,1,""],SQLTransformer:[2,1,1,""],StandardScaler:[2,1,1,""],StandardScalerModel:[2,1,1,""],StopWordsRemover:[2,1,1,""],StringIndexer:[2,1,1,""],StringIndexerModel:[2,1,1,""],Tokenizer:[2,1,1,""],VectorAssembler:[2,1,1,""],VectorIndexer:[2,1,1,""],VectorIndexerModel:[2,1,1,""],VectorSlicer:[2,1,1,""],Word2Vec:[2,1,1,""],Word2VecModel:[2,1,1,""]},"pyspark.ml.feature.Binarizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getThreshold:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setThreshold:[2,2,1,""],threshold:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.BucketedRandomProjectionLSH":{bucketLength:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getBucketLength:[2,2,1,""],getInputCol:[2,2,1,""],getNumHashTables:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numHashTables:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBucketLength:[2,2,1,""],setInputCol:[2,2,1,""],setNumHashTables:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.BucketedRandomProjectionLSHModel":{approxNearestNeighbors:[2,2,1,""],approxSimilarityJoin:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Bucketizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSplits:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSplits:[2,2,1,""],splits:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ChiSqSelector":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fdr:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fpr:[2,3,1,""],fwe:[2,3,1,""],getFdr:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFpr:[2,2,1,""],getFwe:[2,2,1,""],getLabelCol:[2,2,1,""],getNumTopFeatures:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getPercentile:[2,2,1,""],getSelectorType:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],numTopFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],percentile:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],selectorType:[2,3,1,""],setFdr:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFpr:[2,2,1,""],setFwe:[2,2,1,""],setLabelCol:[2,2,1,""],setNumTopFeatures:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setPercentile:[2,2,1,""],setSelectorType:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ChiSqSelectorModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],selectedFeatures:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.CountVectorizer":{binary:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getBinary:[2,2,1,""],getInputCol:[2,2,1,""],getMinDF:[2,2,1,""],getMinTF:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getVocabSize:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],minDF:[2,3,1,""],minTF:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setBinary:[2,2,1,""],setInputCol:[2,2,1,""],setMinDF:[2,2,1,""],setMinTF:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setVocabSize:[2,2,1,""],vocabSize:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.CountVectorizerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],vocabulary:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.DCT":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getInverse:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],inverse:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setInverse:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ElementwiseProduct":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getScalingVec:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],scalingVec:[2,3,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setScalingVec:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.HashingTF":{binary:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getBinary:[2,2,1,""],getInputCol:[2,2,1,""],getNumFeatures:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setBinary:[2,2,1,""],setInputCol:[2,2,1,""],setNumFeatures:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IDF":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMinDocFreq:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],minDocFreq:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMinDocFreq:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IDFModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],idf:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Imputer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCols:[2,2,1,""],getMissingValue:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCols:[2,2,1,""],getParam:[2,2,1,""],getStrategy:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCols:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],missingValue:[2,3,1,""],outputCols:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCols:[2,2,1,""],setMissingValue:[2,2,1,""],setOutputCols:[2,2,1,""],setParams:[2,2,1,""],setStrategy:[2,2,1,""],strategy:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ImputerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],surrogateDF:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IndexToString":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getLabels:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labels:[2,3,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setLabels:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MaxAbsScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MaxAbsScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],maxAbs:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinHashLSH":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getNumHashTables:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numHashTables:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInputCol:[2,2,1,""],setNumHashTables:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinHashLSHModel":{approxNearestNeighbors:[2,2,1,""],approxSimilarityJoin:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinMaxScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMax:[2,2,1,""],getMin:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],max:[2,3,1,""],min:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMax:[2,2,1,""],setMin:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinMaxScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],originalMax:[2,3,1,""],originalMin:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.NGram":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getN:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],n:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setN:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Normalizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getP:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],p:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setP:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.OneHotEncoder":{copy:[2,2,1,""],dropLast:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getDropLast:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setDropLast:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PCA":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getK:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setK:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PCAModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],explainedVariance:[2,3,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],pc:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PolynomialExpansion":{copy:[2,2,1,""],degree:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getDegree:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setDegree:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.QuantileDiscretizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getNumBuckets:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getRelativeError:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numBuckets:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],relativeError:[2,3,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setNumBuckets:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setRelativeError:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RFormula":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],forceIndexLabel:[2,3,1,""],formula:[2,3,1,""],getFeaturesCol:[2,2,1,""],getForceIndexLabel:[2,2,1,""],getFormula:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeaturesCol:[2,2,1,""],setForceIndexLabel:[2,2,1,""],setFormula:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RFormulaModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RegexTokenizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],gaps:[2,3,1,""],getGaps:[2,2,1,""],getInputCol:[2,2,1,""],getMinTokenLength:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getPattern:[2,2,1,""],getToLowercase:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],minTokenLength:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],pattern:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setGaps:[2,2,1,""],setInputCol:[2,2,1,""],setMinTokenLength:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setPattern:[2,2,1,""],setToLowercase:[2,2,1,""],toLowercase:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.SQLTransformer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getStatement:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setParams:[2,2,1,""],setStatement:[2,2,1,""],statement:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StandardScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getWithMean:[2,2,1,""],getWithStd:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setWithMean:[2,2,1,""],setWithStd:[2,2,1,""],withMean:[2,3,1,""],withStd:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StandardScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],mean:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],std:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StopWordsRemover":{caseSensitive:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getCaseSensitive:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getStopWords:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],loadDefaultStopWords:[2,5,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setCaseSensitive:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setStopWords:[2,2,1,""],stopWords:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StringIndexer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StringIndexerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labels:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Tokenizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorAssembler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCols:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCols:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCols:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorIndexer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMaxCategories:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],maxCategories:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMaxCategories:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorIndexerModel":{categoryMaps:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorSlicer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getIndices:[2,2,1,""],getInputCol:[2,2,1,""],getNames:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],indices:[2,3,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],names:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setIndices:[2,2,1,""],setInputCol:[2,2,1,""],setNames:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Word2Vec":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxSentenceLength:[2,2,1,""],getMinCount:[2,2,1,""],getNumPartitions:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getVectorSize:[2,2,1,""],getWindowSize:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],maxSentenceLength:[2,3,1,""],minCount:[2,3,1,""],numPartitions:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInputCol:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxSentenceLength:[2,2,1,""],setMinCount:[2,2,1,""],setNumPartitions:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setVectorSize:[2,2,1,""],setWindowSize:[2,2,1,""],stepSize:[2,3,1,""],vectorSize:[2,3,1,""],windowSize:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Word2VecModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],findSynonyms:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getVectors:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.fpm":{FPGrowth:[2,1,1,""],FPGrowthModel:[2,1,1,""]},"pyspark.ml.fpm.FPGrowth":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getItemsCol:[2,2,1,""],getMinConfidence:[2,2,1,""],getMinSupport:[2,2,1,""],getNumPartitions:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemsCol:[2,3,1,""],load:[2,4,1,""],minConfidence:[2,3,1,""],minSupport:[2,3,1,""],numPartitions:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setItemsCol:[2,2,1,""],setMinConfidence:[2,2,1,""],setMinSupport:[2,2,1,""],setNumPartitions:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.fpm.FPGrowthModel":{associationRules:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],freqItemsets:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.linalg":{DenseMatrix:[2,1,1,""],DenseVector:[2,1,1,""],Matrices:[2,1,1,""],Matrix:[2,1,1,""],SparseMatrix:[2,1,1,""],SparseVector:[2,1,1,""],Vector:[2,1,1,""],Vectors:[2,1,1,""]},"pyspark.ml.linalg.DenseMatrix":{toArray:[2,2,1,""],toSparse:[2,2,1,""]},"pyspark.ml.linalg.DenseVector":{dot:[2,2,1,""],norm:[2,2,1,""],numNonzeros:[2,2,1,""],squared_distance:[2,2,1,""],toArray:[2,2,1,""],values:[2,3,1,""]},"pyspark.ml.linalg.Matrices":{dense:[2,5,1,""],sparse:[2,5,1,""]},"pyspark.ml.linalg.Matrix":{toArray:[2,2,1,""]},"pyspark.ml.linalg.SparseMatrix":{toArray:[2,2,1,""],toDense:[2,2,1,""]},"pyspark.ml.linalg.SparseVector":{dot:[2,2,1,""],indices:[2,3,1,""],norm:[2,2,1,""],numNonzeros:[2,2,1,""],size:[2,3,1,""],squared_distance:[2,2,1,""],toArray:[2,2,1,""],values:[2,3,1,""]},"pyspark.ml.linalg.Vector":{toArray:[2,2,1,""]},"pyspark.ml.linalg.Vectors":{dense:[2,5,1,""],norm:[2,5,1,""],sparse:[2,5,1,""],squared_distance:[2,5,1,""],zeros:[2,5,1,""]},"pyspark.ml.param":{Param:[2,1,1,""],Params:[2,1,1,""],TypeConverters:[2,1,1,""]},"pyspark.ml.param.Params":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.param.TypeConverters":{identity:[2,5,1,""],toBoolean:[2,5,1,""],toFloat:[2,5,1,""],toInt:[2,5,1,""],toList:[2,5,1,""],toListFloat:[2,5,1,""],toListInt:[2,5,1,""],toListString:[2,5,1,""],toString:[2,5,1,""],toVector:[2,5,1,""]},"pyspark.ml.recommendation":{ALS:[2,1,1,""],ALSModel:[2,1,1,""]},"pyspark.ml.recommendation.ALS":{alpha:[2,3,1,""],checkpointInterval:[2,3,1,""],coldStartStrategy:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],finalStorageLevel:[2,3,1,""],fit:[2,2,1,""],getAlpha:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getColdStartStrategy:[2,2,1,""],getFinalStorageLevel:[2,2,1,""],getImplicitPrefs:[2,2,1,""],getIntermediateStorageLevel:[2,2,1,""],getItemCol:[2,2,1,""],getMaxIter:[2,2,1,""],getNonnegative:[2,2,1,""],getNumItemBlocks:[2,2,1,""],getNumUserBlocks:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRank:[2,2,1,""],getRatingCol:[2,2,1,""],getRegParam:[2,2,1,""],getSeed:[2,2,1,""],getUserCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],implicitPrefs:[2,3,1,""],intermediateStorageLevel:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],nonnegative:[2,3,1,""],numItemBlocks:[2,3,1,""],numUserBlocks:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],rank:[2,3,1,""],ratingCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],seed:[2,3,1,""],setAlpha:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setColdStartStrategy:[2,2,1,""],setFinalStorageLevel:[2,2,1,""],setImplicitPrefs:[2,2,1,""],setIntermediateStorageLevel:[2,2,1,""],setItemCol:[2,2,1,""],setMaxIter:[2,2,1,""],setNonnegative:[2,2,1,""],setNumBlocks:[2,2,1,""],setNumItemBlocks:[2,2,1,""],setNumUserBlocks:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRank:[2,2,1,""],setRatingCol:[2,2,1,""],setRegParam:[2,2,1,""],setSeed:[2,2,1,""],setUserCol:[2,2,1,""],userCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.recommendation.ALSModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemFactors:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],rank:[2,3,1,""],read:[2,4,1,""],recommendForAllItems:[2,2,1,""],recommendForAllUsers:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],userFactors:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression":{AFTSurvivalRegression:[2,1,1,""],AFTSurvivalRegressionModel:[2,1,1,""],DecisionTreeRegressionModel:[2,1,1,""],DecisionTreeRegressor:[2,1,1,""],GBTRegressionModel:[2,1,1,""],GBTRegressor:[2,1,1,""],GeneralizedLinearRegression:[2,1,1,""],GeneralizedLinearRegressionModel:[2,1,1,""],GeneralizedLinearRegressionSummary:[2,1,1,""],GeneralizedLinearRegressionTrainingSummary:[2,1,1,""],IsotonicRegression:[2,1,1,""],IsotonicRegressionModel:[2,1,1,""],LinearRegression:[2,1,1,""],LinearRegressionModel:[2,1,1,""],LinearRegressionSummary:[2,1,1,""],LinearRegressionTrainingSummary:[2,1,1,""],RandomForestRegressionModel:[2,1,1,""],RandomForestRegressor:[2,1,1,""]},"pyspark.ml.regression.AFTSurvivalRegression":{aggregationDepth:[2,3,1,""],censorCol:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getCensorCol:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getQuantileProbabilities:[2,2,1,""],getQuantilesCol:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],quantileProbabilities:[2,3,1,""],quantilesCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setCensorCol:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setQuantileProbabilities:[2,2,1,""],setQuantilesCol:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.AFTSurvivalRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],predict:[2,2,1,""],predictQuantiles:[2,2,1,""],read:[2,4,1,""],save:[2,2,1,""],scale:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.DecisionTreeRegressionModel":{copy:[2,2,1,""],depth:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.DecisionTreeRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getVarianceCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setVarianceCol:[2,2,1,""],supportedImpurities:[2,3,1,""],varianceCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GBTRegressionModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GBTRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getLossType:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setLossType:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setSubsamplingRate:[2,2,1,""],stepSize:[2,3,1,""],subsamplingRate:[2,3,1,""],supportedImpurities:[2,3,1,""],supportedLossTypes:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegression":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],family:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getFamily:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getLink:[2,2,1,""],getLinkPower:[2,2,1,""],getLinkPredictionCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getSolver:[2,2,1,""],getTol:[2,2,1,""],getVariancePower:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],link:[2,3,1,""],linkPower:[2,3,1,""],linkPredictionCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setFamily:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setLink:[2,2,1,""],setLinkPower:[2,2,1,""],setLinkPredictionCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setSolver:[2,2,1,""],setTol:[2,2,1,""],setVariancePower:[2,2,1,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],tol:[2,3,1,""],variancePower:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionSummary":{aic:[2,3,1,""],degreesOfFreedom:[2,3,1,""],deviance:[2,3,1,""],dispersion:[2,3,1,""],nullDeviance:[2,3,1,""],numInstances:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],rank:[2,3,1,""],residualDegreeOfFreedom:[2,3,1,""],residualDegreeOfFreedomNull:[2,3,1,""],residuals:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionTrainingSummary":{aic:[2,3,1,""],coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],deviance:[2,3,1,""],dispersion:[2,3,1,""],nullDeviance:[2,3,1,""],numInstances:[2,3,1,""],numIterations:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],rank:[2,3,1,""],residualDegreeOfFreedom:[2,3,1,""],residualDegreeOfFreedomNull:[2,3,1,""],residuals:[2,2,1,""],solver:[2,3,1,""],tValues:[2,3,1,""]},"pyspark.ml.regression.IsotonicRegression":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureIndex:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeatureIndex:[2,2,1,""],getFeaturesCol:[2,2,1,""],getIsotonic:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],isotonic:[2,3,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeatureIndex:[2,2,1,""],setFeaturesCol:[2,2,1,""],setIsotonic:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.IsotonicRegressionModel":{boundaries:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],predictions:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegression":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],elasticNetParam:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getElasticNetParam:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getSolver:[2,2,1,""],getStandardization:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setElasticNetParam:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setSolver:[2,2,1,""],setStandardization:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],standardization:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionSummary":{coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],devianceResiduals:[2,3,1,""],explainedVariance:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],meanAbsoluteError:[2,3,1,""],meanSquaredError:[2,3,1,""],numInstances:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],r2:[2,3,1,""],residuals:[2,3,1,""],rootMeanSquaredError:[2,3,1,""],tValues:[2,3,1,""]},"pyspark.ml.regression.LinearRegressionTrainingSummary":{coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],devianceResiduals:[2,3,1,""],explainedVariance:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],meanAbsoluteError:[2,3,1,""],meanSquaredError:[2,3,1,""],numInstances:[2,3,1,""],objectiveHistory:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],r2:[2,3,1,""],residuals:[2,3,1,""],rootMeanSquaredError:[2,3,1,""],tValues:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.regression.RandomForestRegressionModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.RandomForestRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatureSubsetStrategy:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getNumTrees:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],numTrees:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeatureSubsetStrategy:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setNumTrees:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],subsamplingRate:[2,3,1,""],supportedFeatureSubsetStrategies:[2,3,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.stat":{ChiSquareTest:[2,1,1,""],Correlation:[2,1,1,""]},"pyspark.ml.stat.ChiSquareTest":{test:[2,5,1,""]},"pyspark.ml.stat.Correlation":{corr:[2,5,1,""]},"pyspark.ml.tuning":{CrossValidator:[2,1,1,""],CrossValidatorModel:[2,1,1,""],ParamGridBuilder:[2,1,1,""],TrainValidationSplit:[2,1,1,""],TrainValidationSplitModel:[2,1,1,""]},"pyspark.ml.tuning.CrossValidator":{copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getNumFolds:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],numFolds:[2,3,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setNumFolds:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""]},"pyspark.ml.tuning.CrossValidatorModel":{avgMetrics:[2,3,1,""],bestModel:[2,3,1,""],copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setSeed:[2,2,1,""],transform:[2,2,1,""]},"pyspark.ml.tuning.ParamGridBuilder":{addGrid:[2,2,1,""],baseOn:[2,2,1,""],build:[2,2,1,""]},"pyspark.ml.tuning.TrainValidationSplit":{copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getTrainRatio:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setTrainRatio:[2,2,1,""],trainRatio:[2,3,1,""]},"pyspark.ml.tuning.TrainValidationSplitModel":{bestModel:[2,3,1,""],copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setSeed:[2,2,1,""],transform:[2,2,1,""],validationMetrics:[2,3,1,""]},"pyspark.ml.util":{Identifiable:[2,1,1,""],JavaMLReadable:[2,1,1,""],JavaMLReader:[2,1,1,""],JavaMLWritable:[2,1,1,""],JavaMLWriter:[2,1,1,""],JavaPredictionModel:[2,1,1,""],MLReadable:[2,1,1,""],MLReader:[2,1,1,""],MLWritable:[2,1,1,""],MLWriter:[2,1,1,""]},"pyspark.ml.util.Identifiable":{uid:[2,3,1,""]},"pyspark.ml.util.JavaMLReadable":{load:[2,4,1,""],read:[2,4,1,""]},"pyspark.ml.util.JavaMLReader":{context:[2,2,1,""],load:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.JavaMLWritable":{save:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.util.JavaMLWriter":{context:[2,2,1,""],overwrite:[2,2,1,""],save:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.JavaPredictionModel":{numFeatures:[2,3,1,""]},"pyspark.ml.util.MLReadable":{load:[2,4,1,""],read:[2,4,1,""]},"pyspark.ml.util.MLReader":{context:[2,2,1,""],load:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.MLWritable":{save:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.util.MLWriter":{context:[2,2,1,""],overwrite:[2,2,1,""],save:[2,2,1,""],session:[2,2,1,""]},"pyspark.mllib":{classification:[3,0,0,"-"],clustering:[3,0,0,"-"],evaluation:[3,0,0,"-"],feature:[3,0,0,"-"],fpm:[3,0,0,"-"],linalg:[3,0,0,"-"],random:[3,0,0,"-"],recommendation:[3,0,0,"-"],regression:[3,0,0,"-"],stat:[3,0,0,"-"],tree:[3,0,0,"-"],util:[3,0,0,"-"]},"pyspark.mllib.classification":{LogisticRegressionModel:[3,1,1,""],LogisticRegressionWithLBFGS:[3,1,1,""],LogisticRegressionWithSGD:[3,1,1,""],NaiveBayes:[3,1,1,""],NaiveBayesModel:[3,1,1,""],SVMModel:[3,1,1,""],SVMWithSGD:[3,1,1,""],StreamingLogisticRegressionWithSGD:[3,1,1,""]},"pyspark.mllib.classification.LogisticRegressionModel":{clearThreshold:[3,2,1,""],intercept:[3,3,1,""],load:[3,4,1,""],numClasses:[3,3,1,""],numFeatures:[3,3,1,""],predict:[3,2,1,""],save:[3,2,1,""],setThreshold:[3,2,1,""],threshold:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.classification.LogisticRegressionWithLBFGS":{train:[3,4,1,""]},"pyspark.mllib.classification.LogisticRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.classification.NaiveBayes":{train:[3,4,1,""]},"pyspark.mllib.classification.NaiveBayesModel":{load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.classification.SVMModel":{clearThreshold:[3,2,1,""],intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],setThreshold:[3,2,1,""],threshold:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.classification.SVMWithSGD":{train:[3,4,1,""]},"pyspark.mllib.classification.StreamingLogisticRegressionWithSGD":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setInitialWeights:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.clustering":{BisectingKMeans:[3,1,1,""],BisectingKMeansModel:[3,1,1,""],GaussianMixture:[3,1,1,""],GaussianMixtureModel:[3,1,1,""],KMeans:[3,1,1,""],KMeansModel:[3,1,1,""],LDA:[3,1,1,""],LDAModel:[3,1,1,""],PowerIterationClustering:[3,1,1,""],PowerIterationClusteringModel:[3,1,1,""],StreamingKMeans:[3,1,1,""],StreamingKMeansModel:[3,1,1,""]},"pyspark.mllib.clustering.BisectingKMeans":{train:[3,4,1,""]},"pyspark.mllib.clustering.BisectingKMeansModel":{clusterCenters:[3,3,1,""],computeCost:[3,2,1,""],k:[3,3,1,""],predict:[3,2,1,""]},"pyspark.mllib.clustering.GaussianMixture":{train:[3,4,1,""]},"pyspark.mllib.clustering.GaussianMixtureModel":{gaussians:[3,3,1,""],k:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],predictSoft:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.clustering.KMeans":{train:[3,4,1,""]},"pyspark.mllib.clustering.KMeansModel":{clusterCenters:[3,3,1,""],computeCost:[3,2,1,""],k:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.clustering.LDA":{train:[3,4,1,""]},"pyspark.mllib.clustering.LDAModel":{describeTopics:[3,2,1,""],load:[3,4,1,""],topicsMatrix:[3,2,1,""],vocabSize:[3,2,1,""]},"pyspark.mllib.clustering.PowerIterationClustering":{Assignment:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.clustering.PowerIterationClusteringModel":{assignments:[3,2,1,""],k:[3,3,1,""],load:[3,4,1,""]},"pyspark.mllib.clustering.StreamingKMeans":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setDecayFactor:[3,2,1,""],setHalfLife:[3,2,1,""],setInitialCenters:[3,2,1,""],setK:[3,2,1,""],setRandomCenters:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.clustering.StreamingKMeansModel":{clusterWeights:[3,3,1,""],update:[3,2,1,""]},"pyspark.mllib.evaluation":{BinaryClassificationMetrics:[3,1,1,""],MulticlassMetrics:[3,1,1,""],RankingMetrics:[3,1,1,""],RegressionMetrics:[3,1,1,""]},"pyspark.mllib.evaluation.BinaryClassificationMetrics":{areaUnderPR:[3,3,1,""],areaUnderROC:[3,3,1,""],unpersist:[3,2,1,""]},"pyspark.mllib.evaluation.MulticlassMetrics":{accuracy:[3,3,1,""],confusionMatrix:[3,2,1,""],fMeasure:[3,2,1,""],falsePositiveRate:[3,2,1,""],precision:[3,2,1,""],recall:[3,2,1,""],truePositiveRate:[3,2,1,""],weightedFMeasure:[3,2,1,""],weightedFalsePositiveRate:[3,3,1,""],weightedPrecision:[3,3,1,""],weightedRecall:[3,3,1,""],weightedTruePositiveRate:[3,3,1,""]},"pyspark.mllib.evaluation.RankingMetrics":{meanAveragePrecision:[3,3,1,""],ndcgAt:[3,2,1,""],precisionAt:[3,2,1,""]},"pyspark.mllib.evaluation.RegressionMetrics":{explainedVariance:[3,3,1,""],meanAbsoluteError:[3,3,1,""],meanSquaredError:[3,3,1,""],r2:[3,3,1,""],rootMeanSquaredError:[3,3,1,""]},"pyspark.mllib.feature":{ChiSqSelector:[3,1,1,""],ChiSqSelectorModel:[3,1,1,""],ElementwiseProduct:[3,1,1,""],HashingTF:[3,1,1,""],IDF:[3,1,1,""],IDFModel:[3,1,1,""],Normalizer:[3,1,1,""],StandardScaler:[3,1,1,""],StandardScalerModel:[3,1,1,""],Word2Vec:[3,1,1,""],Word2VecModel:[3,1,1,""]},"pyspark.mllib.feature.ChiSqSelector":{fit:[3,2,1,""],setFdr:[3,2,1,""],setFpr:[3,2,1,""],setFwe:[3,2,1,""],setNumTopFeatures:[3,2,1,""],setPercentile:[3,2,1,""],setSelectorType:[3,2,1,""]},"pyspark.mllib.feature.ChiSqSelectorModel":{transform:[3,2,1,""]},"pyspark.mllib.feature.ElementwiseProduct":{transform:[3,2,1,""]},"pyspark.mllib.feature.HashingTF":{indexOf:[3,2,1,""],setBinary:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.IDF":{fit:[3,2,1,""]},"pyspark.mllib.feature.IDFModel":{idf:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.Normalizer":{transform:[3,2,1,""]},"pyspark.mllib.feature.StandardScaler":{fit:[3,2,1,""]},"pyspark.mllib.feature.StandardScalerModel":{mean:[3,3,1,""],setWithMean:[3,2,1,""],setWithStd:[3,2,1,""],std:[3,3,1,""],transform:[3,2,1,""],withMean:[3,3,1,""],withStd:[3,3,1,""]},"pyspark.mllib.feature.Word2Vec":{fit:[3,2,1,""],setLearningRate:[3,2,1,""],setMinCount:[3,2,1,""],setNumIterations:[3,2,1,""],setNumPartitions:[3,2,1,""],setSeed:[3,2,1,""],setVectorSize:[3,2,1,""],setWindowSize:[3,2,1,""]},"pyspark.mllib.feature.Word2VecModel":{findSynonyms:[3,2,1,""],getVectors:[3,2,1,""],load:[3,4,1,""],transform:[3,2,1,""]},"pyspark.mllib.fpm":{FPGrowth:[3,1,1,""],FPGrowthModel:[3,1,1,""],PrefixSpan:[3,1,1,""],PrefixSpanModel:[3,1,1,""]},"pyspark.mllib.fpm.FPGrowth":{FreqItemset:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.fpm.FPGrowthModel":{freqItemsets:[3,2,1,""],load:[3,4,1,""]},"pyspark.mllib.fpm.PrefixSpan":{FreqSequence:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.fpm.PrefixSpanModel":{freqSequences:[3,2,1,""]},"pyspark.mllib.linalg":{DenseMatrix:[3,1,1,""],DenseVector:[3,1,1,""],Matrices:[3,1,1,""],Matrix:[3,1,1,""],QRDecomposition:[3,1,1,""],SparseMatrix:[3,1,1,""],SparseVector:[3,1,1,""],Vector:[3,1,1,""],Vectors:[3,1,1,""],distributed:[3,0,0,"-"]},"pyspark.mllib.linalg.DenseMatrix":{asML:[3,2,1,""],toArray:[3,2,1,""],toSparse:[3,2,1,""]},"pyspark.mllib.linalg.DenseVector":{asML:[3,2,1,""],dot:[3,2,1,""],norm:[3,2,1,""],numNonzeros:[3,2,1,""],parse:[3,5,1,""],squared_distance:[3,2,1,""],toArray:[3,2,1,""],values:[3,3,1,""]},"pyspark.mllib.linalg.Matrices":{dense:[3,5,1,""],fromML:[3,5,1,""],sparse:[3,5,1,""]},"pyspark.mllib.linalg.Matrix":{asML:[3,2,1,""],toArray:[3,2,1,""]},"pyspark.mllib.linalg.QRDecomposition":{Q:[3,3,1,""],R:[3,3,1,""]},"pyspark.mllib.linalg.SparseMatrix":{asML:[3,2,1,""],toArray:[3,2,1,""],toDense:[3,2,1,""]},"pyspark.mllib.linalg.SparseVector":{asML:[3,2,1,""],dot:[3,2,1,""],indices:[3,3,1,""],norm:[3,2,1,""],numNonzeros:[3,2,1,""],parse:[3,5,1,""],size:[3,3,1,""],squared_distance:[3,2,1,""],toArray:[3,2,1,""],values:[3,3,1,""]},"pyspark.mllib.linalg.Vector":{asML:[3,2,1,""],toArray:[3,2,1,""]},"pyspark.mllib.linalg.Vectors":{dense:[3,5,1,""],fromML:[3,5,1,""],norm:[3,5,1,""],parse:[3,5,1,""],sparse:[3,5,1,""],squared_distance:[3,5,1,""],stringify:[3,5,1,""],zeros:[3,5,1,""]},"pyspark.mllib.linalg.distributed":{BlockMatrix:[3,1,1,""],CoordinateMatrix:[3,1,1,""],DistributedMatrix:[3,1,1,""],IndexedRow:[3,1,1,""],IndexedRowMatrix:[3,1,1,""],MatrixEntry:[3,1,1,""],RowMatrix:[3,1,1,""],SingularValueDecomposition:[3,1,1,""]},"pyspark.mllib.linalg.distributed.BlockMatrix":{add:[3,2,1,""],blocks:[3,3,1,""],cache:[3,2,1,""],colsPerBlock:[3,3,1,""],multiply:[3,2,1,""],numColBlocks:[3,3,1,""],numCols:[3,2,1,""],numRowBlocks:[3,3,1,""],numRows:[3,2,1,""],persist:[3,2,1,""],rowsPerBlock:[3,3,1,""],subtract:[3,2,1,""],toCoordinateMatrix:[3,2,1,""],toIndexedRowMatrix:[3,2,1,""],toLocalMatrix:[3,2,1,""],transpose:[3,2,1,""],validate:[3,2,1,""]},"pyspark.mllib.linalg.distributed.CoordinateMatrix":{entries:[3,3,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],toBlockMatrix:[3,2,1,""],toIndexedRowMatrix:[3,2,1,""],toRowMatrix:[3,2,1,""],transpose:[3,2,1,""]},"pyspark.mllib.linalg.distributed.DistributedMatrix":{numCols:[3,2,1,""],numRows:[3,2,1,""]},"pyspark.mllib.linalg.distributed.IndexedRowMatrix":{columnSimilarities:[3,2,1,""],computeGramianMatrix:[3,2,1,""],computeSVD:[3,2,1,""],multiply:[3,2,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],rows:[3,3,1,""],toBlockMatrix:[3,2,1,""],toCoordinateMatrix:[3,2,1,""],toRowMatrix:[3,2,1,""]},"pyspark.mllib.linalg.distributed.RowMatrix":{columnSimilarities:[3,2,1,""],computeColumnSummaryStatistics:[3,2,1,""],computeCovariance:[3,2,1,""],computeGramianMatrix:[3,2,1,""],computePrincipalComponents:[3,2,1,""],computeSVD:[3,2,1,""],multiply:[3,2,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],rows:[3,3,1,""],tallSkinnyQR:[3,2,1,""]},"pyspark.mllib.linalg.distributed.SingularValueDecomposition":{U:[3,3,1,""],V:[3,3,1,""],s:[3,3,1,""]},"pyspark.mllib.random":{RandomRDDs:[3,1,1,""]},"pyspark.mllib.random.RandomRDDs":{exponentialRDD:[3,5,1,""],exponentialVectorRDD:[3,5,1,""],gammaRDD:[3,5,1,""],gammaVectorRDD:[3,5,1,""],logNormalRDD:[3,5,1,""],logNormalVectorRDD:[3,5,1,""],normalRDD:[3,5,1,""],normalVectorRDD:[3,5,1,""],poissonRDD:[3,5,1,""],poissonVectorRDD:[3,5,1,""],uniformRDD:[3,5,1,""],uniformVectorRDD:[3,5,1,""]},"pyspark.mllib.recommendation":{ALS:[3,1,1,""],MatrixFactorizationModel:[3,1,1,""],Rating:[3,1,1,""]},"pyspark.mllib.recommendation.ALS":{train:[3,4,1,""],trainImplicit:[3,4,1,""]},"pyspark.mllib.recommendation.MatrixFactorizationModel":{load:[3,4,1,""],predict:[3,2,1,""],predictAll:[3,2,1,""],productFeatures:[3,2,1,""],rank:[3,3,1,""],recommendProducts:[3,2,1,""],recommendProductsForUsers:[3,2,1,""],recommendUsers:[3,2,1,""],recommendUsersForProducts:[3,2,1,""],userFeatures:[3,2,1,""]},"pyspark.mllib.regression":{IsotonicRegression:[3,1,1,""],IsotonicRegressionModel:[3,1,1,""],LabeledPoint:[3,1,1,""],LassoModel:[3,1,1,""],LassoWithSGD:[3,1,1,""],LinearModel:[3,1,1,""],LinearRegressionModel:[3,1,1,""],LinearRegressionWithSGD:[3,1,1,""],RidgeRegressionModel:[3,1,1,""],RidgeRegressionWithSGD:[3,1,1,""],StreamingLinearAlgorithm:[3,1,1,""],StreamingLinearRegressionWithSGD:[3,1,1,""]},"pyspark.mllib.regression.IsotonicRegression":{train:[3,4,1,""]},"pyspark.mllib.regression.IsotonicRegressionModel":{load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.regression.LassoModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LassoWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.LinearModel":{intercept:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LinearRegressionModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LinearRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.RidgeRegressionModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.RidgeRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.StreamingLinearAlgorithm":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""]},"pyspark.mllib.regression.StreamingLinearRegressionWithSGD":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setInitialWeights:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.stat":{ChiSqTestResult:[3,1,1,""],KernelDensity:[3,1,1,""],MultivariateGaussian:[3,1,1,""],MultivariateStatisticalSummary:[3,1,1,""],Statistics:[3,1,1,""]},"pyspark.mllib.stat.ChiSqTestResult":{method:[3,3,1,""]},"pyspark.mllib.stat.KernelDensity":{estimate:[3,2,1,""],setBandwidth:[3,2,1,""],setSample:[3,2,1,""]},"pyspark.mllib.stat.MultivariateStatisticalSummary":{count:[3,2,1,""],max:[3,2,1,""],mean:[3,2,1,""],min:[3,2,1,""],normL1:[3,2,1,""],normL2:[3,2,1,""],numNonzeros:[3,2,1,""],variance:[3,2,1,""]},"pyspark.mllib.stat.Statistics":{chiSqTest:[3,5,1,""],colStats:[3,5,1,""],corr:[3,5,1,""],kolmogorovSmirnovTest:[3,5,1,""]},"pyspark.mllib.tree":{DecisionTree:[3,1,1,""],DecisionTreeModel:[3,1,1,""],GradientBoostedTrees:[3,1,1,""],GradientBoostedTreesModel:[3,1,1,""],RandomForest:[3,1,1,""],RandomForestModel:[3,1,1,""]},"pyspark.mllib.tree.DecisionTree":{trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.DecisionTreeModel":{call:[3,2,1,""],depth:[3,2,1,""],load:[3,4,1,""],numNodes:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""]},"pyspark.mllib.tree.GradientBoostedTrees":{trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.GradientBoostedTreesModel":{call:[3,2,1,""],load:[3,4,1,""],numTrees:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""],totalNumNodes:[3,2,1,""]},"pyspark.mllib.tree.RandomForest":{supportedFeatureSubsetStrategies:[3,3,1,""],trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.RandomForestModel":{call:[3,2,1,""],load:[3,4,1,""],numTrees:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""],totalNumNodes:[3,2,1,""]},"pyspark.mllib.util":{JavaLoader:[3,1,1,""],JavaSaveable:[3,1,1,""],LinearDataGenerator:[3,1,1,""],Loader:[3,1,1,""],MLUtils:[3,1,1,""],Saveable:[3,1,1,""]},"pyspark.mllib.util.JavaLoader":{load:[3,4,1,""]},"pyspark.mllib.util.JavaSaveable":{save:[3,2,1,""]},"pyspark.mllib.util.LinearDataGenerator":{generateLinearInput:[3,5,1,""],generateLinearRDD:[3,5,1,""]},"pyspark.mllib.util.Loader":{load:[3,4,1,""]},"pyspark.mllib.util.MLUtils":{appendBias:[3,5,1,""],convertMatrixColumnsFromML:[3,5,1,""],convertMatrixColumnsToML:[3,5,1,""],convertVectorColumnsFromML:[3,5,1,""],convertVectorColumnsToML:[3,5,1,""],loadLabeledPoints:[3,5,1,""],loadLibSVMFile:[3,5,1,""],loadVectors:[3,5,1,""],saveAsLibSVMFile:[3,5,1,""]},"pyspark.mllib.util.Saveable":{save:[3,2,1,""]},"pyspark.sql":{Column:[4,1,1,""],DataFrame:[4,1,1,""],DataFrameNaFunctions:[4,1,1,""],DataFrameReader:[4,1,1,""],DataFrameStatFunctions:[4,1,1,""],DataFrameWriter:[4,1,1,""],GroupedData:[4,1,1,""],HiveContext:[4,1,1,""],Row:[4,1,1,""],SQLContext:[4,1,1,""],SparkSession:[4,1,1,""],UDFRegistration:[4,1,1,""],Window:[4,1,1,""],WindowSpec:[4,1,1,""],functions:[4,0,0,"-"],streaming:[4,0,0,"-"],types:[4,0,0,"-"]},"pyspark.sql.Column":{alias:[4,2,1,""],asc:[4,2,1,""],astype:[4,2,1,""],between:[4,2,1,""],bitwiseAND:[4,2,1,""],bitwiseOR:[4,2,1,""],bitwiseXOR:[4,2,1,""],cast:[4,2,1,""],contains:[4,2,1,""],desc:[4,2,1,""],endswith:[4,2,1,""],getField:[4,2,1,""],getItem:[4,2,1,""],isNotNull:[4,2,1,""],isNull:[4,2,1,""],isin:[4,2,1,""],like:[4,2,1,""],name:[4,2,1,""],otherwise:[4,2,1,""],over:[4,2,1,""],rlike:[4,2,1,""],startswith:[4,2,1,""],substr:[4,2,1,""],when:[4,2,1,""]},"pyspark.sql.DataFrame":{agg:[4,2,1,""],alias:[4,2,1,""],approxQuantile:[4,2,1,""],cache:[4,2,1,""],checkpoint:[4,2,1,""],coalesce:[4,2,1,""],collect:[4,2,1,""],columns:[4,3,1,""],corr:[4,2,1,""],count:[4,2,1,""],cov:[4,2,1,""],createGlobalTempView:[4,2,1,""],createOrReplaceGlobalTempView:[4,2,1,""],createOrReplaceTempView:[4,2,1,""],createTempView:[4,2,1,""],crossJoin:[4,2,1,""],crosstab:[4,2,1,""],cube:[4,2,1,""],describe:[4,2,1,""],distinct:[4,2,1,""],drop:[4,2,1,""],dropDuplicates:[4,2,1,""],drop_duplicates:[4,2,1,""],dropna:[4,2,1,""],dtypes:[4,3,1,""],explain:[4,2,1,""],fillna:[4,2,1,""],filter:[4,2,1,""],first:[4,2,1,""],foreach:[4,2,1,""],foreachPartition:[4,2,1,""],freqItems:[4,2,1,""],groupBy:[4,2,1,""],groupby:[4,2,1,""],head:[4,2,1,""],hint:[4,2,1,""],intersect:[4,2,1,""],isLocal:[4,2,1,""],isStreaming:[4,3,1,""],join:[4,2,1,""],limit:[4,2,1,""],na:[4,3,1,""],orderBy:[4,2,1,""],persist:[4,2,1,""],printSchema:[4,2,1,""],randomSplit:[4,2,1,""],rdd:[4,3,1,""],registerTempTable:[4,2,1,""],repartition:[4,2,1,""],replace:[4,2,1,""],rollup:[4,2,1,""],sample:[4,2,1,""],sampleBy:[4,2,1,""],schema:[4,3,1,""],select:[4,2,1,""],selectExpr:[4,2,1,""],show:[4,2,1,""],sort:[4,2,1,""],sortWithinPartitions:[4,2,1,""],stat:[4,3,1,""],storageLevel:[4,3,1,""],subtract:[4,2,1,""],take:[4,2,1,""],toDF:[4,2,1,""],toJSON:[4,2,1,""],toLocalIterator:[4,2,1,""],toPandas:[4,2,1,""],union:[4,2,1,""],unionAll:[4,2,1,""],unpersist:[4,2,1,""],where:[4,2,1,""],withColumn:[4,2,1,""],withColumnRenamed:[4,2,1,""],withWatermark:[4,2,1,""],write:[4,3,1,""],writeStream:[4,3,1,""]},"pyspark.sql.DataFrameNaFunctions":{drop:[4,2,1,""],fill:[4,2,1,""],replace:[4,2,1,""]},"pyspark.sql.DataFrameReader":{csv:[4,2,1,""],format:[4,2,1,""],jdbc:[4,2,1,""],json:[4,2,1,""],load:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],orc:[4,2,1,""],parquet:[4,2,1,""],schema:[4,2,1,""],table:[4,2,1,""],text:[4,2,1,""]},"pyspark.sql.DataFrameStatFunctions":{approxQuantile:[4,2,1,""],corr:[4,2,1,""],cov:[4,2,1,""],crosstab:[4,2,1,""],freqItems:[4,2,1,""],sampleBy:[4,2,1,""]},"pyspark.sql.DataFrameWriter":{csv:[4,2,1,""],format:[4,2,1,""],insertInto:[4,2,1,""],jdbc:[4,2,1,""],json:[4,2,1,""],mode:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],orc:[4,2,1,""],parquet:[4,2,1,""],partitionBy:[4,2,1,""],save:[4,2,1,""],saveAsTable:[4,2,1,""],text:[4,2,1,""]},"pyspark.sql.GroupedData":{agg:[4,2,1,""],avg:[4,2,1,""],count:[4,2,1,""],max:[4,2,1,""],mean:[4,2,1,""],min:[4,2,1,""],pivot:[4,2,1,""],sum:[4,2,1,""]},"pyspark.sql.HiveContext":{refreshTable:[4,2,1,""]},"pyspark.sql.Row":{asDict:[4,2,1,""]},"pyspark.sql.SQLContext":{cacheTable:[4,2,1,""],clearCache:[4,2,1,""],createDataFrame:[4,2,1,""],createExternalTable:[4,2,1,""],dropTempTable:[4,2,1,""],getConf:[4,2,1,""],getOrCreate:[4,4,1,""],newSession:[4,2,1,""],range:[4,2,1,""],read:[4,3,1,""],readStream:[4,3,1,""],registerDataFrameAsTable:[4,2,1,""],registerFunction:[4,2,1,""],registerJavaFunction:[4,2,1,""],setConf:[4,2,1,""],sql:[4,2,1,""],streams:[4,3,1,""],table:[4,2,1,""],tableNames:[4,2,1,""],tables:[4,2,1,""],udf:[4,3,1,""],uncacheTable:[4,2,1,""]},"pyspark.sql.SparkSession":{Builder:[4,1,1,""],builder:[4,3,1,""],catalog:[4,3,1,""],conf:[4,3,1,""],createDataFrame:[4,2,1,""],newSession:[4,2,1,""],range:[4,2,1,""],read:[4,3,1,""],readStream:[4,3,1,""],sparkContext:[4,3,1,""],sql:[4,2,1,""],stop:[4,2,1,""],streams:[4,3,1,""],table:[4,2,1,""],udf:[4,3,1,""],version:[4,3,1,""]},"pyspark.sql.SparkSession.Builder":{appName:[4,2,1,""],config:[4,2,1,""],enableHiveSupport:[4,2,1,""],getOrCreate:[4,2,1,""],master:[4,2,1,""]},"pyspark.sql.UDFRegistration":{register:[4,2,1,""]},"pyspark.sql.Window":{currentRow:[4,3,1,""],orderBy:[4,5,1,""],partitionBy:[4,5,1,""],rangeBetween:[4,5,1,""],rowsBetween:[4,5,1,""],unboundedFollowing:[4,3,1,""],unboundedPreceding:[4,3,1,""]},"pyspark.sql.WindowSpec":{orderBy:[4,2,1,""],partitionBy:[4,2,1,""],rangeBetween:[4,2,1,""],rowsBetween:[4,2,1,""]},"pyspark.sql.functions":{abs:[4,6,1,""],acos:[4,6,1,""],add_months:[4,6,1,""],approxCountDistinct:[4,6,1,""],approx_count_distinct:[4,6,1,""],array:[4,6,1,""],array_contains:[4,6,1,""],asc:[4,6,1,""],ascii:[4,6,1,""],asin:[4,6,1,""],atan2:[4,6,1,""],atan:[4,6,1,""],avg:[4,6,1,""],base64:[4,6,1,""],bin:[4,6,1,""],bitwiseNOT:[4,6,1,""],broadcast:[4,6,1,""],bround:[4,6,1,""],cbrt:[4,6,1,""],ceil:[4,6,1,""],coalesce:[4,6,1,""],col:[4,6,1,""],collect_list:[4,6,1,""],collect_set:[4,6,1,""],column:[4,6,1,""],concat:[4,6,1,""],concat_ws:[4,6,1,""],conv:[4,6,1,""],corr:[4,6,1,""],cos:[4,6,1,""],cosh:[4,6,1,""],count:[4,6,1,""],countDistinct:[4,6,1,""],covar_pop:[4,6,1,""],covar_samp:[4,6,1,""],crc32:[4,6,1,""],create_map:[4,6,1,""],cume_dist:[4,6,1,""],current_date:[4,6,1,""],current_timestamp:[4,6,1,""],date_add:[4,6,1,""],date_format:[4,6,1,""],date_sub:[4,6,1,""],datediff:[4,6,1,""],dayofmonth:[4,6,1,""],dayofyear:[4,6,1,""],decode:[4,6,1,""],degrees:[4,6,1,""],dense_rank:[4,6,1,""],desc:[4,6,1,""],encode:[4,6,1,""],exp:[4,6,1,""],explode:[4,6,1,""],expm1:[4,6,1,""],expr:[4,6,1,""],factorial:[4,6,1,""],first:[4,6,1,""],floor:[4,6,1,""],format_number:[4,6,1,""],format_string:[4,6,1,""],from_json:[4,6,1,""],from_unixtime:[4,6,1,""],from_utc_timestamp:[4,6,1,""],get_json_object:[4,6,1,""],greatest:[4,6,1,""],grouping:[4,6,1,""],grouping_id:[4,6,1,""],hash:[4,6,1,""],hex:[4,6,1,""],hour:[4,6,1,""],hypot:[4,6,1,""],initcap:[4,6,1,""],input_file_name:[4,6,1,""],instr:[4,6,1,""],isnan:[4,6,1,""],isnull:[4,6,1,""],json_tuple:[4,6,1,""],kurtosis:[4,6,1,""],lag:[4,6,1,""],last:[4,6,1,""],last_day:[4,6,1,""],lead:[4,6,1,""],least:[4,6,1,""],length:[4,6,1,""],levenshtein:[4,6,1,""],lit:[4,6,1,""],locate:[4,6,1,""],log10:[4,6,1,""],log1p:[4,6,1,""],log2:[4,6,1,""],log:[4,6,1,""],lower:[4,6,1,""],lpad:[4,6,1,""],ltrim:[4,6,1,""],max:[4,6,1,""],md5:[4,6,1,""],mean:[4,6,1,""],min:[4,6,1,""],minute:[4,6,1,""],monotonically_increasing_id:[4,6,1,""],month:[4,6,1,""],months_between:[4,6,1,""],nanvl:[4,6,1,""],next_day:[4,6,1,""],ntile:[4,6,1,""],percent_rank:[4,6,1,""],posexplode:[4,6,1,""],pow:[4,6,1,""],quarter:[4,6,1,""],radians:[4,6,1,""],rand:[4,6,1,""],randn:[4,6,1,""],rank:[4,6,1,""],regexp_extract:[4,6,1,""],regexp_replace:[4,6,1,""],repeat:[4,6,1,""],reverse:[4,6,1,""],rint:[4,6,1,""],round:[4,6,1,""],row_number:[4,6,1,""],rpad:[4,6,1,""],rtrim:[4,6,1,""],second:[4,6,1,""],sha1:[4,6,1,""],sha2:[4,6,1,""],shiftLeft:[4,6,1,""],shiftRight:[4,6,1,""],shiftRightUnsigned:[4,6,1,""],signum:[4,6,1,""],sin:[4,6,1,""],sinh:[4,6,1,""],size:[4,6,1,""],skewness:[4,6,1,""],sort_array:[4,6,1,""],soundex:[4,6,1,""],spark_partition_id:[4,6,1,""],split:[4,6,1,""],sqrt:[4,6,1,""],stddev:[4,6,1,""],stddev_pop:[4,6,1,""],stddev_samp:[4,6,1,""],struct:[4,6,1,""],substring:[4,6,1,""],substring_index:[4,6,1,""],sum:[4,6,1,""],sumDistinct:[4,6,1,""],tan:[4,6,1,""],tanh:[4,6,1,""],toDegrees:[4,6,1,""],toRadians:[4,6,1,""],to_date:[4,6,1,""],to_json:[4,6,1,""],to_timestamp:[4,6,1,""],to_utc_timestamp:[4,6,1,""],translate:[4,6,1,""],trim:[4,6,1,""],trunc:[4,6,1,""],udf:[4,6,1,""],unbase64:[4,6,1,""],unhex:[4,6,1,""],unix_timestamp:[4,6,1,""],upper:[4,6,1,""],var_pop:[4,6,1,""],var_samp:[4,6,1,""],variance:[4,6,1,""],weekofyear:[4,6,1,""],when:[4,6,1,""],window:[4,6,1,""],year:[4,6,1,""]},"pyspark.sql.streaming":{DataStreamReader:[4,1,1,""],DataStreamWriter:[4,1,1,""],StreamingQuery:[4,1,1,""],StreamingQueryManager:[4,1,1,""]},"pyspark.sql.streaming.DataStreamReader":{csv:[4,2,1,""],format:[4,2,1,""],json:[4,2,1,""],load:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],parquet:[4,2,1,""],schema:[4,2,1,""],text:[4,2,1,""]},"pyspark.sql.streaming.DataStreamWriter":{format:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],outputMode:[4,2,1,""],partitionBy:[4,2,1,""],queryName:[4,2,1,""],start:[4,2,1,""],trigger:[4,2,1,""]},"pyspark.sql.streaming.StreamingQuery":{awaitTermination:[4,2,1,""],exception:[4,2,1,""],explain:[4,2,1,""],id:[4,3,1,""],isActive:[4,3,1,""],lastProgress:[4,3,1,""],name:[4,3,1,""],processAllAvailable:[4,2,1,""],recentProgress:[4,3,1,""],runId:[4,3,1,""],status:[4,3,1,""],stop:[4,2,1,""]},"pyspark.sql.streaming.StreamingQueryManager":{active:[4,3,1,""],awaitAnyTermination:[4,2,1,""],get:[4,2,1,""],resetTerminated:[4,2,1,""]},"pyspark.sql.types":{ArrayType:[4,1,1,""],BinaryType:[4,1,1,""],BooleanType:[4,1,1,""],ByteType:[4,1,1,""],DataType:[4,1,1,""],DateType:[4,1,1,""],DecimalType:[4,1,1,""],DoubleType:[4,1,1,""],FloatType:[4,1,1,""],IntegerType:[4,1,1,""],LongType:[4,1,1,""],MapType:[4,1,1,""],NullType:[4,1,1,""],ShortType:[4,1,1,""],StringType:[4,1,1,""],StructField:[4,1,1,""],StructType:[4,1,1,""],TimestampType:[4,1,1,""]},"pyspark.sql.types.ArrayType":{fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.ByteType":{simpleString:[4,2,1,""]},"pyspark.sql.types.DataType":{fromInternal:[4,2,1,""],json:[4,2,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""],typeName:[4,4,1,""]},"pyspark.sql.types.DateType":{EPOCH_ORDINAL:[4,3,1,""],fromInternal:[4,2,1,""],needConversion:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.DecimalType":{jsonValue:[4,2,1,""],simpleString:[4,2,1,""]},"pyspark.sql.types.IntegerType":{simpleString:[4,2,1,""]},"pyspark.sql.types.LongType":{simpleString:[4,2,1,""]},"pyspark.sql.types.MapType":{fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.ShortType":{simpleString:[4,2,1,""]},"pyspark.sql.types.StructField":{fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""],typeName:[4,2,1,""]},"pyspark.sql.types.StructType":{add:[4,2,1,""],fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.TimestampType":{fromInternal:[4,2,1,""],needConversion:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.streaming":{DStream:[5,1,1,""],StreamingContext:[5,1,1,""],StreamingListener:[5,1,1,""],flume:[5,0,0,"-"],kafka:[5,0,0,"-"],kinesis:[5,0,0,"-"]},"pyspark.streaming.DStream":{cache:[5,2,1,""],checkpoint:[5,2,1,""],cogroup:[5,2,1,""],combineByKey:[5,2,1,""],context:[5,2,1,""],count:[5,2,1,""],countByValue:[5,2,1,""],countByValueAndWindow:[5,2,1,""],countByWindow:[5,2,1,""],filter:[5,2,1,""],flatMap:[5,2,1,""],flatMapValues:[5,2,1,""],foreachRDD:[5,2,1,""],fullOuterJoin:[5,2,1,""],glom:[5,2,1,""],groupByKey:[5,2,1,""],groupByKeyAndWindow:[5,2,1,""],join:[5,2,1,""],leftOuterJoin:[5,2,1,""],map:[5,2,1,""],mapPartitions:[5,2,1,""],mapPartitionsWithIndex:[5,2,1,""],mapValues:[5,2,1,""],partitionBy:[5,2,1,""],persist:[5,2,1,""],pprint:[5,2,1,""],reduce:[5,2,1,""],reduceByKey:[5,2,1,""],reduceByKeyAndWindow:[5,2,1,""],reduceByWindow:[5,2,1,""],repartition:[5,2,1,""],rightOuterJoin:[5,2,1,""],saveAsTextFiles:[5,2,1,""],slice:[5,2,1,""],transform:[5,2,1,""],transformWith:[5,2,1,""],union:[5,2,1,""],updateStateByKey:[5,2,1,""],window:[5,2,1,""]},"pyspark.streaming.StreamingContext":{addStreamingListener:[5,2,1,""],awaitTermination:[5,2,1,""],awaitTerminationOrTimeout:[5,2,1,""],binaryRecordsStream:[5,2,1,""],checkpoint:[5,2,1,""],getActive:[5,4,1,""],getActiveOrCreate:[5,4,1,""],getOrCreate:[5,4,1,""],queueStream:[5,2,1,""],remember:[5,2,1,""],socketTextStream:[5,2,1,""],sparkContext:[5,3,1,""],start:[5,2,1,""],stop:[5,2,1,""],textFileStream:[5,2,1,""],transform:[5,2,1,""],union:[5,2,1,""]},"pyspark.streaming.StreamingListener":{Java:[5,1,1,""],onBatchCompleted:[5,2,1,""],onBatchStarted:[5,2,1,""],onBatchSubmitted:[5,2,1,""],onOutputOperationCompleted:[5,2,1,""],onOutputOperationStarted:[5,2,1,""],onReceiverError:[5,2,1,""],onReceiverStarted:[5,2,1,""],onReceiverStopped:[5,2,1,""]},"pyspark.streaming.StreamingListener.Java":{"implements":[5,3,1,""]},"pyspark.streaming.flume":{FlumeUtils:[5,1,1,""],utf8_decoder:[5,6,1,""]},"pyspark.streaming.flume.FlumeUtils":{createPollingStream:[5,5,1,""],createStream:[5,5,1,""]},"pyspark.streaming.kafka":{Broker:[5,1,1,""],KafkaMessageAndMetadata:[5,1,1,""],KafkaUtils:[5,1,1,""],OffsetRange:[5,1,1,""],TopicAndPartition:[5,1,1,""],utf8_decoder:[5,6,1,""]},"pyspark.streaming.kafka.KafkaMessageAndMetadata":{key:[5,3,1,""],message:[5,3,1,""]},"pyspark.streaming.kafka.KafkaUtils":{createDirectStream:[5,5,1,""],createRDD:[5,5,1,""],createStream:[5,5,1,""]},"pyspark.streaming.kinesis":{InitialPositionInStream:[5,1,1,""],KinesisUtils:[5,1,1,""],utf8_decoder:[5,6,1,""]},"pyspark.streaming.kinesis.InitialPositionInStream":{LATEST:[5,3,1,""],TRIM_HORIZON:[5,3,1,""]},"pyspark.streaming.kinesis.KinesisUtils":{createStream:[5,5,1,""]},pyspark:{Accumulator:[1,1,1,""],AccumulatorParam:[1,1,1,""],BasicProfiler:[1,1,1,""],Broadcast:[1,1,1,""],MarshalSerializer:[1,1,1,""],PickleSerializer:[1,1,1,""],Profiler:[1,1,1,""],RDD:[1,1,1,""],SparkConf:[1,1,1,""],SparkContext:[1,1,1,""],SparkFiles:[1,1,1,""],SparkJobInfo:[1,1,1,""],SparkStageInfo:[1,1,1,""],StatusTracker:[1,1,1,""],StorageLevel:[1,1,1,""],TaskContext:[1,1,1,""],ml:[2,0,0,"-"],sql:[4,0,0,"-"],streaming:[5,0,0,"-"]}},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","attribute","Python attribute"],"4":["py","classmethod","Python class method"],"5":["py","staticmethod","Python static method"],"6":["py","function","Python function"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:attribute","4":"py:classmethod","5":"py:staticmethod","6":"py:function"},terms:{"16be":4,"16le":4,"1a2s3a":4,"1e4":4,"1e6":4,"2nd":2,"3bc51062973c458d5a6f2d8d64a023246354ad7e064b1e4e009ec8a0699a3043":4,"3c01bdbb26f358bab27f267924aa2c9a03fcfdb8":4,"56e":3,"902fbdd2b1df0c4f70b4a5d23525e932":4,"9223372036854775807l":4,"9223372036854775808l":4,"abstract":[0,1,2,3,5],"boolean":[2,3,4],"byte":[1,4,5],"case":[1,2,3,4,5],"char":4,"class":[1,2,3,4,5],"default":[1,2,3,4,5],"final":[1,3,4],"float":[1,2,3,4],"function":[0,1,2,3,5],"import":[1,2,3,4],"int":[1,2,3,4],"long":[1,3,4,5],"new":[1,2,3,4,5],"null":[1,2,3,4,5],"public":1,"return":[1,2,3,4,5],"short":4,"static":[1,2,3,4,5],"switch":1,"throw":[2,3,4,5],"true":[1,2,3,4,5],"try":[1,3,4],"while":[1,2,4,5],ALS:[2,3],AND:4,AWS:5,Abs:2,Added:[1,4],And:[1,2],But:3,For:[1,2,3,4,5],IDs:[2,3,4],Ids:2,Its:1,NOT:[1,2,3],Not:[1,2],One:2,STS:5,THEN:4,TRs:3,That:4,The:[1,2,3,4,5],Then:2,There:[2,4],These:[1,2,4],Use:[1,2,3,4],Used:[1,3],Using:[1,3,4],With:2,__this__:2,_c0:4,_c1:4,_jconf:1,_jvm:1,aaaac:4,ab12cd:4,ababab:4,abc:4,abcd123:4,abcd:4,about:[1,2,4],abov:3,abs:[1,2,3,4],absenc:5,absolut:[1,2,3,4],absqrow:3,acceler:2,accept:[2,4],access:[1,3,4,5],accesskeyid:5,accord:[1,2,3,4],accordingli:4,accum_param:1,accumul:1,accumulatorparam:1,accuraci:[1,2,3],achiev:[2,4],aco:4,acquir:1,across:[1,2,3,4],act:2,action:[1,3],activ:[1,2,3,4,5],actual:[1,2,3,4],adapt:2,add:[1,2,3,4,5],add_month:4,add_on:4,added:[1,2,3],addfil:1,addgrid:2,adding:[2,4,5],addinplac:1,addit:[1,2,3,4,5],addition:[2,4],addpyfil:1,address:5,addstreaminglisten:5,adel:2,adjac:[2,3],adjust:2,advanc:3,advis:[1,2],affect:[1,2],affin:3,aft:2,after:[1,2,3,4,5],aftsr2:2,aftsr:2,aftsr_model:2,aftsr_path:2,aftsurvivalregress:2,aftsurvivalregressionmodel:2,again:[1,2,4],against:[2,3,4,5],againt:3,age2:4,age3:4,age:4,agecol:4,agent:5,ages:4,agg:4,aggreg:[1,2,4],aggregatebykei:1,aggregationdepth:2,aic:2,aid:1,aka:[2,4],akaik:2,alan:2,algebra:[2,3],algo:2,algorithm:[1,2,3,4],ali:4,alia:[1,2,4],alias:4,alic:4,align:4,all:[1,2,3,4,5],allclos:2,alloc:[1,2,3],allow:[1,2,3,4,5],allowbackslashescapinganycharact:4,allowcom:4,allowloc:1,allownumericleadingzero:4,allowsinglequot:4,allowunquotedfieldnam:4,almost:3,along:1,alpha:[2,3],alreadi:[1,2,3,4],als2:2,als:2,als_model:2,als_path:2,alsmodel:2,also:[1,2,3,4],alter:4,altern:[2,3,4],although:1,alwai:[1,3,4,5],amazonaw:5,among:4,amount:[2,3,4],analysi:4,analysisexcept:4,analyz:4,anexponenti:2,angl:4,ani:[1,2,3,4],anint:4,anoth:[1,2,3,4,5],answer:4,anteced:2,anthoni:3,antiton:3,apach:[1,2,4,5],api:[1,4,5],app:1,appear:[2,3],append:[1,2,3,4],appendbia:3,appl:1,applebi:2,appli:[1,2,3,4,5],applic:[1,2,3,4,5],application_1433865536131_34483:1,applicationid:1,appnam:[1,4],approach:[2,3],approx_count_distinct:4,approxcountdistinct:4,approxim:[1,2,3,4],approxnearestneighbor:2,approxquantil:[2,4],approxsimilarityjoin:2,arbitrari:[1,4],architectur:3,area:[2,3],areaunderpr:[2,3],areaunderroc:[2,3],arg1:4,arg2:4,arg:[1,2,3,4],argmax:2,argument:[1,2,3,4,5],arithmet:[2,3],ariti:3,arn:5,arnoldi:3,around:[2,3,4],arr:4,arrai:[1,2,3,4],array_contain:4,arraytyp:4,arriv:4,art:1,asc:4,ascend:[1,2,3,4],ascii:4,asdict:4,asin:4,asml:3,assembl:2,assert_almost_equ:3,assert_equ:3,assertionerror:[2,3],assess:5,assign:[1,2,3,4],associ:[1,2,3,4,5],associationrul:2,assum:[1,3,4,5],assumpt:4,astyp:4,asymptot:2,atan2:4,atan:4,atom:4,attach:2,attempt:[1,2],attemptnumb:1,attribut:[2,3,4],augment:3,austin:2,auto:[2,3],autobatchedseri:1,automat:[1,2,4],avaialbl:1,avail:[1,2,3,4,5],averag:[1,2,3,4],avg:4,avgmetr:2,avoid:[1,2,4],awaitanytermin:4,awaittermin:[4,5],awaitterminationortimeout:5,awsaccesskeyid:5,awssecretkei:5,back:[2,3,4],background:4,backslash:4,backward:4,bad:[1,2],bag:3,bahmani:2,banana:1,bandwidth:3,bar:1,base64:4,base:[1,2,3,4,5],baseon:2,basic:[0,1,5],basicprofil:1,batch:[1,2,3,4,5],batchcomplet:5,batchdur:5,batchsiz:1,batchstart:5,batchsubmit:5,bay:[2,3],bce:2,bce_path:2,bdf:2,bea:3,becaus:[2,3,4],becom:[3,4],been:[1,2,3,4,5],befor:[1,2,3,4,5],begin:[4,5],behav:1,behavior:[2,4],behind:4,being:[1,3,4,5],belong:[1,3,4],below:[2,3,4],benefit:4,benjamini:[2,3],bernoulli:[2,3],best:2,bestmodel:2,beta:[2,3],better:[1,2],between:[1,2,3,4,5],beyond:4,bfg:[2,3],bia:[1,3],bias:2,bigint:4,billion:4,bin:[2,3,4],binar:2,binari:[1,2,3,4,5],binarizerpath:2,binaryclassificationevalu:2,binaryclassificationmetr:3,binaryfil:1,binarylogisticregressionsummari:2,binarylogisticregressiontrainingsummari:2,binaryrecord:1,binaryrecordsstream:5,binarysearch:3,binarytyp:4,binomi:2,bisect:[2,3],bisectingkmean:[2,3],bisectingkmeansmodel:[2,3],bisectingkmeanssummari:2,bit:[2,3,4],bitwis:4,bitwiseand:4,bitwisenot:4,bitwiseor:4,bitwisexor:4,bkm2:2,bkm:2,bkm_model:2,bkm_path:2,blanklin:[3,4],blei:[2,3],block:[1,2,3,4],blockcolindex:3,blockmatrix:3,blockrowindex:3,blocks1:3,blocks2:3,blocks3:3,blocksiz:2,blor:2,blormodel:2,bob:4,bodi:5,bodydecod:5,bohman:2,bool:[2,4],booleantyp:4,boost:[2,3],bootstrap:3,both:[1,2,4,5],bottom:[2,3],bound:[2,3,4],boundari:[2,3,4],breiman:2,broadcast:[1,2,4],broker:5,bround:4,brp2:2,brp:2,brppath:2,brute:3,bskm:3,bucket:[1,2,4],bucketedrandomprojectionlsh:2,bucketedrandomprojectionlshmodel:2,bucketizerpath:2,bucketlength:2,build:[1,2,3],builder:[2,4],built:[1,4],builtin:4,bypass:3,bytearrai:4,bytebuff:1,bytetyp:4,bzip2:4,c_t:3,cach:[1,2,3,4,5],cachedexecutoridletimeout:1,cachenodeid:2,cachet:4,calcul:[2,3,4,5],calibr:2,call:[1,2,3,4,5],caller:4,came:4,can:[1,2,3,4,5],cancel:1,cancelalljob:1,canceljobgroup:1,candid:2,cannot:[1,2,3,4],captur:1,cardin:[1,3],care:[2,3],carri:[2,3],cartesian:[1,4],casesensit:2,cast:[2,4],cat:1,catalog:4,categor:[2,3],categori:[2,3],categoricalfeaturesinfo:3,categorymap:2,caus:[1,2,3],caution:1,cbrt:4,cd9fb1e148ccd8442e5aa74904cc73bf6fb54d1d54d333bd596aa9bb4bb4e961:4,cdf:[3,4],ceil:4,cell:4,censor:2,censorcol:2,center:[2,3],centr:3,centroid:3,certain:[2,3,4],chain:1,chang:[1,2,3,4,5],charact:[2,4],character:[2,5],characterist:[2,3],charset:4,cheaper:3,check:[1,2,4],checkcod:1,checkpoint:[1,2,3,4,5],checkpointinterv:[2,3,5],checkpointloc:4,checkpointpath:5,chi:[2,3],child:[2,3],chisqresult:2,chisqselector:[2,3],chisqselectormodel:[2,3],chisqselectorpath:2,chisqtest:3,chisqtestresult:3,chisquar:3,chisquaredtest:3,chisquaretest:2,choic:2,choos:[1,2,3],chosen:[1,2],chunk:2,claim:4,classif:0,classifi:[2,3],classmethod:[1,2,3,4,5],classnam:1,classof:3,classpath:4,claus:4,clazz:2,clean:2,clear:[1,2,3,4],clearcach:4,clearthreshold:3,client:5,cloglog:2,clone:1,close:[1,3,4],closest:[2,3,4],cloudwatch:5,cluster:[0,1,4,5],clustercent:[2,3],clusterdata_1:3,clusterdata_2:3,clusters:2,clusterweight:3,cmu:3,coalesc:[1,4],code:[2,3,4],codec:[1,4],coeffici:[2,3,4],coefficient_of_determin:2,coefficientmatrix:2,coefficientstandarderror:2,cogroup:[1,5],cohen:3,col1:4,col1_:4,col2:4,col:[2,3,4],coldstartstrategi:2,colin:2,collabor:2,collect:[0,1,2,3,4,5],collect_list:4,collect_set:4,collectasmap:1,colnam:4,colptr:[2,3],colsperblock:3,colstat:3,column:[0,2,3,4],columnnameofcorruptrecord:4,columnsimilar:3,com:[3,5],combfunc:1,combin:[1,2,4],combinator:2,combinebykei:[1,5],combop:1,come:4,command:[1,4],comment:4,commit:4,common:[2,3],commonli:[1,2,3],commun:2,commut:[1,5],companion:2,compar:[1,3],comparison:[2,3],compat:[1,2,3,4,5],competit:4,compil:2,complet:[1,2,3,4,5],compon:[2,3],composit:2,composition:3,compress:[1,4],compressioncodecclass:1,compris:3,comput:[1,2,3,4,5],computecolumnsummarystatist:3,computecost:[2,3],computecovari:3,computegramianmatrix:3,computeprincipalcompon:3,computeq:3,computesvd:3,computeu:3,concat:4,concat_w:4,concaten:4,concentr:[2,3],concept:[2,3],concis:4,concret:4,concurr:5,cond:4,condit:[2,3,4],conduct:[2,3],conf:[1,4],confid:[1,2,3],config:4,configur:[1,2,3,4],conflict:[2,4],confus:3,confusionmatrix:3,connect:[1,4,5],consecut:4,consequ:2,consid:[1,2,3,4],consist:[1,2,3,4],consol:4,constant:[1,2,3],constantin:3,constraint:[2,3,5],construct:[2,3,4],consum:[1,4,5],contain:[1,2,3,4,5],containsnul:4,content:[0,4],context:[0,1,2,3,5],contextu:1,conting:[2,3,4],continu:[2,3,4,5],contribut:[2,3],control:[1,2,3,4],conv:4,converg:[2,3],convergencetol:[2,3],convers:[2,4],convert:[1,2,3,4,5],convertmatrixcolumnsfromml:3,convertmatrixcolumnstoml:3,convertvectorcolumnsfromml:3,convertvectorcolumnstoml:3,cooper:2,coordin:[3,4,5],coordinatematrix:3,copi:[1,2,3,5],core:[4,5],corpu:[2,3],corr:[2,3,4],correct:[1,2,3],correctli:[3,4],correl:[2,3,4],correspond:[2,3,4,5],corrupt:4,cos:[3,4],cosh:4,cosin:[2,3,4],cosinesimilar:3,cost:[2,3,4],costli:2,could:[1,2,3,4,5],count:[1,2,3,4,5],countapprox:1,countapproxdistinct:1,countbykei:1,countbyvalu:[1,5],countbyvalueandwindow:5,countbywindow:5,countdistinct:4,counter:1,countri:4,countvector:2,countvectorizermodel:2,countvectorizerpath:2,cours:4,cov:[2,4],covar_pop:4,covar_samp:4,covari:[3,4],cover:2,covert:[2,3],cprofil:1,crash:4,crc32:4,creat:[1,2,3,4,5],create_map:4,createcombin:[1,5],createdatafram:[2,3,4],createdirectstream:5,createexternalt:4,createglobaltempview:4,createorreplaceglobaltempview:4,createorreplacetempview:4,createpollingstream:5,createrdd:5,createstream:5,createtempview:4,creation:4,credenti:5,criterion:[2,3],cross:[2,4],crossjoin:4,crosstab:4,crossvalid:2,crossvalidatormodel:2,crpc:3,csc:[2,3],cstat:3,csv:4,csv_sdf:4,ctx:1,cube:4,cume_dist:4,cumul:[3,4],currenlti:2,current:[1,2,3,4,5],current_d:4,current_timestamp:4,currentrow:4,curv:[2,3],custom:[1,4],cutler:2,cvmodel:2,cyclic:4,dai:4,danish:2,data2:2,data:[0,1,2,3,4,5],data_path:2,data_typ:4,databas:[3,4],datafram:[0,1,2,3,4],dataframenafunct:4,dataframeread:4,dataframestatfunct:4,dataframewrit:4,dataset:[0,1,2,3,4],dataseta:2,datasetb:2,datasourc:4,datastreamread:4,datastreamwrit:4,datatyp:[1,4],date1:4,date2:4,date:4,date_add:4,date_format:4,date_sub:4,datediff:4,dateformat:4,datetim:[4,5],datetyp:4,david:3,dayofmonth:4,dayofweek:4,dayofyear:4,dbname:4,dcg:3,dct:2,dctpath:2,dead:1,deal:[2,4],debug:[1,4],decai:[2,3],decayfactor:3,decid:[3,4],decim:4,decimaltyp:4,decis:[2,3],decisiontre:3,decisiontreeclassifi:2,decisiontreeclassificationmodel:2,decisiontreemodel:3,decisiontreeregressionmodel:2,decisiontreeregressor:2,declar:2,decod:[1,4,5],decomp:3,decompos:3,decomposit:3,decompress:5,decreas:[1,2,3,5],dedupl:4,deep:2,deeper:2,def:[1,3,4],defaultawscredentialsproviderchain:5,defaultminpartit:1,defaultparallel:[1,3],defaultvalu:[1,4],defin:[1,2,3,4,5],deflat:4,degre:[2,3,4],degreesoffreedom:[2,3],delai:4,delaythreshold:4,deleg:[2,3],delet:[1,2,3],delim:4,delimit:[3,4,5],dens:[2,3],dense1:[2,3],dense2:[2,3],dense3:[2,3],dense_rank:4,densematrix:[2,3],densevector:[2,3],densiti:3,depart:4,depend:[1,2,3,4,5],deploi:5,deprec:[1,2,3,4],depth:[1,2,3],deptid:4,deriv:[2,3],desc:4,descend:[1,3,4],descent:[2,3],describ:[2,3,4],describetop:[2,3],descript:[1,2],deseri:1,design:[2,3],desir:[2,3,4],destroi:[1,2],detail:[1,2,3,5],determin:[2,3,4],determinist:[3,4],develop:[3,5],developerapi:[1,2],devianc:2,devianceresidu:2,deviat:[1,2,3,4],df0:4,df1:[2,4],df2:[2,4],df3:[2,4],df4:4,df_as1:4,df_as2:4,dialect:2,dict:[1,3,4,5],dictionari:[1,2,3,4],did:[1,4],diff:4,differ:[1,2,3,4,5],difficult:2,digest:4,digit:4,dim:3,dimens:[1,2,3],dimension:[2,3,4],dir:[2,3],directli:[1,3,4,5],directori:[1,3,4,5],dirichlet:[2,3],dirnam:1,dirpath:1,disabl:[2,4],discard:2,discount:3,discoveri:[2,3],discret:[0,2,3,5],disk:[1,3,4],disk_onli:1,disk_only_2:[1,4],dispers:2,dist2:3,distanc:[2,3,4],distcol:2,distinct:[1,2,3,4,5],distnam:3,distribut:[0,1,2,4],distributed_model_path:2,distributedldamodel:2,distributedmatrix:3,divid:[1,2,3],divis:[2,3],dm1:3,dm2:3,dm3:3,dm4:3,doc:[1,2,3],docclusterkddtmw00:3,docconcentr:[2,3],doctest:[1,3,4],document:[2,3,4,5],doe:[1,2,3,4,5],doesn:4,doi:[2,3,4],doing:4,domain:4,don:[1,4],done:[1,4,5],dot:[2,3,4],dotnet:4,doubl:[2,4],doubletyp:[2,4],down:1,download:1,downweight:2,drastic:4,drawn:3,driver:[1,2,3,4,5],drop:[1,2,4],drop_dupl:4,dropdupl:4,dropglobaltempview:4,droplast:2,dropmalform:4,dropna:4,droptempt:4,droptempview:4,dsl:4,dstream:[0,3,5],dt2:2,dtc:[2,3],dtc_model:2,dtc_path:2,dtr:2,dtr_model:2,dtr_path:2,dtype:[2,4],due:[1,2,3,4],dummi:2,dump:1,dump_profil:1,duplic:[1,2,4],durat:[4,5],dure:[1,2,3,4,5],dutch:2,dynam:1,dynamicalloc:1,dynamodb:5,e_i:2,e_max:2,e_min:2,each:[1,2,3,4,5],eager:4,earli:2,earlier:5,earn:4,east:5,ecdf:3,edf:4,edit:2,edu:3,effect:[1,2,3],effici:[1,2,3,4,5],egg:1,eigenvalu:3,eigenvector:3,either:[1,2,3,4,5],elaps:5,elast:2,elasticnet:2,elasticnetparam:[2,3],electron:2,element:[1,2,3,4,5],elementtyp:4,elementwis:[2,3],elementwiseproduct:[2,3],elementwiseproductpath:2,elimin:[4,5],ellipsi:1,els:[3,4],embed:[2,3],emit:4,empir:3,empti:[1,2,3,4,5],emptyrdd:1,enabl:[4,5],enabledecompress:5,enablehivesupport:4,enclos:4,encod:[1,2,4,5],end:[1,3,4,5],endpointurl:5,endswith:4,engin:1,english:2,enough:[2,3,4],ensembl:[2,3],ensu:3,ensur:[1,5],enter:5,entir:[2,4],entri:[0,1,2,3,4,5],entropi:[2,3],env:1,environ:[1,2,3],ephemer:1,epoch:[1,4],epoch_ordin:4,eprod:[2,3],eps:3,epsilon:3,equal:[2,3,4],equat:[2,3],equi:4,equival:[1,2,3,4,5],err:4,error:[1,2,3,4,5],escap:4,escapequot:4,especi:4,essenti:2,estim:[1,2,3],estimateddocconcentr:2,estimatorparammap:2,eta:[2,3],etc:[1,4,5],euclidean:[2,3],euclideandist:2,evalu:[0,4],evaluator2:2,even:[1,2,3,4],evenli:[1,2,4],event:[2,4,5],eventtim:4,ever:4,everi:[1,2,3,4,5],everyth:4,evolv:4,exact:4,exactli:[1,2,3,4],exampl:[1,2,3,4],exce:[2,3],except:[1,2,3,4,5],exclud:2,exclus:[1,4],execut:[1,2,4,5],executor:[1,2,4],exist:[1,2,3,4,5],existingrdd:4,exp:[3,4],expand:[2,4],expans:2,expect:[1,2,3,4],expens:[1,4],experiment:[1,2,4,5],expir:5,explain:[2,3,4],explainedvari:[2,3],explainparam:2,explan:2,explicit:2,explicitli:[2,4],explod:4,exploratori:4,expm1:4,expmean:3,exponenti:[3,4],exponentialrdd:3,exponentialvectorrdd:3,expos:1,expr:4,express:[2,3,4],expstd:3,extend:[1,4],extens:2,extern:[1,4,5],extra:[2,4],extract:[2,4],extractparammap:2,fact:2,factor:[2,3],factori:[2,3,4],factoris:3,fail:[1,4],failfast:4,failur:[1,2,5],fair:1,fairli:2,fall:[1,3],fallback:1,fals:[1,2,3,4,5],falsepositiver:3,famili:[2,3,4],fast:[1,4],faster:1,fatal:1,fault:[1,5],fdr:[2,3],featur:[0,1],featureimport:2,featureindex:2,featurescol:2,featuresubsetstrategi:[2,3],feedback:2,fetch:3,few:[2,5],fewer:[1,2,3,4],field1:4,field2:4,field:[2,4],fifth:4,file1:1,file2:1,file:[1,2,3,4,5],fileinput:[1,3],filenam:1,filesystem:1,filev:1,fill:4,fillna:4,filter:[1,2,3,4,5],filterfunc:5,finalstoragelevel:2,find:[1,2,3,4],findsynonym:[2,3],finer:1,finish:1,finit:2,finnish:2,first:[1,2,3,4,5],first_product:3,first_us:3,fit:[2,3,4],fitintercept:2,five:4,fix:[1,2,3,4,5],flag:[1,4],flat:[1,2,5],flatmap:[1,5],flatmapvalu:[1,5],flatten:[1,5],fleec:1,floattyp:[2,4],floor:4,flume:0,flumeutil:5,flush:3,fmeasur:3,fmeasurebythreshold:2,fmt:2,fold:[1,2],foldbykei:1,follow:[1,2,3,4],foo:[1,4],forc:[1,2,3],forceindexlabel:2,foreach:[1,4],foreachpartit:[1,4],foreachrdd:5,forest:[2,3],forev:4,forget:[3,4],forgotten:3,fork:1,form:[1,3,4],format:[1,2,3,4],format_numb:[2,4],format_str:4,former:1,formul:3,formula:[2,3],found:[1,2,3,4],fpgrowth:[2,3],fpgrowthmodel:[2,3],fpm:0,fpr:[2,3],fraction:[1,2,3,4],frame:4,freedom:[2,3],french:2,freq:[2,3],freqitem:4,freqitemset:[2,3],freqsequ:3,frequenc:[2,3,4],frequent:[2,3,4],fri:4,friedman:2,friez:2,from:[1,2,3,4,5],from_json:4,from_unixtim:4,from_utc_timestamp:4,frombas:4,fromintern:4,fromjson:4,fromml:3,fromoffset:5,ftp:1,full:[2,3,4,5],full_out:4,fulli:[1,4],fullouterjoin:[1,5],func:[1,5],further:2,futur:[1,2],fwe:[2,3],gain:[2,3],gamma:[2,3],gammardd:3,gammavectorrdd:3,gap:[1,2,4],garbag:[1,5],gatewai:1,gaussian:[2,3],gaussianmixtur:[2,3],gaussianmixturemodel:[2,3],gaussianmixturesummari:2,gaussiansdf:2,gbt2:2,gbt:2,gbtc:2,gbtc_model:2,gbtc_path:2,gbtclassifi:2,gbtclassificationmodel:2,gbtr:2,gbtr_model:2,gbtr_path:2,gbtregressionmodel:2,gbtregressor:2,gdf:4,gencircl:3,gender:4,gener:[1,2,3,4,5],generalizedlinearregress:2,generalizedlinearregressionmodel:2,generalizedlinearregressionsummari:2,generalizedlinearregressiontrainingsummari:2,generatelinearinput:3,generatelinearrdd:3,german:2,get:[1,2,3,4,5],get_json_object:4,getact:5,getactivejobsid:1,getactiveorcr:5,getactivestageid:1,getaggregationdepth:2,getal:1,getalpha:2,getbinari:2,getblocks:2,getbucketlength:2,getcachenodeid:2,getcasesensit:2,getcensorcol:2,getcheckpointfil:[1,2],getcheckpointinterv:2,getclassifi:2,getcoldstartstrategi:2,getconf:[1,4],getdegre:2,getdocconcentr:2,getdroplast:2,getelasticnetparam:2,getestim:2,getestimatorparammap:2,getevalu:2,getfamili:2,getfdr:2,getfeatureindex:2,getfeaturescol:2,getfeaturesubsetstrategi:2,getfield:4,getfinalstoragelevel:2,getfitintercept:2,getforceindexlabel:2,getformula:2,getfpr:2,getfw:2,getgap:2,gethandleinvalid:2,getimplicitpref:2,getimpur:2,getindic:2,getinitialweight:2,getinitmod:2,getinitstep:2,getinputcol:2,getintermediatestoragelevel:2,getinvers:2,getisoton:2,getitem:4,getitemcol:2,getitemscol:2,getjobidsforgroup:1,getjobinfo:1,getk:2,getkeeplastcheckpoint:2,getlabel:2,getlabelcol:2,getlay:2,getlearningdecai:2,getlearningoffset:2,getlink:2,getlinkpow:2,getlinkpredictioncol:2,getlocalproperti:1,getlosstyp:2,getmax:2,getmaxbin:2,getmaxcategori:2,getmaxdepth:2,getmaxit:2,getmaxmemoryinmb:2,getmaxsentencelength:2,getmetricnam:2,getmin:2,getminconfid:2,getmincount:2,getmindf:2,getmindivisibleclusters:2,getmindocfreq:2,getmininfogain:2,getmininstancespernod:2,getminsupport:2,getmintf:2,getmintokenlength:2,getmissingvalu:2,getmodeltyp:2,getn:2,getnam:[2,3],getnonneg:2,getnumbucket:2,getnumfeatur:2,getnumfold:2,getnumhasht:2,getnumitemblock:2,getnumpartit:[1,2,3,4],getnumtopfeatur:2,getnumtre:2,getnumuserblock:2,getoffset:4,getoptim:2,getoptimizedocconcentr:2,getorcr:[1,4,5],getordefault:2,getoutputcol:2,getp:2,getparam:2,getpattern:2,getpercentil:2,getpredictioncol:2,getprobabilitycol:2,getquantileprob:2,getquantilescol:2,getrank:2,getratingcol:2,getrawpredictioncol:2,getregparam:2,getrelativeerror:2,getrootdirectori:1,getscalingvec:2,getse:2,getselectortyp:2,getsmooth:2,getsolv:2,getsplit:2,getstag:2,getstageinfo:1,getstandard:2,getstat:2,getsteps:2,getstopword:2,getstoragelevel:1,getstrategi:2,getsubsamplingr:2,getthreshold:2,gettol:2,gettolowercas:2,gettopicconcentr:2,gettopicdistributioncol:2,gettrainratio:2,getusercol:2,getvariancecol:2,getvariancepow:2,getvector:[2,3],getvectors:2,getvocabs:2,getweightcol:2,getwindows:2,getwithmean:2,getwithstd:2,gini:[2,3],give:[1,2,3,4],given:[1,2,3,4,5],gkhome:3,glaro:3,gleich:3,glm:2,glob:[1,3],global:[1,2,4],global_temp:4,glom:[1,5],glr2:2,glr:2,glr_model:2,glr_path:2,gm2:2,gmm:[2,3],gmm_model:2,gmm_path:2,goe:4,going:[1,4],good:3,googl:3,gracefulli:5,gradient:[2,3],gradientboostedtre:3,gradientboostedtreesmodel:3,grain:1,gram:[2,3],gramian:3,grape:1,graph:[3,5],graphx:1,greater:[1,3,4],greatest:[3,4],greenwald:4,grid:2,ground:3,group:[0,1,2,3,4,5],groupbi:[1,4],groupbykei:[1,5],groupbykeyandwindow:5,groupeddata:4,groupid:[1,5],grouping_id:4,groupwith:1,grow:4,growth:[2,3],guarante:[1,2,3,4],guid:5,gzip:4,gzipcodec:1,had:[1,4],hadamard:[2,3],hadoop:[1,3,4,5],hadoopfil:1,hadooprdd:1,half:3,half_even:4,half_up:4,halflif:3,han2000:2,han:2,hand:3,handl:[1,2,3,4],handleinvalid:2,happen:4,hard:4,has:[1,2,3,4,5],hasdefault:2,hash:[1,2,3,4,5],hashabl:3,hashingtf:[2,3],hashingtfpath:2,hasintercept:2,hasparam:2,hassummari:2,hasti:2,hat:[2,3],have:[1,2,3,4,5],hdf:[1,5],head:[2,4],header:4,height:4,held:2,hello:[1,4],help:[1,2],helper:[1,3],henc:[2,3],here:[1,2,3,4],hex:4,hexadecim:4,hidden:2,hierarch:3,high:[1,2,3],higher:[2,3,5],highest:[2,3],hing:2,hint:4,histogram:[1,2],histori:2,hive:4,hivecontext:4,hiveql:4,hochberg:[2,3],hoefl:3,hoffman:2,hold:[2,3],holger:3,hook_compress:1,host:5,hostnam:5,hot:2,hour:[4,5],hourli:4,how:[1,2,3,4,5],howev:[1,3,4],htf:3,html:1,http:[1,2,3,4,5],human:3,hungarian:2,hyper:2,hyperbol:4,hyperloglog:1,hyperparamet:2,hypot:4,hypothesi:[2,3],iam:5,icd:3,ice:4,icml2010:3,ida:2,idb:2,idea:2,ident:[2,4],identifi:[1,2,3,5],idf:[2,3],idfmodel:[2,3],idfpath:2,ids:[1,2],idx:4,iff:4,ignor:[2,3,4,5],ignore_exception_detail:4,ignoreleadingwhitespac:4,ignorenul:4,ignoretrailingwhitespac:4,ill:3,immedi:[1,4],immut:1,implement:[1,2,3,4,5],implicit:[2,3],implicitli:4,implicitpref:2,improv:2,impur:[2,3],imput:2,imputermodel:2,imputerpath:2,includ:[1,2,3,4,5],inclus:[4,5],incom:3,incomplet:1,inconsist:3,incorrect:2,increas:[1,2,3,4,5],increment:[1,4,5],incur:3,independ:[2,3,4],indeterminist:4,index1:3,index2:3,index:[1,2,3,4],indexedrow:3,indexedrowmatrix:3,indexof:3,indextostr:2,indextostringpath:2,indic:[1,2,3,4],individu:[1,2,3],inf:[2,3,4],infer:[1,2,3,4],inferschema:4,infin:[1,2,4],info:[1,2,3,5],inform:[1,2,3,4,5],inherit:[1,3],initcap:4,initcent:3,initi:[1,2,3,5],initializationmod:3,initializationmodel:3,initializationstep:3,initialmodel:3,initialpositioninstream:5,initialrdd:5,initialweight:[2,3],initmod:[2,3],initstep:2,initweight:3,inner:4,inout:3,input:[1,2,3,4,5],input_file_nam:4,inputcol:2,inputformat:1,inputformatclass:1,inputtoken:2,insensit:[2,4],inser:1,insert:4,insertinto:4,insid:[1,4],instal:[1,4],instanc:[1,2,3,4],instanti:[1,4],instead:[1,2,3,4],instr:4,integ:[1,2,3,4],integertyp:4,integr:4,intend:4,intent:5,intention:1,intercept:[2,3],interceptvector:2,interfac:4,intermedi:[2,3,4],intermediatestoragelevel:2,intern:[1,2,3,4,5],interoper:5,interpol:3,interpret:[1,4,5],interrupt:1,interruptoncancel:1,intersect:[1,4],interv:[2,3,4,5],intlist:4,intuit:3,intwrit:1,invalid:[2,4],invers:[2,3,4,5],invert:[2,5],invfunc:5,invoc:[1,4],invok:[1,3,4],involv:2,invreducefunc:5,ir2:2,ir_model:2,ir_path:2,irl:2,irm:3,irrecover:1,is_cach:1,isact:4,ischeckpoint:1,isdefin:2,isdistribut:2,isempti:1,isin:4,isinst:3,islargerbett:2,isloc:4,islocallycheckpoint:1,isn:4,isnan:[3,4],isnotnul:4,isnul:4,iso:4,isoton:[2,3],isotonicregress:[2,3],isotonicregressionmodel:[2,3],isset:2,isstream:4,issu:[2,3],istemporari:4,istranspos:[2,3],italian:2,itd:2,item:[1,2,3,4],item_rec:2,itemcol:2,itemfactor:2,itemscol:2,itemset:[2,3],iter:[1,2,3,4],its:[1,2,3,4,5],itself:[4,5],jaccard:2,jaccarddist:2,jar:1,java:[1,2,3,4,5],java_model:[2,3],java_obj:2,javaclassnam:4,javaload:3,javamlread:2,javamlwrit:2,javamodel:2,javamodelwrapp:3,javaparam:2,javapredictionmodel:2,javardd:5,javasav:3,javastreamingcontext:5,javastringlength2:4,javastringlength:4,javatowritableconvert:1,javavectortransform:3,jdbc:4,jdf:4,jdstream:5,jgd:4,jhivecontext:4,jmlr:[2,3],job:[1,5],job_to_cancel:1,jobgroup:1,jobid:1,john:4,join:[1,2,3,4,5],joined_df:4,jordan:[2,3],journal:[2,3],jrdd:1,jrdd_deseri:[1,5],jsc:1,json:[3,4],json_sdf:4,json_tupl:4,jsonvalu:4,jsparksess:4,jspec:4,jsq:4,jsqlcontext:4,jsqm:4,jssc:5,jstring:4,jtracker:1,just:[2,3,4],jvm:4,kafka:0,kafkamessageandmetadata:5,kafkaparam:5,kafkautil:5,karp:4,karypi:[2,3],kcl:5,kdd:3,kearslei:3,keep:[1,2,3,4],keeplastcheckpoint:2,keepseri:5,kei:[1,2,3,4,5],kept:[1,2],kerneldens:3,key1:4,key2:4,keybi:1,keyclass:1,keyconvert:1,keydecod:5,keyfunc:1,keytyp:4,keyword:[2,4],khanna:4,kind:[3,4],kinesi:0,kinesisappnam:5,kinesisutil:5,kitten:4,kmean:[2,3],kmeans2:2,kmeans_model:2,kmeans_path:2,kmeansmodel:[2,3],knob:3,know:4,known:[1,2,3,4],kolmogorov:3,kolmogorovsmirnovtest:3,kolmogorovsmirnovtestresult:3,ksmodel:3,kstest:3,kth:1,kumar:[2,3],kurtosi:4,kwarg:[2,4],l_1:3,l_2:3,label2:2,label:[2,3],labelcol:2,labeledpoint:3,lag:4,laid:4,lamb:1,lambda:[1,2,3,4],lambda_:3,languag:[1,2,3,4],larg:[1,2,3,4,5],large_broadcast:1,larger:[2,3,4],largest:[1,2,3,4],lasso:2,lassomodel:3,lassowithsgd:3,last:[1,2,3,4,5],last_dai:4,lastprogress:4,late:4,latent:[2,3],later:[2,3,4],latest:[3,4,5],latestmodel:3,latter:[1,2,3,4],layer:[1,2],lazi:3,lbfg:3,lda:[2,3],lda_distributed_model:2,lda_local_model:2,lda_path:2,ldamodel:[2,3],ldaoptim:3,lead:[3,4],leader:5,leaf:[2,3],learn:[2,3],learningdecai:2,learningoffset:2,learningr:3,leas:5,least:[1,2,3,4],leastabsoluteerror:3,leastsquareserror:3,leav:4,left:[1,2,3,4,5],left_anti:4,left_out:4,left_semi:4,leftouterjoin:[1,5],lemon:1,len:[1,2,3,4],length:[1,2,3,4,5],leo:2,less:[2,3,4],lesser:3,let:[2,3],letter:4,level:[1,2,3,4,5],levenshtein:4,li2008:2,lib:1,liblinear:3,librari:[1,4,5],libsvm:[2,3],lifetim:4,like:[1,2,3,4],likelihood:[2,3],limit:[1,2,4,5],lin:3,linalg:0,line:[1,3,4,5],lineag:[1,2],linear:[2,3],lineardatagener:3,linearli:2,linearmodel:3,linearregress:[2,3],linearregressionmodel:[2,3],linearregressionsummari:2,linearregressiontrainingsummari:2,linearregressionwithsgd:3,linearsvc:2,linearsvcmodel:2,link:2,linkpow:2,linkpredictioncol:2,list:[1,2,3,4,5],lit:4,liter:4,literatur:2,littl:1,live:5,load:[1,2,3,4,5],loaddefault:1,loaddefaultstopword:2,loadedassembl:2,loadedbinar:2,loadedbucket:2,loadedcv:2,loadeddtc:2,loadedencod:2,loadedep:2,loadedhashingtf:2,loadedidf:2,loadedimput:2,loadedindex:2,loadedinvert:2,loadedmascal:2,loadedmmscal:2,loadedmodel:2,loadedngram:2,loadednorm:2,loadedpca:2,loadedpx:2,loadedqd:2,loadedremov:2,loadedretoken:2,loadedrf:2,loadedselector:2,loadedsqltran:2,loadedstandardscal:2,loadedtoken:2,loadedv:2,loadedword2vec:2,loader:3,loadlabeledpoint:3,loadlibsvmfil:3,loadvector:3,local:[1,2,3,4],local_model_path:2,localcheckpoint:1,localdoc:3,localldamodel:2,localmodel:2,locat:[1,2,4,5],lock:1,log10:4,log1p:4,log2:[2,3,4],log:[1,2,3,4],logarithm:4,logic:4,logist:[2,3],logisticregress:[2,3],logisticregressionmodel:[2,3],logisticregressionsummari:2,logisticregressiontrainingsummari:2,logisticregressionwithlbfg:3,logisticregressionwithsgd:3,logit:2,loglevel:1,loglikelihood:2,logloss:3,lognormalrdd:3,lognormalvectorrdd:3,logperplex:2,logprior:2,longer:[1,2,4],longtyp:[2,4],longwrit:1,look:[3,4,5],lookup:1,loss:[2,3],losstyp:2,lost:2,low:[1,2,3],lower:[1,2,3,4],lowerbound:4,lowercas:2,lowest:3,lpad:4,lr2:2,lr_model:2,lr_path:2,lrm:3,lsdw6p:3,lsh:2,ltrim:4,lz4:4,lzo:4,m_t:3,machin:[2,3,5],made:[1,4],mae:2,magnitud:3,mai:[1,2,3,4,5],main:[0,1,4,5],maintain:2,major:[2,3],make:[2,3,4,5],malform:4,manag:[2,4],mani:[1,2,4],manipul:4,manner:1,map:[1,2,3,4,5],map_func:1,mapfield:4,mappartit:[1,4,5],mappartitionswithindex:[1,5],mappartitionswithsplit:1,mapper:1,mapr:1,mapreduc:[1,3],maptyp:4,mapvalu:[1,5],mari:1,mark:[1,2,4],marshal:1,marshalseri:1,mascal:2,master:[1,4,5],mat1:3,mat2:3,mat3:3,mat:3,mat_transpos:3,match:[1,2,3,4],materi:1,math:3,mathemat:[2,3,4],matric:[2,3],matrix:[2,3],matrixentri:3,matrixfactorizationmodel:3,matter:1,max:[1,2,3,4],maxab:2,maxabsscal:2,maxabsscalermodel:2,maxbatchs:5,maxbin:[2,3],maxcategori:2,maxcharspercolumn:4,maxcolumn:4,maxdepth:[2,3],maxim:[2,3],maximum:[1,2,3,4,5],maxit:2,maxiter:3,maxlocalprojdbs:3,maxmalformedlogperpartit:4,maxmemoryinmb:2,maxpatternlength:3,maxsentencelength:2,maxsiz:4,maxtermspertop:[2,3],mce:2,mce_path:2,mcm:3,md5:4,mdf:2,mean:[1,2,3,4],meanabsoluteerror:[2,3],meanapprox:1,meanaverageprecis:3,meaning:3,meansquarederror:[2,3],meant:4,measur:[2,3,4],mechan:[1,4],median:[2,4],meet:[1,4],membership:3,memori:[1,2,4],memory_and_disk:[1,2,4],memory_and_disk_2:[1,5],memory_and_disk_s:1,memory_and_disk_ser_2:1,memory_onli:[1,5],memory_only_2:1,memory_only_s:1,memory_only_ser_2:1,merg:[1,2,4],mergecombin:[1,5],mergeschema:4,mergevalu:[1,5],messag:[2,5],messagehandl:5,meta:5,metadata:[1,2,3,4,5],metastor:4,meth:3,method:[1,2,3,4,5],methodnam:2,metric:[2,3,5],metricnam:2,mh2:2,mhpath:2,michael:3,microsecond:4,might:[1,3,4],mike:4,millisecond:4,min:[1,2,3,4],minconfid:2,mincount:[2,3],mindf:2,mindivisibleclusters:[2,3],mindocfreq:[2,3],mine:[2,3],minhash:2,minhashlsh:2,minhashlshmodel:2,mini:2,minibatchfract:3,minim:[2,3,4],minimum:[1,2,3,4,5],mininfogain:[2,3],mininstancespernod:[2,3],minmaxscal:2,minmaxscalermodel:2,minmaxscalerpath:2,minpartit:[1,3],minsplit:1,minsupport:[2,3],mintf:2,mintokenlength:2,minu:4,minut:4,mismatch:[2,3],miss:[1,2,4],missingvalu:2,mix:2,mixin:[2,3],mixtur:[2,3],mkdir:1,mkdtemp:[3,4],mllib:[0,1,2],mlor:2,mlormodel:2,mlp2:2,mlp:2,mlp_model:2,mlp_path:2,mlreadabl:2,mlreader:2,mlutil:3,mlwritabl:2,mlwriter:2,mmscaler:2,mode:[2,3,4],model2:2,model3:2,model:[2,3],model_path:[2,3],modelpath:2,modeltyp:2,modif:[2,3],modifi:[1,2],modul:[0,1],modulo:2,moment:4,mon:4,monitor:[1,5],monoton:[2,3,4],monotonically_increasing_id:4,month:4,months_between:4,more:[1,2,3,4,5],most:[1,2,3,4],move:[3,5],mse:2,much:[1,4],multi:[1,2,4],multi_class_data:3,multiclass:[2,3],multiclassclassificationevalu:2,multiclassmetr:3,multilay:2,multilayerperceptronclassifi:2,multilayerperceptronclassificationmodel:2,multilin:4,multinomi:[2,3],multipl:[1,2,3,4,5],multipli:[2,3],multivari:[2,3],multivariategaussian:3,multivariatestatisticalsummari:3,murmurhash3_x86_32:2,murmurhash:2,mus:3,must:[1,2,3,4,5],mutat:1,mycustomprofil:1,mypassword:4,myrdd:1,n_t:3,n_th:3,naiv:[2,3],naivebay:[2,3],naivebayesmodel:[2,3],name:[0,1,2,3,4,5],namedtemporaryfil:[1,3],namedtupl:4,nan:[2,3,4],nanvalu:4,nanvl:4,narrow:4,nativ:4,natur:[2,3,4],nb2:2,nb_model:2,nb_path:2,nbar:1,ndarrai:[2,3],ndcg:3,ndcgat:3,nearest:[2,3],neariso:3,nearli:[1,3],necessari:2,need:[1,2,3,4],needconvers:4,neg:[2,3,4],negativeinf:4,neighbor:2,neither:2,nest:[3,4],net:2,netflix:3,netti:5,neuron:2,neutral:1,new_data:2,newapihadoopfil:1,newapihadooprdd:1,newli:[2,4],newlin:[3,4],newsess:4,nexampl:3,next:[2,4],next_dai:4,nfeatur:3,nfoo:1,ngram:2,ngrampath:2,nnnnn:1,node:[1,2,3,4],nois:3,nomin:2,non:[1,2,3,4],none:[1,2,3,4,5],nonneg:[2,3],nonposit:3,nonzero:[2,3],noqa:1,nor2:3,nor:3,norm:[2,3],normal:[1,2,3,4],normalize_whitespac:3,normalizerpath:2,normalrdd:3,normalvectorrdd:3,norml1:3,norml2:3,norwegian:2,notat:3,note:[2,3,4,5],now:[2,4],npart:3,npoint:3,ntile:4,nullabl:4,nulldevi:2,nullhypothesi:3,nulltyp:4,nullvalu:4,num:[1,2,3,4,5],number:[1,2,3,4,5],numbit:4,numbucket:2,numclass:[2,3],numcol:[2,3],numcolblock:3,numer:[1,2,3,4],numfeatur:[2,3],numfold:2,numhasht:2,numinst:2,numitem:2,numitemblock:2,numiter:[2,3],numlabel:2,numnearestneighbor:2,numnod:[2,3],numnonzero:[2,3],numpartit:[1,2,3,4,5],numpi:[2,3],numrecentprogressupd:4,numrow:[2,3],numrowblock:3,numslic:1,numtopfeatur:[2,3],numtre:[2,3],numus:2,numuserblock:2,obj:[1,4],object:[1,2,3,4,5],objectivehistori:2,observ:[2,3],obtain:[2,3],occur:[2,3],occurr:[2,4],off:[1,3,4],off_heap:1,offset:[4,5],offsetrang:5,often:[1,2,4],old:[1,3,5],older:4,omit:4,onbatchcomplet:5,onbatchstart:5,onbatchsubmit:5,onc:[1,2,4,5],one:[1,2,3,4,5],oneatatim:5,onehot:2,onehotencod:2,onehotencoderpath:2,ones:3,onethird:[2,3],onevsrest:2,onevsrestmodel:2,onli:[1,2,3,4,5],onlin:[2,3,4],onoutputoperationcomplet:5,onoutputoperationstart:5,onreceivererror:5,onreceiverstart:5,onreceiverstop:5,open:1,openhook:1,oper:[1,2,3,4,5],opt1:4,opt2:4,opt3:4,optim:[2,3,4],optimizedocconcentr:2,optimum:2,option:[1,2,3,4,5],orantiton:2,orc:4,orc_df:4,orc_partit:4,order:[1,2,3,4,5],orderbi:[2,4],ordin:4,ordinari:2,org:[1,2,3,4,5],orient:3,origin:[1,2,3],originalmax:2,originalmin:2,origvec:2,orthogon:3,oserror:3,other:[1,2,3,4,5],otherwis:[1,2,3,4],our:[1,3],out:[1,2,3,4],out_a:2,out_b:2,outcom:[2,3],outer:[1,4,5],output:[1,2,3,4],outputcol:2,outputformat:1,outputformatclass:1,outputmod:4,outputoperationcomplet:5,outputoperationstart:5,outsid:[2,4,5],over:[1,2,3,4,5],overflow:4,overlap:2,overrid:[1,2,4],overwrit:[2,4],ovr:2,ovr_model:2,owlqn:2,own:[2,4,5],p362:4,p7c96j6:3,packag:0,package_extens:1,pad:[2,4],page:0,pair:[1,2,3,4,5],panda:4,papadimitri:4,paper:[2,3],parallel:[1,2,3,4,5],param:[0,3,4,5],paramet:[1,2,3,4,5],parametr:2,paramgridbuild:2,parammap:2,paramnam:2,paramt:2,parent:[1,2,3,5],parquet:[3,4],parquet_partit:4,parquet_sdf:4,pars:[3,4],part:[1,3,4],particular:[1,3],partit:[1,2,3,4,5],partition:[1,5],partitionbi:[1,4,5],partitionfunc:[1,5],partitionid:1,pass:[1,2,3,4],password:4,past:4,path:[1,2,3,4],pattern:[1,2,3,4],paul:3,pav:3,pca:[2,3],pca_featur:2,pcamodel:2,pcapath:2,pdf:3,pearson:[2,3,4],pearsoncorr:[2,3],pei:3,penalti:[2,3],peopl:4,people1:4,per:[1,2,3,4,5],percent_rank:4,percentil:[2,3,4],perceptron:2,perform:[1,2,3,4],period:[1,3,5],permiss:4,permit:2,permut:2,perplex:2,persist:[1,3,4,5],person:4,peter:4,pfp:2,phrase:3,physic:4,physica:3,pic:3,pick:[2,5],pickl:1,pickle_registri:1,picklefil:1,pickleseri:1,pid:4,piec:2,piecewis:3,pipe:1,pipelin:0,pipelinemodel:2,pivot:4,pivot_col:4,place:[1,2,3,4],placehold:2,plan:[2,4],pleas:[3,4],plu:[3,4],poi:3,point:[0,1,2,3,4,5],poisson:[2,3],poissonrdd:3,poissonvectorrdd:3,poli:2,polici:5,poll:5,polyexpansionpath:2,polynomi:2,polynomialexpans:2,pool:[1,2,3],poorli:2,popul:[3,4],port:5,portable_hash:[1,5],portugues:2,pos:4,posexplod:4,posit:[2,3,4,5],positiveinf:4,possibl:[2,3,4],potenti:1,pow:4,power:[2,3,4],poweriterationclust:3,poweriterationclusteringmodel:3,pprint:5,practic:[1,2],pre:[2,3],preced:[2,4],precis:[2,3,4],precisionat:3,precisionbythreshold:2,predic:[1,4,5],predict:[2,3],predictal:3,predictionandlabel:3,predictionandobserv:3,predictioncol:2,predicton:3,predictonvalu:3,predictor:2,predictquantil:2,predictsoft:3,prefer:[1,2,3],prefersdecim:4,prefix:[3,5],prefixspan:3,prefixspanmodel:3,prepar:1,prepend:2,present:[2,3,4],preserv:2,preservespartit:[1,5],prevent:3,previou:[3,4,5],previous:1,prime:2,primit:[1,4],primitivesasstr:4,princip:[2,3],print:[1,2,3,4,5],printabl:1,printf:4,printschema:4,prior:[2,3,4],prioriti:[1,2,3],privat:2,probabilist:2,probabilitycol:2,probabilti:3,probabl:[1,2,3,4],probit:2,problem:[2,3],procedur:[2,3],process:[1,2,3,4,5],processallavail:4,processingtim:4,produc:[1,2,3,4],product:[1,2,3,4],productfeatur:3,productid:3,products_for_us:3,profil:1,profiler_cl:1,program:[1,4,5],programm:1,progress:[1,4],project:[2,3,4],propag:[1,4],properti:[1,3,4,5],proport:[2,3],propos:4,provid:[1,2,3,4,5],pst:4,pstat:1,pub:3,pull:5,purpos:4,put:[2,4],pvalu:[2,3],py4jjavaerror:4,pyfil:1,pyrolit:1,pyspark:0,python:[1,2,3,4],pythonstreaminglisten:5,qds:2,qrdecomposit:3,quadrat:[2,3],qualifi:[1,4],qualiti:3,quantil:[2,4],quantilediscret:2,quantilediscretizerpath:2,quantileprob:2,quantilescol:2,quarter:4,queri:[2,3,4,5],query_explain:4,querynam:4,queue:5,queuestream:5,quickli:2,quorum:5,quot:4,quotat:4,quoteal:4,r26:2,radian:4,rais:[1,2,3,4],rand:4,randn:4,random:[0,1,2,4],randomforest:3,randomforestclassifi:2,randomforestclassificationmodel:2,randomforestmodel:3,randomforestregressionmodel:2,randomforestregressor:2,randomli:[1,2,4],randomrdd:3,randomsplit:[1,4],rang:[1,2,3,4,5],range0:4,rangebetween:4,rank:[2,3,4],rankingmetr:3,rare:2,rate:[1,2,3],rather:[1,2,3,4],ratingcol:2,ratio:[2,4],raw:[2,3],rawpredict:2,rawpredictioncol:2,rcond:3,rdd1:1,rdd2:1,rdd:[0,1,2,3,4,5],rdd_a:5,rdd_b:5,re_path:2,reach:[2,3],read:[1,2,4,5],readabl:3,readlin:1,readstream:4,real:[2,3,4],reason:4,recal:[2,3],recallbythreshold:2,receiv:[1,2,3,5],receivererror:5,receiverstart:5,receiverstop:5,recent:[1,2,3,4],recentprogress:4,reciproc:3,recogn:[3,5],recommend:[0,1,4],recommendforallitem:2,recommendforallus:2,recommendproduct:3,recommendproductsforus:3,recommendus:3,recommendusersforproduct:3,recomput:[1,2],record:[1,3,4,5],recordlength:[1,5],recov:5,recreat:5,rectangular:4,recurs:[1,4],redistribut:1,reduc:[1,2,5],reducebykei:[1,5],reducebykeyandwindow:5,reducebykeyloc:1,reducebywindow:5,reducefunc:5,reduct:[2,5],redund:4,refer:[1,2,3],reflect:4,refresh:4,refresht:4,regex:[2,4],regexp:4,regexp_extract:4,regexp_replac:4,regextoken:2,regextokenizerpath:2,region:5,regionnam:5,regist:[1,4],registerdataframeast:4,registerfunct:4,registerjavafunct:4,registertempt:4,registr:4,regparam:[2,3],regress:0,regressionevalu:2,regressionmetr:3,regtyp:3,regular:[2,3,4],reimplement:3,rel:[1,2,3,4],relat:[1,2,4,5],relationship:2,relativeerror:[2,4],relativesd:1,releas:[1,2,5],relev:[3,4],reliabl:[1,5],remain:2,rememb:5,remov:[1,2,3,4],renam:4,rep:4,repartit:[1,4,5],repartitionandsortwithinpartit:1,repeat:4,repeatedli:2,replac:[1,2,3,4],replic:1,report:[1,3,5],repres:[1,2,3,4,5],represent:[1,2,3,4,5],request:[4,5],requir:[1,2,3,4],rescal:[2,3],research:3,reseri:1,resettermin:4,reshap:[2,3],residu:2,residualdegreeoffreedom:2,residualdegreeoffreedomnul:2,residualstyp:2,resili:[0,1],resolv:[1,4],resolvedrformula:2,respect:[3,4,5],respond:1,respons:2,restart:4,result:[1,2,3,4,5],resultvec:2,retain:[1,4,5],retainedjob:1,retainedstag:1,retoken:2,retriev:[2,3,4],returntyp:4,reus:1,revers:4,rf2:2,rfc:2,rfc_model:2,rfc_path:2,rformula:2,rformulamodel:2,rformulapath:2,rfr:2,rfr_model:2,rfr_path:2,rice:3,richard:3,ridg:2,ridgeregressionmod:3,ridgeregressionmodel:3,ridgeregressionwithsgd:3,right:[1,2,3,4,5],right_out:4,rightouterjoin:[1,5],rint:4,rise:3,risk:[2,3],ritz:3,rlike:4,rmse:2,rmtree:3,rng:3,rnlt:4,robert:3,roc:[2,3],role:5,rollup:4,root:[1,2,3,4],rootmeansquarederror:[2,3],roughli:1,round:[2,3,4],row1:4,row2:4,row3:4,row:[2,3,4],row_numb:4,rowindic:[2,3],rowmatrix:3,rowsbetween:4,rowsperblock:3,rpad:4,rpc:5,rsd:4,rtrim:4,rule:[2,3],run:[1,2,3,4,5],runid:4,runjob:1,runtim:4,russian:2,ryan:3,ryantib:3,sacrific:1,safe:[1,4],sai:4,said:2,salari:4,same:[1,2,3,4,5],samelda:2,samelocalmodel:2,samemodel:[2,3],samemu:3,samesigma:3,sampl:[1,2,3,4],sample_fpgrowth:2,sample_multiclass_classification_data:2,samplebi:4,samplebykei:1,samplestdev:1,samplevari:1,samplingratio:4,sat:4,satisfi:[1,5],save:[1,2,3,4,5],saveabl:3,saveashadoopdataset:1,saveashadoopfil:1,saveaslibsvmfil:3,saveasnewapihadoopdataset:1,saveasnewapihadoopfil:1,saveaspicklefil:1,saveassequencefil:1,saveast:4,saveastextfil:[1,3,5],savemod:4,scala:[1,3,4],scalabl:3,scalar:[2,4],scale:[2,3,4],scaler:2,scalerpath:2,scalingvec:2,scalingvector:3,scan:[1,2,3,4],scenario:2,schedul:[1,4,5],schema:4,scheme:4,schenker:4,scikit:2,scipi:[2,3],scope:2,score:[2,3],scoreandlabel:[2,3],sdf:4,sdf_schema:4,search:[0,1,2,4],second:[1,3,4,5],secretkei:5,secur:5,see:[1,2,3,4,5],seed:[1,2,3,4],seen:[2,4,5],select:[2,3,4],selectedfeatur:2,selectexpr:4,selector:[2,3],selectortyp:[2,3],self:[1,2],semant:1,send:[1,2,5],sensit:[2,4],sent:[1,2,5],sentenc:[2,3,4],sep:4,separ:[2,3,4],seqfunc:1,seqop:1,sequenc:[1,2,3,4,5],sequencefil:1,sequencefileoutputformat:1,sequenti:[1,3,4],sequncefil:1,serd:4,serial:1,server:5,servic:5,session:[2,4,5],set:[1,2,3,4,5],setaggregationdepth:2,setal:1,setalpha:2,setappnam:1,setbandwidth:3,setbinari:[2,3],setblocks:2,setbucketlength:2,setcachenodeid:2,setcasesensit:2,setcensorcol:2,setcheckpointdir:[1,4],setcheckpointinterv:2,setclassifi:2,setcoldstartstrategi:2,setconf:4,setdecayfactor:3,setdegre:2,setdocconcentr:2,setdroplast:2,setelasticnetparam:2,setestim:2,setestimatorparammap:2,setevalu:2,setexecutorenv:1,setfamili:2,setfdr:[2,3],setfeatureindex:2,setfeaturescol:2,setfeaturesubsetstrategi:2,setfinalstoragelevel:2,setfitintercept:2,setforceindexlabel:2,setformula:2,setfpr:[2,3],setfw:[2,3],setgap:2,sethalflif:3,sethandleinvalid:2,setifmiss:1,setimplicitpref:2,setimpur:2,setindic:2,setinitialcent:3,setinitialweight:[2,3],setinitmod:2,setinitstep:2,setinputcol:2,setintermediatestoragelevel:2,setinvers:2,setisoton:2,setitemcol:2,setitemscol:2,setjobgroup:1,setk:[2,3],setkeeplastcheckpoint:2,setlabel:2,setlabelcol:2,setlay:2,setlearningdecai:2,setlearningoffset:2,setlearningr:3,setlink:2,setlinkpow:2,setlinkpredictioncol:2,setlocalproperti:1,setloglevel:1,setlosstyp:2,setmast:1,setmax:2,setmaxbin:2,setmaxcategori:2,setmaxdepth:2,setmaxit:2,setmaxmemoryinmb:2,setmaxsentencelength:2,setmetricnam:2,setmin:2,setminconfid:2,setmincount:[2,3],setmindf:2,setmindivisibleclusters:2,setmindocfreq:2,setmininfogain:2,setmininstancespernod:2,setminsupport:2,setmintf:2,setmintokenlength:2,setmissingvalu:2,setmodeltyp:2,setn:2,setnam:[1,2],setnonneg:2,setnumblock:2,setnumbucket:2,setnumfeatur:2,setnumfold:2,setnumhasht:2,setnumitemblock:2,setnumiter:3,setnumpartit:[2,3],setnumtopfeatur:[2,3],setnumtre:2,setnumuserblock:2,setoptim:2,setoptimizedocconcentr:2,setoutputcol:2,setp:2,setparam:2,setpattern:2,setpercentil:[2,3],setpredictioncol:2,setprobabilitycol:2,setquantileprob:2,setquantilescol:2,setrandomcent:3,setrank:2,setratingcol:2,setrawpredictioncol:2,setregparam:2,setrelativeerror:2,setsampl:3,setscalingvec:2,setse:[2,3],setselectortyp:[2,3],setsmooth:2,setsolv:2,setsparkhom:1,setsplit:2,setstag:2,setstandard:2,setstat:2,setsteps:2,setstopword:2,setstrategi:2,setsubsamplingr:2,setsystemproperti:1,setter:[1,3],setthreshold:[2,3],settol:2,settolowercas:2,settopicconcentr:2,settopicdistributioncol:2,settrainratio:2,setup:5,setupfunc:5,setusercol:2,setvariancecol:2,setvariancepow:2,setvectors:[2,3],setvocabs:2,setweightcol:2,setwindows:[2,3],setwithmean:[2,3],setwithstd:[2,3],sever:4,sgd:3,sha1:4,sha2:4,sha:4,shallow:2,shape:3,share:[1,3,4],shell:1,shift:[2,4],shiftleft:4,shiftright:4,shiftrightunsign:4,ship:1,shortcut:2,shorten:4,shorter:4,shorthand:4,shorttyp:4,should:[1,2,3,4,5],shouldn:3,show:[1,2,4],show_profil:1,shown:4,shrink:3,shuffl:[1,3,4],shut:1,shutil:3,si_model:2,side:[1,2,3,4],sigma:3,sigmoid:2,sign:4,signum:4,silent:4,sim:3,similar:[2,3,4,5],similarli:1,simpl:[2,3,4],simpledateformat:4,simplestr:4,simpli:[2,3,4],sin:[3,4],sinc:[1,2,3,4],sine:4,singl:[1,2,3,4,5],singleton:1,singular:3,singularvaluedecomposit:3,sinh:4,sink:[4,5],sit:4,site:4,size:[1,2,3,4],skew:4,skinni:3,skip:[1,2,3,4],slave:5,sleep:1,slen:4,slice:[2,4,5],slicer:2,slide:5,slidedur:[4,5],slow:1,slower:5,small:[1,2,3,4],smaller:[1,2,3],smallest:3,smirnov:3,smooth:[2,3],snappi:4,socket:5,sockettextstream:5,soft:3,softlib:3,softmax:[2,3],softpredict:3,solv:[2,3],solver:2,some:[1,2,3,4],someth:1,somewhat:1,sort:[1,2,3,4],sort_arrai:4,sortbi:1,sortbykei:1,sortwithinpartit:4,soundex:4,sourc:[1,2,3,4,5],space:[1,2,3,4],span:4,spanish:2,spark:[1,2,3,4,5],spark_partition_id:4,spark_us:1,sparkconf:[1,4],sparkcontext:[0,1,3,4,5],sparkfil:1,sparkhom:1,sparkjobinfo:1,sparksess:[2,4],sparkstageinfo:1,sparkui:1,sparkus:1,spars:[2,3],sparse1:[2,3],sparse_data:3,sparsematrix:[2,3],sparsevector:[2,3],sparsiti:2,spearman:[2,3],spearmancorr:[2,3],special:[1,2,4],specif:[1,2,3,4,5],specifi:[1,2,3,4,5],speed:[2,4],split:[1,2,3,4],splitindex:1,sql:[0,1,2],sql_ctx:4,sqlconf:4,sqlcontext:[0,2,3,4],sqlqueri:4,sqltran:2,sqltransform:2,sqltransformerpath:2,sqm:4,sqrt:[2,3,4],squar:[2,3,4],squared_dist:[2,3],srccol:4,ssc:5,sssxxx:4,stabil:2,stabl:2,stack:[2,3],stage:[1,2],stageid:1,stai:4,stamp:4,standalon:4,standard:[1,2,3,4],standardscal:[2,3],standardscalarmodel:3,standardscalermodel:[2,3],standardscalerpath:2,start:[1,2,3,4,5],start_job:1,startpo:4,startswith:4,starttim:[1,4],stat:[0,1,4],statcount:1,state:[1,4,5],statement:[2,4],statist:[2,3,4],statu:[1,4],statustrack:1,std:[2,3],stddev:4,stddev_pop:4,stddev_samp:4,stdev:[1,3],stdout:1,steinbach:[2,3],step:[1,2,3,4],stepsiz:[2,3],still:4,stkm:3,stochast:[2,3],stop:[1,2,3,4,5],stop_job:1,stopgracefulli:5,stopsparkcontext:5,stopword:2,stopwordremov:2,stopwordsremov:2,stopwordsremoverpath:2,storag:[1,2,3,4,5],storagelevel:[1,2,3,4,5],store:[2,3,4,5],str:[1,2,3,4],strata:4,strategi:2,stratifi:[1,4],stratum:4,stream:[0,1,3],streaming_queri:4,streamingcontext:[0,5],streamingkmean:3,streamingkmeansmodel:3,streaminglinearalgorithm:3,streaminglinearregressionwithsgd:3,streaminglisten:5,streaminglogisticregressionwithsgd:3,streamingqueri:4,streamingqueryexcept:4,streamingquerymanag:4,streamingqueryprogress:4,streamlib:1,streamnam:5,strength:2,strictli:[2,3],stride:4,string:[1,2,3,4,5],stringifi:3,stringinddf:2,stringindex:2,stringindexermodel:2,stringindexerpath:2,stringlengthint:4,stringlengthstr:4,stringtyp:4,strongli:1,struct1:4,struct2:4,struct:4,structfield:4,structtyp:4,structur:[2,4],stsassumerolearn:5,stsexternalid:5,stssessionnam:5,style:4,sub:3,subarrai:2,subclass:2,submit:[1,5],subnam:4,subpackag:0,subprotocol:4,subsamplingr:2,subsequ:[1,4],subset:[1,2,3,4],substr:4,substring_index:4,subtract:[1,3,4,5],subtractbykei:1,suffici:2,suffix:5,suggest:[1,2],suitabl:4,sum:[1,2,3,4],sumapprox:1,sumdistinct:4,summari:[2,3,4],sun:4,suppli:[2,3],support:[1,2,3,4],supportedfeaturesubsetstrategi:[2,3],supportedimpur:2,supportedlosstyp:2,supress:1,sure:5,surrog:2,surrogatedf:2,survei:2,surviv:2,svd:3,svd_model:3,svec:2,svm2:2,svm:[2,3],svm_model:2,svm_path:2,svmmodel:3,svmwithsgd:3,swedish:2,sym:3,symbol:2,symmetr:3,synchron:4,synonym:3,syntax:2,sys:4,system:[1,3,4,5],tabl:[2,4],table1:4,tablenam:4,take:[1,2,3,4],taken:2,takeord:1,takesampl:1,tall:3,tallskinnyqr:3,tan:4,tangent:4,tanh:4,tapia:3,target:[1,2,3,4],task:[1,2,4],taskattemptid:1,taskcontext:1,tcp:5,techniqu:[2,3],technometr:3,temp:4,temp_path:[2,3],tempdir:1,tempfil:[1,3,4],tempfile2:1,tempfile3:1,temporari:4,temporarili:2,temptablealreadyexistsexcept:4,ten:4,term:[1,2,3],termin:[2,3,4,5],termindic:2,terminolog:[2,3],termweight:2,test0:2,test1:2,test2:2,test:[1,2,3,4],test_support:4,testdf:2,testfil:1,testset:3,text:[1,2,3,4,5],text_sdf:4,textfil:[1,4],textfilestream:5,textinputformat:1,tfidf:3,than:[1,2,3,4,5],that_queri:4,thei:[1,2,3,4,5],them:[1,2,3,4,5],theoret:[2,3],therefor:3,theta:[2,3,4],thi:[1,2,3,4,5],third:4,this_queri:4,those:[1,2,3,4],thread:[1,4,5],three:[1,2,4,5],thresh:4,threshold:[2,3],through:[1,2,3,4],thrown:[2,4],thu:[1,2,3,4],tibshirani:[2,3],tie:4,tied:4,ties:4,time:[1,2,3,4,5],timecolumn:4,timeout:[1,4,5],timestamp:4,timestampformat:4,timestamptyp:4,timeunit:3,timezon:4,tinyint:4,tinyurl:3,tip:5,tmp2:1,tmp:1,tmpfile:1,tmptabl:4,to_dat:4,to_json:4,to_list:1,to_profil:1,to_replac:4,to_timestamp:4,to_upp:4,to_utc_timestamp:4,toarrai:[2,3],tobas:4,toblockmatrix:3,toboolean:2,tocoordinatematrix:3,todebugstr:[1,2,3],todegre:4,todens:[2,3],todf:[2,4],todo:2,tofloat:2,togeth:[1,2,3,4],toggl:2,toindexedrowmatrix:3,toint:2,tointern:4,tointernald:4,tojson:4,token:[2,3,4],tokenizerpath:2,tol:2,toler:[1,2,3,5],tolist:[2,3],tolistfloat:2,tolistint:2,toliststr:2,toloc:2,tolocaliter:[1,4],tolocalmatrix:3,tolowercas:2,tom:[2,4],too:[2,4],tool:5,top:[1,2,3,4],topanda:4,topic:[2,3,5],topic_nam:5,topicandpartit:5,topicconcentr:[2,3],topicdistribut:2,topicdistributioncol:2,topics_expect:3,topicsmatrix:[2,3],topolar:4,toradian:4,torowmatrix:3,tospars:[2,3],tostr:[1,2],total:[1,2,3,4],totaliter:2,totalnumnod:[2,3],tovector:2,tpr:2,tr96640:3,trace:[1,2],traceback:[1,2,3,4],track:[1,2,4,5],trade:3,trail:4,train:[2,3],trainclassifi:3,trainer:2,trainimplicit:3,trainingloglikelihood:2,trainingsummari:2,trainon:3,trainratio:2,trainregressor:3,trainvalidationsplit:2,trainvalidationsplitmodel:2,trait:3,transact:3,transform:[2,3,5],transformfunc:5,transformwith:5,translat:[1,4],transpos:3,treat:[2,3,4],tree:[0,1,2,4],treeaggreg:[1,2],treeboost:2,treeensemblemodel:3,treereduc:1,treeweight:2,tri:2,triangular:3,trick:[2,3],trigger:[1,4],trim:4,trim_horizon:5,trosset:3,truepositiver:3,trunc:4,truncat:[1,2,3,4],trust:5,truth:3,tue:4,tumbl:4,tune:0,tupl:[1,2,3,4],turkish:2,turn:[1,4],tvalu:2,tvs:2,tvsmodel:2,tweedi:2,two:[1,2,3,4,5],txt:[1,2,4],type:[0,1,2,3,5],typeconvert:2,typeerror:[2,3],typenam:4,typic:2,u612:4,udf:4,udfregistr:4,uhrbach:4,uid:2,uiweburl:1,umn:3,unbase64:4,unbias:[2,4],unbound:4,unboundedfollow:4,unboundedpreced:4,uncachet:4,uncensor:2,unchang:2,undefin:[2,3],under:[1,2,3],underflow:4,underli:[2,3,4],unhex:4,unicod:[1,5],unifi:5,uniform:3,uniformrdd:3,uniformvectorrdd:3,union:[1,4,5],unional:4,uniqu:[1,2,3,4,5],unit:[1,2,3,4],unitari:2,univari:[2,3],unix:4,unix_timestamp:[4,5],unknown:[2,3,4],unless:2,unlimit:4,unmatch:4,unnecessari:4,unpars:4,unpersist:[1,3,4],unpredict:3,unquot:4,unset:2,unsign:4,unspecifi:3,unsupport:4,until:[1,2,3,4],untiloffset:5,updat:[1,2,3,4,5],updatefunc:5,updatestatebykei:5,upon:2,upper:[2,3,4],upperbound:4,upstream:4,uri:[1,3],url:[1,4,5],usabl:1,usag:[1,2,3,4],use:[1,2,3,4,5],use_unicod:[1,4],used:[1,2,3,4,5],usedisk:1,useful:[1,2,3,4],usememori:1,useoffheap:1,user:[1,2,3,4],user_product:3,user_rec:2,usercol:2,userfactor:2,userfeatur:3,userid:3,users_for_product:3,uses:[1,2,3,4,5],using:[1,2,3,4,5],usual:2,utc:4,utf8:5,utf8_decod:5,utf:[1,4,5],util:[0,4],val:4,valid:[1,2,3,4,5],validatedata:3,validationmetr:2,valu:[1,2,3,4,5],value12:4,value1:[1,3,4],value2:[1,3,4],valueclass:1,valuecontainsnul:4,valueconvert:1,valuedecod:5,valueerror:1,valuetyp:4,var_pop:4,var_samp:4,vari:[1,3],variabl:[1,2,3],varianc:[1,2,3,4],variancecol:2,variancepow:2,variant:[2,4],variat:[2,4],variou:[1,4,5],vec:[2,3],vecassembl:2,vector:[1,2,3],vectorassembl:2,vectorassemblerpath:2,vectorindex:2,vectorindexermodel:2,vectorindexerpath:2,vectors:[2,3],vectorslic:2,vectorslicerpath:2,vectortransform:3,vectorudt:2,veri:[1,2,3,4],verifi:4,verifyschema:4,verlag:3,version:[1,2,3,4],vertex:3,via:[1,2,4],view:4,violat:[2,3],vocabs:[2,3],vocabulari:[2,3],wai:[1,2],wait:[4,5],want:[2,3,4,5],warin:3,warn:[1,2,3],watermark:4,weak:1,web:[1,4],wed:4,week:4,weekofyear:4,weibul:2,weight:[1,2,3,4],weightag:3,weightcol:2,weightedfalsepositiver:3,weightedfmeasur:3,weightedprecis:[2,3],weightedrecal:[2,3],weightedtruepositiver:3,well:[1,2,3],were:4,what:1,whatev:4,when:[1,2,3,4,5],where:[1,2,3,4,5],wherea:2,whether:[1,2,3,4],which:[1,2,3,4,5],white:[1,2],whitespac:4,who:1,whole:4,wholetextfil:1,whose:[1,2,3,4],width:[4,5],wiki:2,wikipedia:[2,3],window:[2,3,4,5],windowdur:[4,5],windows:[2,3],windowspec:4,wise:[2,3,4],wish:[1,5],withcolumn:4,withcolumnrenam:4,within:[1,2,3,4,5],withmean:[2,3],without:[1,2,3,4,5],withreplac:[1,4],withstd:[2,3],withwatermark:4,won:1,word2vec:[2,3],word2vecmodel:[2,3],word2vecpath:2,word:[2,3,4],work:[1,2,3,4],worker:[1,2,5],workshop:3,world:1,would:[1,2,3,4],wrap:4,wrapper:[2,3,4],writabl:1,write:[1,2,3,4],writer:4,writestream:4,written:[1,4,5],wrong_kei:4,wrriten:5,www:3,x_t:3,xmean:3,xml:4,xrang:1,xvarianc:3,yarn:1,year:4,yes:4,yet:[1,4],yield:1,you:[1,2,3,4,5],your:[1,4,5],yourself:5,yyi:4,yyyi:4,zero:[1,2,3,4],zerovalu:1,zip:[1,3,4],zipwithindex:1,zipwithuniqueid:1,zkquorum:5,zlib:4,zone:4,zookeep:5},titles:["Welcome to Spark Python API Docs!","pyspark package","pyspark.ml package","pyspark.mllib package","pyspark.sql module","pyspark.streaming module"],titleterms:{"class":0,"function":4,api:[0,2],classif:[2,3],cluster:[2,3],content:[1,5],context:4,core:0,distribut:3,doc:0,evalu:[2,3],featur:[2,3],flume:5,fpm:[2,3],indic:0,kafka:5,kinesi:5,linalg:[2,3],mllib:3,modul:[2,3,4,5],packag:[1,2,3],param:2,pipelin:2,pyspark:[1,2,3,4,5],python:0,random:3,recommend:[2,3],regress:[2,3],spark:0,sql:4,stat:[2,3],stream:[4,5],subpackag:1,tabl:0,tree:3,tune:2,type:4,util:[2,3],welcom:0}})
\ No newline at end of file
+Search.setIndex({docnames:["index","pyspark","pyspark.ml","pyspark.mllib","pyspark.sql","pyspark.streaming"],envversion:53,filenames:["index.rst","pyspark.rst","pyspark.ml.rst","pyspark.mllib.rst","pyspark.sql.rst","pyspark.streaming.rst"],objects:{"":{pyspark:[1,0,0,"-"]},"pyspark.Accumulator":{add:[1,2,1,""],value:[1,3,1,""]},"pyspark.AccumulatorParam":{addInPlace:[1,2,1,""],zero:[1,2,1,""]},"pyspark.BasicProfiler":{profile:[1,2,1,""],stats:[1,2,1,""]},"pyspark.Broadcast":{destroy:[1,2,1,""],dump:[1,2,1,""],load:[1,2,1,""],unpersist:[1,2,1,""],value:[1,3,1,""]},"pyspark.MarshalSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.PickleSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.Profiler":{dump:[1,2,1,""],profile:[1,2,1,""],show:[1,2,1,""],stats:[1,2,1,""]},"pyspark.RDD":{aggregate:[1,2,1,""],aggregateByKey:[1,2,1,""],cache:[1,2,1,""],cartesian:[1,2,1,""],checkpoint:[1,2,1,""],coalesce:[1,2,1,""],cogroup:[1,2,1,""],collect:[1,2,1,""],collectAsMap:[1,2,1,""],combineByKey:[1,2,1,""],context:[1,3,1,""],count:[1,2,1,""],countApprox:[1,2,1,""],countApproxDistinct:[1,2,1,""],countByKey:[1,2,1,""],countByValue:[1,2,1,""],distinct:[1,2,1,""],filter:[1,2,1,""],first:[1,2,1,""],flatMap:[1,2,1,""],flatMapValues:[1,2,1,""],fold:[1,2,1,""],foldByKey:[1,2,1,""],foreach:[1,2,1,""],foreachPartition:[1,2,1,""],fullOuterJoin:[1,2,1,""],getCheckpointFile:[1,2,1,""],getNumPartitions:[1,2,1,""],getStorageLevel:[1,2,1,""],glom:[1,2,1,""],groupBy:[1,2,1,""],groupByKey:[1,2,1,""],groupWith:[1,2,1,""],histogram:[1,2,1,""],id:[1,2,1,""],intersection:[1,2,1,""],isCheckpointed:[1,2,1,""],isEmpty:[1,2,1,""],isLocallyCheckpointed:[1,2,1,""],join:[1,2,1,""],keyBy:[1,2,1,""],keys:[1,2,1,""],leftOuterJoin:[1,2,1,""],localCheckpoint:[1,2,1,""],lookup:[1,2,1,""],map:[1,2,1,""],mapPartitions:[1,2,1,""],mapPartitionsWithIndex:[1,2,1,""],mapPartitionsWithSplit:[1,2,1,""],mapValues:[1,2,1,""],max:[1,2,1,""],mean:[1,2,1,""],meanApprox:[1,2,1,""],min:[1,2,1,""],name:[1,2,1,""],partitionBy:[1,2,1,""],persist:[1,2,1,""],pipe:[1,2,1,""],randomSplit:[1,2,1,""],reduce:[1,2,1,""],reduceByKey:[1,2,1,""],reduceByKeyLocally:[1,2,1,""],repartition:[1,2,1,""],repartitionAndSortWithinPartitions:[1,2,1,""],rightOuterJoin:[1,2,1,""],sample:[1,2,1,""],sampleByKey:[1,2,1,""],sampleStdev:[1,2,1,""],sampleVariance:[1,2,1,""],saveAsHadoopDataset:[1,2,1,""],saveAsHadoopFile:[1,2,1,""],saveAsNewAPIHadoopDataset:[1,2,1,""],saveAsNewAPIHadoopFile:[1,2,1,""],saveAsPickleFile:[1,2,1,""],saveAsSequenceFile:[1,2,1,""],saveAsTextFile:[1,2,1,""],setName:[1,2,1,""],sortBy:[1,2,1,""],sortByKey:[1,2,1,""],stats:[1,2,1,""],stdev:[1,2,1,""],subtract:[1,2,1,""],subtractByKey:[1,2,1,""],sum:[1,2,1,""],sumApprox:[1,2,1,""],take:[1,2,1,""],takeOrdered:[1,2,1,""],takeSample:[1,2,1,""],toDebugString:[1,2,1,""],toLocalIterator:[1,2,1,""],top:[1,2,1,""],treeAggregate:[1,2,1,""],treeReduce:[1,2,1,""],union:[1,2,1,""],unpersist:[1,2,1,""],values:[1,2,1,""],variance:[1,2,1,""],zip:[1,2,1,""],zipWithIndex:[1,2,1,""],zipWithUniqueId:[1,2,1,""]},"pyspark.SparkConf":{contains:[1,2,1,""],get:[1,2,1,""],getAll:[1,2,1,""],set:[1,2,1,""],setAll:[1,2,1,""],setAppName:[1,2,1,""],setExecutorEnv:[1,2,1,""],setIfMissing:[1,2,1,""],setMaster:[1,2,1,""],setSparkHome:[1,2,1,""],toDebugString:[1,2,1,""]},"pyspark.SparkContext":{PACKAGE_EXTENSIONS:[1,3,1,""],accumulator:[1,2,1,""],addFile:[1,2,1,""],addPyFile:[1,2,1,""],applicationId:[1,3,1,""],binaryFiles:[1,2,1,""],binaryRecords:[1,2,1,""],broadcast:[1,2,1,""],cancelAllJobs:[1,2,1,""],cancelJobGroup:[1,2,1,""],defaultMinPartitions:[1,3,1,""],defaultParallelism:[1,3,1,""],dump_profiles:[1,2,1,""],emptyRDD:[1,2,1,""],getConf:[1,2,1,""],getLocalProperty:[1,2,1,""],getOrCreate:[1,4,1,""],hadoopFile:[1,2,1,""],hadoopRDD:[1,2,1,""],newAPIHadoopFile:[1,2,1,""],newAPIHadoopRDD:[1,2,1,""],parallelize:[1,2,1,""],pickleFile:[1,2,1,""],range:[1,2,1,""],runJob:[1,2,1,""],sequenceFile:[1,2,1,""],setCheckpointDir:[1,2,1,""],setJobGroup:[1,2,1,""],setLocalProperty:[1,2,1,""],setLogLevel:[1,2,1,""],setSystemProperty:[1,4,1,""],show_profiles:[1,2,1,""],sparkUser:[1,2,1,""],startTime:[1,3,1,""],statusTracker:[1,2,1,""],stop:[1,2,1,""],textFile:[1,2,1,""],uiWebUrl:[1,3,1,""],union:[1,2,1,""],version:[1,3,1,""],wholeTextFiles:[1,2,1,""]},"pyspark.SparkFiles":{get:[1,4,1,""],getRootDirectory:[1,4,1,""]},"pyspark.StatusTracker":{getActiveJobsIds:[1,2,1,""],getActiveStageIds:[1,2,1,""],getJobIdsForGroup:[1,2,1,""],getJobInfo:[1,2,1,""],getStageInfo:[1,2,1,""]},"pyspark.StorageLevel":{DISK_ONLY:[1,3,1,""],DISK_ONLY_2:[1,3,1,""],MEMORY_AND_DISK:[1,3,1,""],MEMORY_AND_DISK_2:[1,3,1,""],MEMORY_AND_DISK_SER:[1,3,1,""],MEMORY_AND_DISK_SER_2:[1,3,1,""],MEMORY_ONLY:[1,3,1,""],MEMORY_ONLY_2:[1,3,1,""],MEMORY_ONLY_SER:[1,3,1,""],MEMORY_ONLY_SER_2:[1,3,1,""],OFF_HEAP:[1,3,1,""]},"pyspark.TaskContext":{attemptNumber:[1,2,1,""],get:[1,4,1,""],partitionId:[1,2,1,""],stageId:[1,2,1,""],taskAttemptId:[1,2,1,""]},"pyspark.ml":{Estimator:[2,1,1,""],Model:[2,1,1,""],Pipeline:[2,1,1,""],PipelineModel:[2,1,1,""],Transformer:[2,1,1,""],classification:[2,0,0,"-"],clustering:[2,0,0,"-"],evaluation:[2,0,0,"-"],feature:[2,0,0,"-"],fpm:[2,0,0,"-"],linalg:[2,0,0,"-"],param:[2,0,0,"-"],recommendation:[2,0,0,"-"],regression:[2,0,0,"-"],stat:[2,0,0,"-"],tuning:[2,0,0,"-"],util:[2,0,0,"-"]},"pyspark.ml.Estimator":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.Model":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],transform:[2,2,1,""]},"pyspark.ml.Pipeline":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getStages:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setParams:[2,2,1,""],setStages:[2,2,1,""],stages:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.PipelineModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.Transformer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],transform:[2,2,1,""]},"pyspark.ml.classification":{BinaryLogisticRegressionSummary:[2,1,1,""],BinaryLogisticRegressionTrainingSummary:[2,1,1,""],DecisionTreeClassificationModel:[2,1,1,""],DecisionTreeClassifier:[2,1,1,""],GBTClassificationModel:[2,1,1,""],GBTClassifier:[2,1,1,""],LinearSVC:[2,1,1,""],LinearSVCModel:[2,1,1,""],LogisticRegression:[2,1,1,""],LogisticRegressionModel:[2,1,1,""],LogisticRegressionSummary:[2,1,1,""],LogisticRegressionTrainingSummary:[2,1,1,""],MultilayerPerceptronClassificationModel:[2,1,1,""],MultilayerPerceptronClassifier:[2,1,1,""],NaiveBayes:[2,1,1,""],NaiveBayesModel:[2,1,1,""],OneVsRest:[2,1,1,""],OneVsRestModel:[2,1,1,""],RandomForestClassificationModel:[2,1,1,""],RandomForestClassifier:[2,1,1,""]},"pyspark.ml.classification.BinaryLogisticRegressionSummary":{areaUnderROC:[2,3,1,""],fMeasureByThreshold:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],pr:[2,3,1,""],precisionByThreshold:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],recallByThreshold:[2,3,1,""],roc:[2,3,1,""]},"pyspark.ml.classification.BinaryLogisticRegressionTrainingSummary":{areaUnderROC:[2,3,1,""],fMeasureByThreshold:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],objectiveHistory:[2,3,1,""],pr:[2,3,1,""],precisionByThreshold:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],recallByThreshold:[2,3,1,""],roc:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.classification.DecisionTreeClassificationModel":{copy:[2,2,1,""],depth:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.DecisionTreeClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.GBTClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.GBTClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getLossType:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setLossType:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setSubsamplingRate:[2,2,1,""],stepSize:[2,3,1,""],subsamplingRate:[2,3,1,""],supportedLossTypes:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LinearSVC":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getStandardization:[2,2,1,""],getThreshold:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setStandardization:[2,2,1,""],setThreshold:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],standardization:[2,3,1,""],threshold:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LinearSVCModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegression":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],elasticNetParam:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],family:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getElasticNetParam:[2,2,1,""],getFamily:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getStandardization:[2,2,1,""],getThreshold:[2,2,1,""],getThresholds:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setElasticNetParam:[2,2,1,""],setFamily:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setStandardization:[2,2,1,""],setThreshold:[2,2,1,""],setThresholds:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],standardization:[2,3,1,""],threshold:[2,3,1,""],thresholds:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegressionModel":{coefficientMatrix:[2,3,1,""],coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],interceptVector:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegressionSummary":{featuresCol:[2,3,1,""],labelCol:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""]},"pyspark.ml.classification.LogisticRegressionTrainingSummary":{featuresCol:[2,3,1,""],labelCol:[2,3,1,""],objectiveHistory:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.classification.MultilayerPerceptronClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],layers:[2,3,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],weights:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.MultilayerPerceptronClassifier":{blockSize:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getBlockSize:[2,2,1,""],getFeaturesCol:[2,2,1,""],getInitialWeights:[2,2,1,""],getLabelCol:[2,2,1,""],getLayers:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSolver:[2,2,1,""],getStepSize:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],initialWeights:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],layers:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBlockSize:[2,2,1,""],setFeaturesCol:[2,2,1,""],setInitialWeights:[2,2,1,""],setLabelCol:[2,2,1,""],setLayers:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSolver:[2,2,1,""],setStepSize:[2,2,1,""],setTol:[2,2,1,""],solver:[2,3,1,""],stepSize:[2,3,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.NaiveBayes":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getModelType:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSmoothing:[2,2,1,""],getThresholds:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],modelType:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setModelType:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSmoothing:[2,2,1,""],setThresholds:[2,2,1,""],setWeightCol:[2,2,1,""],smoothing:[2,3,1,""],thresholds:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.NaiveBayesModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],pi:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],theta:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.OneVsRest":{classifier:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getClassifier:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setClassifier:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.OneVsRestModel":{classifier:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],getClassifier:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setClassifier:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],transform:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.RandomForestClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.RandomForestClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatureSubsetStrategy:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getNumTrees:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],numTrees:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeatureSubsetStrategy:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setNumTrees:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],subsamplingRate:[2,3,1,""],supportedFeatureSubsetStrategies:[2,3,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering":{BisectingKMeans:[2,1,1,""],BisectingKMeansModel:[2,1,1,""],BisectingKMeansSummary:[2,1,1,""],DistributedLDAModel:[2,1,1,""],GaussianMixture:[2,1,1,""],GaussianMixtureModel:[2,1,1,""],GaussianMixtureSummary:[2,1,1,""],KMeans:[2,1,1,""],KMeansModel:[2,1,1,""],LDA:[2,1,1,""],LDAModel:[2,1,1,""],LocalLDAModel:[2,1,1,""]},"pyspark.ml.clustering.BisectingKMeans":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getMinDivisibleClusterSize:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],minDivisibleClusterSize:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setMinDivisibleClusterSize:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.BisectingKMeansModel":{clusterCenters:[2,2,1,""],computeCost:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.BisectingKMeansSummary":{cluster:[2,3,1,""],clusterSizes:[2,3,1,""],featuresCol:[2,3,1,""],k:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""]},"pyspark.ml.clustering.DistributedLDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getCheckpointFiles:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],logPrior:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toLocal:[2,2,1,""],topicsMatrix:[2,2,1,""],trainingLogLikelihood:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixture":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getSeed:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setSeed:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixtureModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],gaussiansDF:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],weights:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixtureSummary":{cluster:[2,3,1,""],clusterSizes:[2,3,1,""],featuresCol:[2,3,1,""],k:[2,3,1,""],logLikelihood:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],probability:[2,3,1,""],probabilityCol:[2,3,1,""]},"pyspark.ml.clustering.KMeans":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getInitMode:[2,2,1,""],getInitSteps:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],initMode:[2,3,1,""],initSteps:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setInitMode:[2,2,1,""],setInitSteps:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.KMeansModel":{clusterCenters:[2,2,1,""],computeCost:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.LDA":{checkpointInterval:[2,3,1,""],copy:[2,2,1,""],docConcentration:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getDocConcentration:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getKeepLastCheckpoint:[2,2,1,""],getLearningDecay:[2,2,1,""],getLearningOffset:[2,2,1,""],getMaxIter:[2,2,1,""],getOptimizeDocConcentration:[2,2,1,""],getOptimizer:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],getTopicConcentration:[2,2,1,""],getTopicDistributionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],keepLastCheckpoint:[2,3,1,""],learningDecay:[2,3,1,""],learningOffset:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],optimizeDocConcentration:[2,3,1,""],optimizer:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCheckpointInterval:[2,2,1,""],setDocConcentration:[2,2,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setKeepLastCheckpoint:[2,2,1,""],setLearningDecay:[2,2,1,""],setLearningOffset:[2,2,1,""],setMaxIter:[2,2,1,""],setOptimizeDocConcentration:[2,2,1,""],setOptimizer:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],setTopicConcentration:[2,2,1,""],setTopicDistributionCol:[2,2,1,""],subsamplingRate:[2,3,1,""],topicConcentration:[2,3,1,""],topicDistributionCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.LDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],topicsMatrix:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""]},"pyspark.ml.clustering.LocalLDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],topicsMatrix:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation":{BinaryClassificationEvaluator:[2,1,1,""],Evaluator:[2,1,1,""],MulticlassClassificationEvaluator:[2,1,1,""],RegressionEvaluator:[2,1,1,""]},"pyspark.ml.evaluation.BinaryClassificationEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getRawPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setRawPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation.Evaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.evaluation.MulticlassClassificationEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation.RegressionEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature":{Binarizer:[2,1,1,""],BucketedRandomProjectionLSH:[2,1,1,""],BucketedRandomProjectionLSHModel:[2,1,1,""],Bucketizer:[2,1,1,""],ChiSqSelector:[2,1,1,""],ChiSqSelectorModel:[2,1,1,""],CountVectorizer:[2,1,1,""],CountVectorizerModel:[2,1,1,""],DCT:[2,1,1,""],ElementwiseProduct:[2,1,1,""],HashingTF:[2,1,1,""],IDF:[2,1,1,""],IDFModel:[2,1,1,""],Imputer:[2,1,1,""],ImputerModel:[2,1,1,""],IndexToString:[2,1,1,""],MaxAbsScaler:[2,1,1,""],MaxAbsScalerModel:[2,1,1,""],MinHashLSH:[2,1,1,""],MinHashLSHModel:[2,1,1,""],MinMaxScaler:[2,1,1,""],MinMaxScalerModel:[2,1,1,""],NGram:[2,1,1,""],Normalizer:[2,1,1,""],OneHotEncoder:[2,1,1,""],PCA:[2,1,1,""],PCAModel:[2,1,1,""],PolynomialExpansion:[2,1,1,""],QuantileDiscretizer:[2,1,1,""],RFormula:[2,1,1,""],RFormulaModel:[2,1,1,""],RegexTokenizer:[2,1,1,""],SQLTransformer:[2,1,1,""],StandardScaler:[2,1,1,""],StandardScalerModel:[2,1,1,""],StopWordsRemover:[2,1,1,""],StringIndexer:[2,1,1,""],StringIndexerModel:[2,1,1,""],Tokenizer:[2,1,1,""],VectorAssembler:[2,1,1,""],VectorIndexer:[2,1,1,""],VectorIndexerModel:[2,1,1,""],VectorSlicer:[2,1,1,""],Word2Vec:[2,1,1,""],Word2VecModel:[2,1,1,""]},"pyspark.ml.feature.Binarizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getThreshold:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setThreshold:[2,2,1,""],threshold:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.BucketedRandomProjectionLSH":{bucketLength:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getBucketLength:[2,2,1,""],getInputCol:[2,2,1,""],getNumHashTables:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numHashTables:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBucketLength:[2,2,1,""],setInputCol:[2,2,1,""],setNumHashTables:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.BucketedRandomProjectionLSHModel":{approxNearestNeighbors:[2,2,1,""],approxSimilarityJoin:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Bucketizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSplits:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSplits:[2,2,1,""],splits:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ChiSqSelector":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fdr:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fpr:[2,3,1,""],fwe:[2,3,1,""],getFdr:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFpr:[2,2,1,""],getFwe:[2,2,1,""],getLabelCol:[2,2,1,""],getNumTopFeatures:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getPercentile:[2,2,1,""],getSelectorType:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],numTopFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],percentile:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],selectorType:[2,3,1,""],setFdr:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFpr:[2,2,1,""],setFwe:[2,2,1,""],setLabelCol:[2,2,1,""],setNumTopFeatures:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setPercentile:[2,2,1,""],setSelectorType:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ChiSqSelectorModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],selectedFeatures:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.CountVectorizer":{binary:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getBinary:[2,2,1,""],getInputCol:[2,2,1,""],getMinDF:[2,2,1,""],getMinTF:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getVocabSize:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],minDF:[2,3,1,""],minTF:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setBinary:[2,2,1,""],setInputCol:[2,2,1,""],setMinDF:[2,2,1,""],setMinTF:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setVocabSize:[2,2,1,""],vocabSize:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.CountVectorizerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],vocabulary:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.DCT":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getInverse:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],inverse:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setInverse:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ElementwiseProduct":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getScalingVec:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],scalingVec:[2,3,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setScalingVec:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.HashingTF":{binary:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getBinary:[2,2,1,""],getInputCol:[2,2,1,""],getNumFeatures:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setBinary:[2,2,1,""],setInputCol:[2,2,1,""],setNumFeatures:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IDF":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMinDocFreq:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],minDocFreq:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMinDocFreq:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IDFModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],idf:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Imputer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCols:[2,2,1,""],getMissingValue:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCols:[2,2,1,""],getParam:[2,2,1,""],getStrategy:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCols:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],missingValue:[2,3,1,""],outputCols:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCols:[2,2,1,""],setMissingValue:[2,2,1,""],setOutputCols:[2,2,1,""],setParams:[2,2,1,""],setStrategy:[2,2,1,""],strategy:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ImputerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],surrogateDF:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IndexToString":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getLabels:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labels:[2,3,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setLabels:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MaxAbsScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MaxAbsScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],maxAbs:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinHashLSH":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getNumHashTables:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numHashTables:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInputCol:[2,2,1,""],setNumHashTables:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinHashLSHModel":{approxNearestNeighbors:[2,2,1,""],approxSimilarityJoin:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinMaxScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMax:[2,2,1,""],getMin:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],max:[2,3,1,""],min:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMax:[2,2,1,""],setMin:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinMaxScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],originalMax:[2,3,1,""],originalMin:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.NGram":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getN:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],n:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setN:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Normalizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getP:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],p:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setP:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.OneHotEncoder":{copy:[2,2,1,""],dropLast:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getDropLast:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setDropLast:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PCA":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getK:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setK:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PCAModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],explainedVariance:[2,3,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],pc:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PolynomialExpansion":{copy:[2,2,1,""],degree:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getDegree:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setDegree:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.QuantileDiscretizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getNumBuckets:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getRelativeError:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numBuckets:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],relativeError:[2,3,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setNumBuckets:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setRelativeError:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RFormula":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],forceIndexLabel:[2,3,1,""],formula:[2,3,1,""],getFeaturesCol:[2,2,1,""],getForceIndexLabel:[2,2,1,""],getFormula:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeaturesCol:[2,2,1,""],setForceIndexLabel:[2,2,1,""],setFormula:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RFormulaModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RegexTokenizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],gaps:[2,3,1,""],getGaps:[2,2,1,""],getInputCol:[2,2,1,""],getMinTokenLength:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getPattern:[2,2,1,""],getToLowercase:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],minTokenLength:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],pattern:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setGaps:[2,2,1,""],setInputCol:[2,2,1,""],setMinTokenLength:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setPattern:[2,2,1,""],setToLowercase:[2,2,1,""],toLowercase:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.SQLTransformer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getStatement:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setParams:[2,2,1,""],setStatement:[2,2,1,""],statement:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StandardScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getWithMean:[2,2,1,""],getWithStd:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setWithMean:[2,2,1,""],setWithStd:[2,2,1,""],withMean:[2,3,1,""],withStd:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StandardScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],mean:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],std:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StopWordsRemover":{caseSensitive:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getCaseSensitive:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getStopWords:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],loadDefaultStopWords:[2,5,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setCaseSensitive:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setStopWords:[2,2,1,""],stopWords:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StringIndexer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StringIndexerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labels:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Tokenizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorAssembler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCols:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCols:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCols:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorIndexer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMaxCategories:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],maxCategories:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMaxCategories:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorIndexerModel":{categoryMaps:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorSlicer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getIndices:[2,2,1,""],getInputCol:[2,2,1,""],getNames:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],indices:[2,3,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],names:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setIndices:[2,2,1,""],setInputCol:[2,2,1,""],setNames:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Word2Vec":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxSentenceLength:[2,2,1,""],getMinCount:[2,2,1,""],getNumPartitions:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getVectorSize:[2,2,1,""],getWindowSize:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],maxSentenceLength:[2,3,1,""],minCount:[2,3,1,""],numPartitions:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInputCol:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxSentenceLength:[2,2,1,""],setMinCount:[2,2,1,""],setNumPartitions:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setVectorSize:[2,2,1,""],setWindowSize:[2,2,1,""],stepSize:[2,3,1,""],vectorSize:[2,3,1,""],windowSize:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Word2VecModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],findSynonyms:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getVectors:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.fpm":{FPGrowth:[2,1,1,""],FPGrowthModel:[2,1,1,""]},"pyspark.ml.fpm.FPGrowth":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getItemsCol:[2,2,1,""],getMinConfidence:[2,2,1,""],getMinSupport:[2,2,1,""],getNumPartitions:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemsCol:[2,3,1,""],load:[2,4,1,""],minConfidence:[2,3,1,""],minSupport:[2,3,1,""],numPartitions:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setItemsCol:[2,2,1,""],setMinConfidence:[2,2,1,""],setMinSupport:[2,2,1,""],setNumPartitions:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.fpm.FPGrowthModel":{associationRules:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],freqItemsets:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.linalg":{DenseMatrix:[2,1,1,""],DenseVector:[2,1,1,""],Matrices:[2,1,1,""],Matrix:[2,1,1,""],SparseMatrix:[2,1,1,""],SparseVector:[2,1,1,""],Vector:[2,1,1,""],Vectors:[2,1,1,""]},"pyspark.ml.linalg.DenseMatrix":{toArray:[2,2,1,""],toSparse:[2,2,1,""]},"pyspark.ml.linalg.DenseVector":{dot:[2,2,1,""],norm:[2,2,1,""],numNonzeros:[2,2,1,""],squared_distance:[2,2,1,""],toArray:[2,2,1,""],values:[2,3,1,""]},"pyspark.ml.linalg.Matrices":{dense:[2,5,1,""],sparse:[2,5,1,""]},"pyspark.ml.linalg.Matrix":{toArray:[2,2,1,""]},"pyspark.ml.linalg.SparseMatrix":{toArray:[2,2,1,""],toDense:[2,2,1,""]},"pyspark.ml.linalg.SparseVector":{dot:[2,2,1,""],indices:[2,3,1,""],norm:[2,2,1,""],numNonzeros:[2,2,1,""],size:[2,3,1,""],squared_distance:[2,2,1,""],toArray:[2,2,1,""],values:[2,3,1,""]},"pyspark.ml.linalg.Vector":{toArray:[2,2,1,""]},"pyspark.ml.linalg.Vectors":{dense:[2,5,1,""],norm:[2,5,1,""],sparse:[2,5,1,""],squared_distance:[2,5,1,""],zeros:[2,5,1,""]},"pyspark.ml.param":{Param:[2,1,1,""],Params:[2,1,1,""],TypeConverters:[2,1,1,""]},"pyspark.ml.param.Params":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.param.TypeConverters":{identity:[2,5,1,""],toBoolean:[2,5,1,""],toFloat:[2,5,1,""],toInt:[2,5,1,""],toList:[2,5,1,""],toListFloat:[2,5,1,""],toListInt:[2,5,1,""],toListString:[2,5,1,""],toString:[2,5,1,""],toVector:[2,5,1,""]},"pyspark.ml.recommendation":{ALS:[2,1,1,""],ALSModel:[2,1,1,""]},"pyspark.ml.recommendation.ALS":{alpha:[2,3,1,""],checkpointInterval:[2,3,1,""],coldStartStrategy:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],finalStorageLevel:[2,3,1,""],fit:[2,2,1,""],getAlpha:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getColdStartStrategy:[2,2,1,""],getFinalStorageLevel:[2,2,1,""],getImplicitPrefs:[2,2,1,""],getIntermediateStorageLevel:[2,2,1,""],getItemCol:[2,2,1,""],getMaxIter:[2,2,1,""],getNonnegative:[2,2,1,""],getNumItemBlocks:[2,2,1,""],getNumUserBlocks:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRank:[2,2,1,""],getRatingCol:[2,2,1,""],getRegParam:[2,2,1,""],getSeed:[2,2,1,""],getUserCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],implicitPrefs:[2,3,1,""],intermediateStorageLevel:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],nonnegative:[2,3,1,""],numItemBlocks:[2,3,1,""],numUserBlocks:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],rank:[2,3,1,""],ratingCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],seed:[2,3,1,""],setAlpha:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setColdStartStrategy:[2,2,1,""],setFinalStorageLevel:[2,2,1,""],setImplicitPrefs:[2,2,1,""],setIntermediateStorageLevel:[2,2,1,""],setItemCol:[2,2,1,""],setMaxIter:[2,2,1,""],setNonnegative:[2,2,1,""],setNumBlocks:[2,2,1,""],setNumItemBlocks:[2,2,1,""],setNumUserBlocks:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRank:[2,2,1,""],setRatingCol:[2,2,1,""],setRegParam:[2,2,1,""],setSeed:[2,2,1,""],setUserCol:[2,2,1,""],userCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.recommendation.ALSModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemFactors:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],rank:[2,3,1,""],read:[2,4,1,""],recommendForAllItems:[2,2,1,""],recommendForAllUsers:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],userFactors:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression":{AFTSurvivalRegression:[2,1,1,""],AFTSurvivalRegressionModel:[2,1,1,""],DecisionTreeRegressionModel:[2,1,1,""],DecisionTreeRegressor:[2,1,1,""],GBTRegressionModel:[2,1,1,""],GBTRegressor:[2,1,1,""],GeneralizedLinearRegression:[2,1,1,""],GeneralizedLinearRegressionModel:[2,1,1,""],GeneralizedLinearRegressionSummary:[2,1,1,""],GeneralizedLinearRegressionTrainingSummary:[2,1,1,""],IsotonicRegression:[2,1,1,""],IsotonicRegressionModel:[2,1,1,""],LinearRegression:[2,1,1,""],LinearRegressionModel:[2,1,1,""],LinearRegressionSummary:[2,1,1,""],LinearRegressionTrainingSummary:[2,1,1,""],RandomForestRegressionModel:[2,1,1,""],RandomForestRegressor:[2,1,1,""]},"pyspark.ml.regression.AFTSurvivalRegression":{aggregationDepth:[2,3,1,""],censorCol:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getCensorCol:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getQuantileProbabilities:[2,2,1,""],getQuantilesCol:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],quantileProbabilities:[2,3,1,""],quantilesCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setCensorCol:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setQuantileProbabilities:[2,2,1,""],setQuantilesCol:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.AFTSurvivalRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],predict:[2,2,1,""],predictQuantiles:[2,2,1,""],read:[2,4,1,""],save:[2,2,1,""],scale:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.DecisionTreeRegressionModel":{copy:[2,2,1,""],depth:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.DecisionTreeRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getVarianceCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setVarianceCol:[2,2,1,""],supportedImpurities:[2,3,1,""],varianceCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GBTRegressionModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GBTRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getLossType:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setLossType:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setSubsamplingRate:[2,2,1,""],stepSize:[2,3,1,""],subsamplingRate:[2,3,1,""],supportedImpurities:[2,3,1,""],supportedLossTypes:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegression":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],family:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getFamily:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getLink:[2,2,1,""],getLinkPower:[2,2,1,""],getLinkPredictionCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getSolver:[2,2,1,""],getTol:[2,2,1,""],getVariancePower:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],link:[2,3,1,""],linkPower:[2,3,1,""],linkPredictionCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setFamily:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setLink:[2,2,1,""],setLinkPower:[2,2,1,""],setLinkPredictionCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setSolver:[2,2,1,""],setTol:[2,2,1,""],setVariancePower:[2,2,1,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],tol:[2,3,1,""],variancePower:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionSummary":{aic:[2,3,1,""],degreesOfFreedom:[2,3,1,""],deviance:[2,3,1,""],dispersion:[2,3,1,""],nullDeviance:[2,3,1,""],numInstances:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],rank:[2,3,1,""],residualDegreeOfFreedom:[2,3,1,""],residualDegreeOfFreedomNull:[2,3,1,""],residuals:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionTrainingSummary":{aic:[2,3,1,""],coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],deviance:[2,3,1,""],dispersion:[2,3,1,""],nullDeviance:[2,3,1,""],numInstances:[2,3,1,""],numIterations:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],rank:[2,3,1,""],residualDegreeOfFreedom:[2,3,1,""],residualDegreeOfFreedomNull:[2,3,1,""],residuals:[2,2,1,""],solver:[2,3,1,""],tValues:[2,3,1,""]},"pyspark.ml.regression.IsotonicRegression":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureIndex:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeatureIndex:[2,2,1,""],getFeaturesCol:[2,2,1,""],getIsotonic:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],isotonic:[2,3,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeatureIndex:[2,2,1,""],setFeaturesCol:[2,2,1,""],setIsotonic:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.IsotonicRegressionModel":{boundaries:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],predictions:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegression":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],elasticNetParam:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getElasticNetParam:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getSolver:[2,2,1,""],getStandardization:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setElasticNetParam:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setSolver:[2,2,1,""],setStandardization:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],standardization:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionSummary":{coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],devianceResiduals:[2,3,1,""],explainedVariance:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],meanAbsoluteError:[2,3,1,""],meanSquaredError:[2,3,1,""],numInstances:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],r2:[2,3,1,""],residuals:[2,3,1,""],rootMeanSquaredError:[2,3,1,""],tValues:[2,3,1,""]},"pyspark.ml.regression.LinearRegressionTrainingSummary":{coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],devianceResiduals:[2,3,1,""],explainedVariance:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],meanAbsoluteError:[2,3,1,""],meanSquaredError:[2,3,1,""],numInstances:[2,3,1,""],objectiveHistory:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],r2:[2,3,1,""],residuals:[2,3,1,""],rootMeanSquaredError:[2,3,1,""],tValues:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.regression.RandomForestRegressionModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.RandomForestRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatureSubsetStrategy:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getNumTrees:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],numTrees:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeatureSubsetStrategy:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setNumTrees:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],subsamplingRate:[2,3,1,""],supportedFeatureSubsetStrategies:[2,3,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.stat":{ChiSquareTest:[2,1,1,""],Correlation:[2,1,1,""]},"pyspark.ml.stat.ChiSquareTest":{test:[2,5,1,""]},"pyspark.ml.stat.Correlation":{corr:[2,5,1,""]},"pyspark.ml.tuning":{CrossValidator:[2,1,1,""],CrossValidatorModel:[2,1,1,""],ParamGridBuilder:[2,1,1,""],TrainValidationSplit:[2,1,1,""],TrainValidationSplitModel:[2,1,1,""]},"pyspark.ml.tuning.CrossValidator":{copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getNumFolds:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],numFolds:[2,3,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setNumFolds:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""]},"pyspark.ml.tuning.CrossValidatorModel":{avgMetrics:[2,3,1,""],bestModel:[2,3,1,""],copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setSeed:[2,2,1,""],transform:[2,2,1,""]},"pyspark.ml.tuning.ParamGridBuilder":{addGrid:[2,2,1,""],baseOn:[2,2,1,""],build:[2,2,1,""]},"pyspark.ml.tuning.TrainValidationSplit":{copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getTrainRatio:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setTrainRatio:[2,2,1,""],trainRatio:[2,3,1,""]},"pyspark.ml.tuning.TrainValidationSplitModel":{bestModel:[2,3,1,""],copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setSeed:[2,2,1,""],transform:[2,2,1,""],validationMetrics:[2,3,1,""]},"pyspark.ml.util":{Identifiable:[2,1,1,""],JavaMLReadable:[2,1,1,""],JavaMLReader:[2,1,1,""],JavaMLWritable:[2,1,1,""],JavaMLWriter:[2,1,1,""],JavaPredictionModel:[2,1,1,""],MLReadable:[2,1,1,""],MLReader:[2,1,1,""],MLWritable:[2,1,1,""],MLWriter:[2,1,1,""]},"pyspark.ml.util.Identifiable":{uid:[2,3,1,""]},"pyspark.ml.util.JavaMLReadable":{load:[2,4,1,""],read:[2,4,1,""]},"pyspark.ml.util.JavaMLReader":{context:[2,2,1,""],load:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.JavaMLWritable":{save:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.util.JavaMLWriter":{context:[2,2,1,""],overwrite:[2,2,1,""],save:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.JavaPredictionModel":{numFeatures:[2,3,1,""]},"pyspark.ml.util.MLReadable":{load:[2,4,1,""],read:[2,4,1,""]},"pyspark.ml.util.MLReader":{context:[2,2,1,""],load:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.MLWritable":{save:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.util.MLWriter":{context:[2,2,1,""],overwrite:[2,2,1,""],save:[2,2,1,""],session:[2,2,1,""]},"pyspark.mllib":{classification:[3,0,0,"-"],clustering:[3,0,0,"-"],evaluation:[3,0,0,"-"],feature:[3,0,0,"-"],fpm:[3,0,0,"-"],linalg:[3,0,0,"-"],random:[3,0,0,"-"],recommendation:[3,0,0,"-"],regression:[3,0,0,"-"],stat:[3,0,0,"-"],tree:[3,0,0,"-"],util:[3,0,0,"-"]},"pyspark.mllib.classification":{LogisticRegressionModel:[3,1,1,""],LogisticRegressionWithLBFGS:[3,1,1,""],LogisticRegressionWithSGD:[3,1,1,""],NaiveBayes:[3,1,1,""],NaiveBayesModel:[3,1,1,""],SVMModel:[3,1,1,""],SVMWithSGD:[3,1,1,""],StreamingLogisticRegressionWithSGD:[3,1,1,""]},"pyspark.mllib.classification.LogisticRegressionModel":{clearThreshold:[3,2,1,""],intercept:[3,3,1,""],load:[3,4,1,""],numClasses:[3,3,1,""],numFeatures:[3,3,1,""],predict:[3,2,1,""],save:[3,2,1,""],setThreshold:[3,2,1,""],threshold:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.classification.LogisticRegressionWithLBFGS":{train:[3,4,1,""]},"pyspark.mllib.classification.LogisticRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.classification.NaiveBayes":{train:[3,4,1,""]},"pyspark.mllib.classification.NaiveBayesModel":{load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.classification.SVMModel":{clearThreshold:[3,2,1,""],intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],setThreshold:[3,2,1,""],threshold:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.classification.SVMWithSGD":{train:[3,4,1,""]},"pyspark.mllib.classification.StreamingLogisticRegressionWithSGD":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setInitialWeights:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.clustering":{BisectingKMeans:[3,1,1,""],BisectingKMeansModel:[3,1,1,""],GaussianMixture:[3,1,1,""],GaussianMixtureModel:[3,1,1,""],KMeans:[3,1,1,""],KMeansModel:[3,1,1,""],LDA:[3,1,1,""],LDAModel:[3,1,1,""],PowerIterationClustering:[3,1,1,""],PowerIterationClusteringModel:[3,1,1,""],StreamingKMeans:[3,1,1,""],StreamingKMeansModel:[3,1,1,""]},"pyspark.mllib.clustering.BisectingKMeans":{train:[3,4,1,""]},"pyspark.mllib.clustering.BisectingKMeansModel":{clusterCenters:[3,3,1,""],computeCost:[3,2,1,""],k:[3,3,1,""],predict:[3,2,1,""]},"pyspark.mllib.clustering.GaussianMixture":{train:[3,4,1,""]},"pyspark.mllib.clustering.GaussianMixtureModel":{gaussians:[3,3,1,""],k:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],predictSoft:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.clustering.KMeans":{train:[3,4,1,""]},"pyspark.mllib.clustering.KMeansModel":{clusterCenters:[3,3,1,""],computeCost:[3,2,1,""],k:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.clustering.LDA":{train:[3,4,1,""]},"pyspark.mllib.clustering.LDAModel":{describeTopics:[3,2,1,""],load:[3,4,1,""],topicsMatrix:[3,2,1,""],vocabSize:[3,2,1,""]},"pyspark.mllib.clustering.PowerIterationClustering":{Assignment:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.clustering.PowerIterationClusteringModel":{assignments:[3,2,1,""],k:[3,3,1,""],load:[3,4,1,""]},"pyspark.mllib.clustering.StreamingKMeans":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setDecayFactor:[3,2,1,""],setHalfLife:[3,2,1,""],setInitialCenters:[3,2,1,""],setK:[3,2,1,""],setRandomCenters:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.clustering.StreamingKMeansModel":{clusterWeights:[3,3,1,""],update:[3,2,1,""]},"pyspark.mllib.evaluation":{BinaryClassificationMetrics:[3,1,1,""],MulticlassMetrics:[3,1,1,""],RankingMetrics:[3,1,1,""],RegressionMetrics:[3,1,1,""]},"pyspark.mllib.evaluation.BinaryClassificationMetrics":{areaUnderPR:[3,3,1,""],areaUnderROC:[3,3,1,""],unpersist:[3,2,1,""]},"pyspark.mllib.evaluation.MulticlassMetrics":{accuracy:[3,3,1,""],confusionMatrix:[3,2,1,""],fMeasure:[3,2,1,""],falsePositiveRate:[3,2,1,""],precision:[3,2,1,""],recall:[3,2,1,""],truePositiveRate:[3,2,1,""],weightedFMeasure:[3,2,1,""],weightedFalsePositiveRate:[3,3,1,""],weightedPrecision:[3,3,1,""],weightedRecall:[3,3,1,""],weightedTruePositiveRate:[3,3,1,""]},"pyspark.mllib.evaluation.RankingMetrics":{meanAveragePrecision:[3,3,1,""],ndcgAt:[3,2,1,""],precisionAt:[3,2,1,""]},"pyspark.mllib.evaluation.RegressionMetrics":{explainedVariance:[3,3,1,""],meanAbsoluteError:[3,3,1,""],meanSquaredError:[3,3,1,""],r2:[3,3,1,""],rootMeanSquaredError:[3,3,1,""]},"pyspark.mllib.feature":{ChiSqSelector:[3,1,1,""],ChiSqSelectorModel:[3,1,1,""],ElementwiseProduct:[3,1,1,""],HashingTF:[3,1,1,""],IDF:[3,1,1,""],IDFModel:[3,1,1,""],Normalizer:[3,1,1,""],StandardScaler:[3,1,1,""],StandardScalerModel:[3,1,1,""],Word2Vec:[3,1,1,""],Word2VecModel:[3,1,1,""]},"pyspark.mllib.feature.ChiSqSelector":{fit:[3,2,1,""],setFdr:[3,2,1,""],setFpr:[3,2,1,""],setFwe:[3,2,1,""],setNumTopFeatures:[3,2,1,""],setPercentile:[3,2,1,""],setSelectorType:[3,2,1,""]},"pyspark.mllib.feature.ChiSqSelectorModel":{transform:[3,2,1,""]},"pyspark.mllib.feature.ElementwiseProduct":{transform:[3,2,1,""]},"pyspark.mllib.feature.HashingTF":{indexOf:[3,2,1,""],setBinary:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.IDF":{fit:[3,2,1,""]},"pyspark.mllib.feature.IDFModel":{idf:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.Normalizer":{transform:[3,2,1,""]},"pyspark.mllib.feature.StandardScaler":{fit:[3,2,1,""]},"pyspark.mllib.feature.StandardScalerModel":{mean:[3,3,1,""],setWithMean:[3,2,1,""],setWithStd:[3,2,1,""],std:[3,3,1,""],transform:[3,2,1,""],withMean:[3,3,1,""],withStd:[3,3,1,""]},"pyspark.mllib.feature.Word2Vec":{fit:[3,2,1,""],setLearningRate:[3,2,1,""],setMinCount:[3,2,1,""],setNumIterations:[3,2,1,""],setNumPartitions:[3,2,1,""],setSeed:[3,2,1,""],setVectorSize:[3,2,1,""],setWindowSize:[3,2,1,""]},"pyspark.mllib.feature.Word2VecModel":{findSynonyms:[3,2,1,""],getVectors:[3,2,1,""],load:[3,4,1,""],transform:[3,2,1,""]},"pyspark.mllib.fpm":{FPGrowth:[3,1,1,""],FPGrowthModel:[3,1,1,""],PrefixSpan:[3,1,1,""],PrefixSpanModel:[3,1,1,""]},"pyspark.mllib.fpm.FPGrowth":{FreqItemset:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.fpm.FPGrowthModel":{freqItemsets:[3,2,1,""],load:[3,4,1,""]},"pyspark.mllib.fpm.PrefixSpan":{FreqSequence:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.fpm.PrefixSpanModel":{freqSequences:[3,2,1,""]},"pyspark.mllib.linalg":{DenseMatrix:[3,1,1,""],DenseVector:[3,1,1,""],Matrices:[3,1,1,""],Matrix:[3,1,1,""],QRDecomposition:[3,1,1,""],SparseMatrix:[3,1,1,""],SparseVector:[3,1,1,""],Vector:[3,1,1,""],Vectors:[3,1,1,""],distributed:[3,0,0,"-"]},"pyspark.mllib.linalg.DenseMatrix":{asML:[3,2,1,""],toArray:[3,2,1,""],toSparse:[3,2,1,""]},"pyspark.mllib.linalg.DenseVector":{asML:[3,2,1,""],dot:[3,2,1,""],norm:[3,2,1,""],numNonzeros:[3,2,1,""],parse:[3,5,1,""],squared_distance:[3,2,1,""],toArray:[3,2,1,""],values:[3,3,1,""]},"pyspark.mllib.linalg.Matrices":{dense:[3,5,1,""],fromML:[3,5,1,""],sparse:[3,5,1,""]},"pyspark.mllib.linalg.Matrix":{asML:[3,2,1,""],toArray:[3,2,1,""]},"pyspark.mllib.linalg.QRDecomposition":{Q:[3,3,1,""],R:[3,3,1,""]},"pyspark.mllib.linalg.SparseMatrix":{asML:[3,2,1,""],toArray:[3,2,1,""],toDense:[3,2,1,""]},"pyspark.mllib.linalg.SparseVector":{asML:[3,2,1,""],dot:[3,2,1,""],indices:[3,3,1,""],norm:[3,2,1,""],numNonzeros:[3,2,1,""],parse:[3,5,1,""],size:[3,3,1,""],squared_distance:[3,2,1,""],toArray:[3,2,1,""],values:[3,3,1,""]},"pyspark.mllib.linalg.Vector":{asML:[3,2,1,""],toArray:[3,2,1,""]},"pyspark.mllib.linalg.Vectors":{dense:[3,5,1,""],fromML:[3,5,1,""],norm:[3,5,1,""],parse:[3,5,1,""],sparse:[3,5,1,""],squared_distance:[3,5,1,""],stringify:[3,5,1,""],zeros:[3,5,1,""]},"pyspark.mllib.linalg.distributed":{BlockMatrix:[3,1,1,""],CoordinateMatrix:[3,1,1,""],DistributedMatrix:[3,1,1,""],IndexedRow:[3,1,1,""],IndexedRowMatrix:[3,1,1,""],MatrixEntry:[3,1,1,""],RowMatrix:[3,1,1,""],SingularValueDecomposition:[3,1,1,""]},"pyspark.mllib.linalg.distributed.BlockMatrix":{add:[3,2,1,""],blocks:[3,3,1,""],cache:[3,2,1,""],colsPerBlock:[3,3,1,""],multiply:[3,2,1,""],numColBlocks:[3,3,1,""],numCols:[3,2,1,""],numRowBlocks:[3,3,1,""],numRows:[3,2,1,""],persist:[3,2,1,""],rowsPerBlock:[3,3,1,""],subtract:[3,2,1,""],toCoordinateMatrix:[3,2,1,""],toIndexedRowMatrix:[3,2,1,""],toLocalMatrix:[3,2,1,""],transpose:[3,2,1,""],validate:[3,2,1,""]},"pyspark.mllib.linalg.distributed.CoordinateMatrix":{entries:[3,3,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],toBlockMatrix:[3,2,1,""],toIndexedRowMatrix:[3,2,1,""],toRowMatrix:[3,2,1,""],transpose:[3,2,1,""]},"pyspark.mllib.linalg.distributed.DistributedMatrix":{numCols:[3,2,1,""],numRows:[3,2,1,""]},"pyspark.mllib.linalg.distributed.IndexedRowMatrix":{columnSimilarities:[3,2,1,""],computeGramianMatrix:[3,2,1,""],computeSVD:[3,2,1,""],multiply:[3,2,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],rows:[3,3,1,""],toBlockMatrix:[3,2,1,""],toCoordinateMatrix:[3,2,1,""],toRowMatrix:[3,2,1,""]},"pyspark.mllib.linalg.distributed.RowMatrix":{columnSimilarities:[3,2,1,""],computeColumnSummaryStatistics:[3,2,1,""],computeCovariance:[3,2,1,""],computeGramianMatrix:[3,2,1,""],computePrincipalComponents:[3,2,1,""],computeSVD:[3,2,1,""],multiply:[3,2,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],rows:[3,3,1,""],tallSkinnyQR:[3,2,1,""]},"pyspark.mllib.linalg.distributed.SingularValueDecomposition":{U:[3,3,1,""],V:[3,3,1,""],s:[3,3,1,""]},"pyspark.mllib.random":{RandomRDDs:[3,1,1,""]},"pyspark.mllib.random.RandomRDDs":{exponentialRDD:[3,5,1,""],exponentialVectorRDD:[3,5,1,""],gammaRDD:[3,5,1,""],gammaVectorRDD:[3,5,1,""],logNormalRDD:[3,5,1,""],logNormalVectorRDD:[3,5,1,""],normalRDD:[3,5,1,""],normalVectorRDD:[3,5,1,""],poissonRDD:[3,5,1,""],poissonVectorRDD:[3,5,1,""],uniformRDD:[3,5,1,""],uniformVectorRDD:[3,5,1,""]},"pyspark.mllib.recommendation":{ALS:[3,1,1,""],MatrixFactorizationModel:[3,1,1,""],Rating:[3,1,1,""]},"pyspark.mllib.recommendation.ALS":{train:[3,4,1,""],trainImplicit:[3,4,1,""]},"pyspark.mllib.recommendation.MatrixFactorizationModel":{load:[3,4,1,""],predict:[3,2,1,""],predictAll:[3,2,1,""],productFeatures:[3,2,1,""],rank:[3,3,1,""],recommendProducts:[3,2,1,""],recommendProductsForUsers:[3,2,1,""],recommendUsers:[3,2,1,""],recommendUsersForProducts:[3,2,1,""],userFeatures:[3,2,1,""]},"pyspark.mllib.regression":{IsotonicRegression:[3,1,1,""],IsotonicRegressionModel:[3,1,1,""],LabeledPoint:[3,1,1,""],LassoModel:[3,1,1,""],LassoWithSGD:[3,1,1,""],LinearModel:[3,1,1,""],LinearRegressionModel:[3,1,1,""],LinearRegressionWithSGD:[3,1,1,""],RidgeRegressionModel:[3,1,1,""],RidgeRegressionWithSGD:[3,1,1,""],StreamingLinearAlgorithm:[3,1,1,""],StreamingLinearRegressionWithSGD:[3,1,1,""]},"pyspark.mllib.regression.IsotonicRegression":{train:[3,4,1,""]},"pyspark.mllib.regression.IsotonicRegressionModel":{load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.regression.LassoModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LassoWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.LinearModel":{intercept:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LinearRegressionModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LinearRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.RidgeRegressionModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.RidgeRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.StreamingLinearAlgorithm":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""]},"pyspark.mllib.regression.StreamingLinearRegressionWithSGD":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setInitialWeights:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.stat":{ChiSqTestResult:[3,1,1,""],KernelDensity:[3,1,1,""],MultivariateGaussian:[3,1,1,""],MultivariateStatisticalSummary:[3,1,1,""],Statistics:[3,1,1,""]},"pyspark.mllib.stat.ChiSqTestResult":{method:[3,3,1,""]},"pyspark.mllib.stat.KernelDensity":{estimate:[3,2,1,""],setBandwidth:[3,2,1,""],setSample:[3,2,1,""]},"pyspark.mllib.stat.MultivariateStatisticalSummary":{count:[3,2,1,""],max:[3,2,1,""],mean:[3,2,1,""],min:[3,2,1,""],normL1:[3,2,1,""],normL2:[3,2,1,""],numNonzeros:[3,2,1,""],variance:[3,2,1,""]},"pyspark.mllib.stat.Statistics":{chiSqTest:[3,5,1,""],colStats:[3,5,1,""],corr:[3,5,1,""],kolmogorovSmirnovTest:[3,5,1,""]},"pyspark.mllib.tree":{DecisionTree:[3,1,1,""],DecisionTreeModel:[3,1,1,""],GradientBoostedTrees:[3,1,1,""],GradientBoostedTreesModel:[3,1,1,""],RandomForest:[3,1,1,""],RandomForestModel:[3,1,1,""]},"pyspark.mllib.tree.DecisionTree":{trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.DecisionTreeModel":{call:[3,2,1,""],depth:[3,2,1,""],load:[3,4,1,""],numNodes:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""]},"pyspark.mllib.tree.GradientBoostedTrees":{trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.GradientBoostedTreesModel":{call:[3,2,1,""],load:[3,4,1,""],numTrees:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""],totalNumNodes:[3,2,1,""]},"pyspark.mllib.tree.RandomForest":{supportedFeatureSubsetStrategies:[3,3,1,""],trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.RandomForestModel":{call:[3,2,1,""],load:[3,4,1,""],numTrees:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""],totalNumNodes:[3,2,1,""]},"pyspark.mllib.util":{JavaLoader:[3,1,1,""],JavaSaveable:[3,1,1,""],LinearDataGenerator:[3,1,1,""],Loader:[3,1,1,""],MLUtils:[3,1,1,""],Saveable:[3,1,1,""]},"pyspark.mllib.util.JavaLoader":{load:[3,4,1,""]},"pyspark.mllib.util.JavaSaveable":{save:[3,2,1,""]},"pyspark.mllib.util.LinearDataGenerator":{generateLinearInput:[3,5,1,""],generateLinearRDD:[3,5,1,""]},"pyspark.mllib.util.Loader":{load:[3,4,1,""]},"pyspark.mllib.util.MLUtils":{appendBias:[3,5,1,""],convertMatrixColumnsFromML:[3,5,1,""],convertMatrixColumnsToML:[3,5,1,""],convertVectorColumnsFromML:[3,5,1,""],convertVectorColumnsToML:[3,5,1,""],loadLabeledPoints:[3,5,1,""],loadLibSVMFile:[3,5,1,""],loadVectors:[3,5,1,""],saveAsLibSVMFile:[3,5,1,""]},"pyspark.mllib.util.Saveable":{save:[3,2,1,""]},"pyspark.sql":{Column:[4,1,1,""],DataFrame:[4,1,1,""],DataFrameNaFunctions:[4,1,1,""],DataFrameReader:[4,1,1,""],DataFrameStatFunctions:[4,1,1,""],DataFrameWriter:[4,1,1,""],GroupedData:[4,1,1,""],HiveContext:[4,1,1,""],Row:[4,1,1,""],SQLContext:[4,1,1,""],SparkSession:[4,1,1,""],UDFRegistration:[4,1,1,""],Window:[4,1,1,""],WindowSpec:[4,1,1,""],functions:[4,0,0,"-"],streaming:[4,0,0,"-"],types:[4,0,0,"-"]},"pyspark.sql.Column":{alias:[4,2,1,""],asc:[4,2,1,""],astype:[4,2,1,""],between:[4,2,1,""],bitwiseAND:[4,2,1,""],bitwiseOR:[4,2,1,""],bitwiseXOR:[4,2,1,""],cast:[4,2,1,""],contains:[4,2,1,""],desc:[4,2,1,""],endswith:[4,2,1,""],getField:[4,2,1,""],getItem:[4,2,1,""],isNotNull:[4,2,1,""],isNull:[4,2,1,""],isin:[4,2,1,""],like:[4,2,1,""],name:[4,2,1,""],otherwise:[4,2,1,""],over:[4,2,1,""],rlike:[4,2,1,""],startswith:[4,2,1,""],substr:[4,2,1,""],when:[4,2,1,""]},"pyspark.sql.DataFrame":{agg:[4,2,1,""],alias:[4,2,1,""],approxQuantile:[4,2,1,""],cache:[4,2,1,""],checkpoint:[4,2,1,""],coalesce:[4,2,1,""],collect:[4,2,1,""],columns:[4,3,1,""],corr:[4,2,1,""],count:[4,2,1,""],cov:[4,2,1,""],createGlobalTempView:[4,2,1,""],createOrReplaceGlobalTempView:[4,2,1,""],createOrReplaceTempView:[4,2,1,""],createTempView:[4,2,1,""],crossJoin:[4,2,1,""],crosstab:[4,2,1,""],cube:[4,2,1,""],describe:[4,2,1,""],distinct:[4,2,1,""],drop:[4,2,1,""],dropDuplicates:[4,2,1,""],drop_duplicates:[4,2,1,""],dropna:[4,2,1,""],dtypes:[4,3,1,""],explain:[4,2,1,""],fillna:[4,2,1,""],filter:[4,2,1,""],first:[4,2,1,""],foreach:[4,2,1,""],foreachPartition:[4,2,1,""],freqItems:[4,2,1,""],groupBy:[4,2,1,""],groupby:[4,2,1,""],head:[4,2,1,""],hint:[4,2,1,""],intersect:[4,2,1,""],isLocal:[4,2,1,""],isStreaming:[4,3,1,""],join:[4,2,1,""],limit:[4,2,1,""],na:[4,3,1,""],orderBy:[4,2,1,""],persist:[4,2,1,""],printSchema:[4,2,1,""],randomSplit:[4,2,1,""],rdd:[4,3,1,""],registerTempTable:[4,2,1,""],repartition:[4,2,1,""],replace:[4,2,1,""],rollup:[4,2,1,""],sample:[4,2,1,""],sampleBy:[4,2,1,""],schema:[4,3,1,""],select:[4,2,1,""],selectExpr:[4,2,1,""],show:[4,2,1,""],sort:[4,2,1,""],sortWithinPartitions:[4,2,1,""],stat:[4,3,1,""],storageLevel:[4,3,1,""],subtract:[4,2,1,""],take:[4,2,1,""],toDF:[4,2,1,""],toJSON:[4,2,1,""],toLocalIterator:[4,2,1,""],toPandas:[4,2,1,""],union:[4,2,1,""],unionAll:[4,2,1,""],unpersist:[4,2,1,""],where:[4,2,1,""],withColumn:[4,2,1,""],withColumnRenamed:[4,2,1,""],withWatermark:[4,2,1,""],write:[4,3,1,""],writeStream:[4,3,1,""]},"pyspark.sql.DataFrameNaFunctions":{drop:[4,2,1,""],fill:[4,2,1,""],replace:[4,2,1,""]},"pyspark.sql.DataFrameReader":{csv:[4,2,1,""],format:[4,2,1,""],jdbc:[4,2,1,""],json:[4,2,1,""],load:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],orc:[4,2,1,""],parquet:[4,2,1,""],schema:[4,2,1,""],table:[4,2,1,""],text:[4,2,1,""]},"pyspark.sql.DataFrameStatFunctions":{approxQuantile:[4,2,1,""],corr:[4,2,1,""],cov:[4,2,1,""],crosstab:[4,2,1,""],freqItems:[4,2,1,""],sampleBy:[4,2,1,""]},"pyspark.sql.DataFrameWriter":{csv:[4,2,1,""],format:[4,2,1,""],insertInto:[4,2,1,""],jdbc:[4,2,1,""],json:[4,2,1,""],mode:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],orc:[4,2,1,""],parquet:[4,2,1,""],partitionBy:[4,2,1,""],save:[4,2,1,""],saveAsTable:[4,2,1,""],text:[4,2,1,""]},"pyspark.sql.GroupedData":{agg:[4,2,1,""],avg:[4,2,1,""],count:[4,2,1,""],max:[4,2,1,""],mean:[4,2,1,""],min:[4,2,1,""],pivot:[4,2,1,""],sum:[4,2,1,""]},"pyspark.sql.HiveContext":{refreshTable:[4,2,1,""]},"pyspark.sql.Row":{asDict:[4,2,1,""]},"pyspark.sql.SQLContext":{cacheTable:[4,2,1,""],clearCache:[4,2,1,""],createDataFrame:[4,2,1,""],createExternalTable:[4,2,1,""],dropTempTable:[4,2,1,""],getConf:[4,2,1,""],getOrCreate:[4,4,1,""],newSession:[4,2,1,""],range:[4,2,1,""],read:[4,3,1,""],readStream:[4,3,1,""],registerDataFrameAsTable:[4,2,1,""],registerFunction:[4,2,1,""],registerJavaFunction:[4,2,1,""],setConf:[4,2,1,""],sql:[4,2,1,""],streams:[4,3,1,""],table:[4,2,1,""],tableNames:[4,2,1,""],tables:[4,2,1,""],udf:[4,3,1,""],uncacheTable:[4,2,1,""]},"pyspark.sql.SparkSession":{Builder:[4,1,1,""],builder:[4,3,1,""],catalog:[4,3,1,""],conf:[4,3,1,""],createDataFrame:[4,2,1,""],newSession:[4,2,1,""],range:[4,2,1,""],read:[4,3,1,""],readStream:[4,3,1,""],sparkContext:[4,3,1,""],sql:[4,2,1,""],stop:[4,2,1,""],streams:[4,3,1,""],table:[4,2,1,""],udf:[4,3,1,""],version:[4,3,1,""]},"pyspark.sql.SparkSession.Builder":{appName:[4,2,1,""],config:[4,2,1,""],enableHiveSupport:[4,2,1,""],getOrCreate:[4,2,1,""],master:[4,2,1,""]},"pyspark.sql.UDFRegistration":{register:[4,2,1,""]},"pyspark.sql.Window":{currentRow:[4,3,1,""],orderBy:[4,5,1,""],partitionBy:[4,5,1,""],rangeBetween:[4,5,1,""],rowsBetween:[4,5,1,""],unboundedFollowing:[4,3,1,""],unboundedPreceding:[4,3,1,""]},"pyspark.sql.WindowSpec":{orderBy:[4,2,1,""],partitionBy:[4,2,1,""],rangeBetween:[4,2,1,""],rowsBetween:[4,2,1,""]},"pyspark.sql.functions":{abs:[4,6,1,""],acos:[4,6,1,""],add_months:[4,6,1,""],approxCountDistinct:[4,6,1,""],approx_count_distinct:[4,6,1,""],array:[4,6,1,""],array_contains:[4,6,1,""],asc:[4,6,1,""],ascii:[4,6,1,""],asin:[4,6,1,""],atan2:[4,6,1,""],atan:[4,6,1,""],avg:[4,6,1,""],base64:[4,6,1,""],bin:[4,6,1,""],bitwiseNOT:[4,6,1,""],broadcast:[4,6,1,""],bround:[4,6,1,""],cbrt:[4,6,1,""],ceil:[4,6,1,""],coalesce:[4,6,1,""],col:[4,6,1,""],collect_list:[4,6,1,""],collect_set:[4,6,1,""],column:[4,6,1,""],concat:[4,6,1,""],concat_ws:[4,6,1,""],conv:[4,6,1,""],corr:[4,6,1,""],cos:[4,6,1,""],cosh:[4,6,1,""],count:[4,6,1,""],countDistinct:[4,6,1,""],covar_pop:[4,6,1,""],covar_samp:[4,6,1,""],crc32:[4,6,1,""],create_map:[4,6,1,""],cume_dist:[4,6,1,""],current_date:[4,6,1,""],current_timestamp:[4,6,1,""],date_add:[4,6,1,""],date_format:[4,6,1,""],date_sub:[4,6,1,""],datediff:[4,6,1,""],dayofmonth:[4,6,1,""],dayofyear:[4,6,1,""],decode:[4,6,1,""],degrees:[4,6,1,""],dense_rank:[4,6,1,""],desc:[4,6,1,""],encode:[4,6,1,""],exp:[4,6,1,""],explode:[4,6,1,""],expm1:[4,6,1,""],expr:[4,6,1,""],factorial:[4,6,1,""],first:[4,6,1,""],floor:[4,6,1,""],format_number:[4,6,1,""],format_string:[4,6,1,""],from_json:[4,6,1,""],from_unixtime:[4,6,1,""],from_utc_timestamp:[4,6,1,""],get_json_object:[4,6,1,""],greatest:[4,6,1,""],grouping:[4,6,1,""],grouping_id:[4,6,1,""],hash:[4,6,1,""],hex:[4,6,1,""],hour:[4,6,1,""],hypot:[4,6,1,""],initcap:[4,6,1,""],input_file_name:[4,6,1,""],instr:[4,6,1,""],isnan:[4,6,1,""],isnull:[4,6,1,""],json_tuple:[4,6,1,""],kurtosis:[4,6,1,""],lag:[4,6,1,""],last:[4,6,1,""],last_day:[4,6,1,""],lead:[4,6,1,""],least:[4,6,1,""],length:[4,6,1,""],levenshtein:[4,6,1,""],lit:[4,6,1,""],locate:[4,6,1,""],log10:[4,6,1,""],log1p:[4,6,1,""],log2:[4,6,1,""],log:[4,6,1,""],lower:[4,6,1,""],lpad:[4,6,1,""],ltrim:[4,6,1,""],max:[4,6,1,""],md5:[4,6,1,""],mean:[4,6,1,""],min:[4,6,1,""],minute:[4,6,1,""],monotonically_increasing_id:[4,6,1,""],month:[4,6,1,""],months_between:[4,6,1,""],nanvl:[4,6,1,""],next_day:[4,6,1,""],ntile:[4,6,1,""],percent_rank:[4,6,1,""],posexplode:[4,6,1,""],pow:[4,6,1,""],quarter:[4,6,1,""],radians:[4,6,1,""],rand:[4,6,1,""],randn:[4,6,1,""],rank:[4,6,1,""],regexp_extract:[4,6,1,""],regexp_replace:[4,6,1,""],repeat:[4,6,1,""],reverse:[4,6,1,""],rint:[4,6,1,""],round:[4,6,1,""],row_number:[4,6,1,""],rpad:[4,6,1,""],rtrim:[4,6,1,""],second:[4,6,1,""],sha1:[4,6,1,""],sha2:[4,6,1,""],shiftLeft:[4,6,1,""],shiftRight:[4,6,1,""],shiftRightUnsigned:[4,6,1,""],signum:[4,6,1,""],sin:[4,6,1,""],sinh:[4,6,1,""],size:[4,6,1,""],skewness:[4,6,1,""],sort_array:[4,6,1,""],soundex:[4,6,1,""],spark_partition_id:[4,6,1,""],split:[4,6,1,""],sqrt:[4,6,1,""],stddev:[4,6,1,""],stddev_pop:[4,6,1,""],stddev_samp:[4,6,1,""],struct:[4,6,1,""],substring:[4,6,1,""],substring_index:[4,6,1,""],sum:[4,6,1,""],sumDistinct:[4,6,1,""],tan:[4,6,1,""],tanh:[4,6,1,""],toDegrees:[4,6,1,""],toRadians:[4,6,1,""],to_date:[4,6,1,""],to_json:[4,6,1,""],to_timestamp:[4,6,1,""],to_utc_timestamp:[4,6,1,""],translate:[4,6,1,""],trim:[4,6,1,""],trunc:[4,6,1,""],udf:[4,6,1,""],unbase64:[4,6,1,""],unhex:[4,6,1,""],unix_timestamp:[4,6,1,""],upper:[4,6,1,""],var_pop:[4,6,1,""],var_samp:[4,6,1,""],variance:[4,6,1,""],weekofyear:[4,6,1,""],when:[4,6,1,""],window:[4,6,1,""],year:[4,6,1,""]},"pyspark.sql.streaming":{DataStreamReader:[4,1,1,""],DataStreamWriter:[4,1,1,""],StreamingQuery:[4,1,1,""],StreamingQueryManager:[4,1,1,""]},"pyspark.sql.streaming.DataStreamReader":{csv:[4,2,1,""],format:[4,2,1,""],json:[4,2,1,""],load:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],parquet:[4,2,1,""],schema:[4,2,1,""],text:[4,2,1,""]},"pyspark.sql.streaming.DataStreamWriter":{format:[4,2,1,""],option:[4,2,1,""],options:[4,2,1,""],outputMode:[4,2,1,""],partitionBy:[4,2,1,""],queryName:[4,2,1,""],start:[4,2,1,""],trigger:[4,2,1,""]},"pyspark.sql.streaming.StreamingQuery":{awaitTermination:[4,2,1,""],exception:[4,2,1,""],explain:[4,2,1,""],id:[4,3,1,""],isActive:[4,3,1,""],lastProgress:[4,3,1,""],name:[4,3,1,""],processAllAvailable:[4,2,1,""],recentProgress:[4,3,1,""],runId:[4,3,1,""],status:[4,3,1,""],stop:[4,2,1,""]},"pyspark.sql.streaming.StreamingQueryManager":{active:[4,3,1,""],awaitAnyTermination:[4,2,1,""],get:[4,2,1,""],resetTerminated:[4,2,1,""]},"pyspark.sql.types":{ArrayType:[4,1,1,""],BinaryType:[4,1,1,""],BooleanType:[4,1,1,""],ByteType:[4,1,1,""],DataType:[4,1,1,""],DateType:[4,1,1,""],DecimalType:[4,1,1,""],DoubleType:[4,1,1,""],FloatType:[4,1,1,""],IntegerType:[4,1,1,""],LongType:[4,1,1,""],MapType:[4,1,1,""],NullType:[4,1,1,""],ShortType:[4,1,1,""],StringType:[4,1,1,""],StructField:[4,1,1,""],StructType:[4,1,1,""],TimestampType:[4,1,1,""]},"pyspark.sql.types.ArrayType":{fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.ByteType":{simpleString:[4,2,1,""]},"pyspark.sql.types.DataType":{fromInternal:[4,2,1,""],json:[4,2,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""],typeName:[4,4,1,""]},"pyspark.sql.types.DateType":{EPOCH_ORDINAL:[4,3,1,""],fromInternal:[4,2,1,""],needConversion:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.DecimalType":{jsonValue:[4,2,1,""],simpleString:[4,2,1,""]},"pyspark.sql.types.IntegerType":{simpleString:[4,2,1,""]},"pyspark.sql.types.LongType":{simpleString:[4,2,1,""]},"pyspark.sql.types.MapType":{fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.ShortType":{simpleString:[4,2,1,""]},"pyspark.sql.types.StructField":{fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""],typeName:[4,2,1,""]},"pyspark.sql.types.StructType":{add:[4,2,1,""],fromInternal:[4,2,1,""],fromJson:[4,4,1,""],jsonValue:[4,2,1,""],needConversion:[4,2,1,""],simpleString:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.sql.types.TimestampType":{fromInternal:[4,2,1,""],needConversion:[4,2,1,""],toInternal:[4,2,1,""]},"pyspark.streaming":{DStream:[5,1,1,""],StreamingContext:[5,1,1,""],StreamingListener:[5,1,1,""],flume:[5,0,0,"-"],kafka:[5,0,0,"-"],kinesis:[5,0,0,"-"]},"pyspark.streaming.DStream":{cache:[5,2,1,""],checkpoint:[5,2,1,""],cogroup:[5,2,1,""],combineByKey:[5,2,1,""],context:[5,2,1,""],count:[5,2,1,""],countByValue:[5,2,1,""],countByValueAndWindow:[5,2,1,""],countByWindow:[5,2,1,""],filter:[5,2,1,""],flatMap:[5,2,1,""],flatMapValues:[5,2,1,""],foreachRDD:[5,2,1,""],fullOuterJoin:[5,2,1,""],glom:[5,2,1,""],groupByKey:[5,2,1,""],groupByKeyAndWindow:[5,2,1,""],join:[5,2,1,""],leftOuterJoin:[5,2,1,""],map:[5,2,1,""],mapPartitions:[5,2,1,""],mapPartitionsWithIndex:[5,2,1,""],mapValues:[5,2,1,""],partitionBy:[5,2,1,""],persist:[5,2,1,""],pprint:[5,2,1,""],reduce:[5,2,1,""],reduceByKey:[5,2,1,""],reduceByKeyAndWindow:[5,2,1,""],reduceByWindow:[5,2,1,""],repartition:[5,2,1,""],rightOuterJoin:[5,2,1,""],saveAsTextFiles:[5,2,1,""],slice:[5,2,1,""],transform:[5,2,1,""],transformWith:[5,2,1,""],union:[5,2,1,""],updateStateByKey:[5,2,1,""],window:[5,2,1,""]},"pyspark.streaming.StreamingContext":{addStreamingListener:[5,2,1,""],awaitTermination:[5,2,1,""],awaitTerminationOrTimeout:[5,2,1,""],binaryRecordsStream:[5,2,1,""],checkpoint:[5,2,1,""],getActive:[5,4,1,""],getActiveOrCreate:[5,4,1,""],getOrCreate:[5,4,1,""],queueStream:[5,2,1,""],remember:[5,2,1,""],socketTextStream:[5,2,1,""],sparkContext:[5,3,1,""],start:[5,2,1,""],stop:[5,2,1,""],textFileStream:[5,2,1,""],transform:[5,2,1,""],union:[5,2,1,""]},"pyspark.streaming.StreamingListener":{Java:[5,1,1,""],onBatchCompleted:[5,2,1,""],onBatchStarted:[5,2,1,""],onBatchSubmitted:[5,2,1,""],onOutputOperationCompleted:[5,2,1,""],onOutputOperationStarted:[5,2,1,""],onReceiverError:[5,2,1,""],onReceiverStarted:[5,2,1,""],onReceiverStopped:[5,2,1,""]},"pyspark.streaming.StreamingListener.Java":{"implements":[5,3,1,""]},"pyspark.streaming.flume":{FlumeUtils:[5,1,1,""],utf8_decoder:[5,6,1,""]},"pyspark.streaming.flume.FlumeUtils":{createPollingStream:[5,5,1,""],createStream:[5,5,1,""]},"pyspark.streaming.kafka":{Broker:[5,1,1,""],KafkaMessageAndMetadata:[5,1,1,""],KafkaUtils:[5,1,1,""],OffsetRange:[5,1,1,""],TopicAndPartition:[5,1,1,""],utf8_decoder:[5,6,1,""]},"pyspark.streaming.kafka.KafkaMessageAndMetadata":{key:[5,3,1,""],message:[5,3,1,""]},"pyspark.streaming.kafka.KafkaUtils":{createDirectStream:[5,5,1,""],createRDD:[5,5,1,""],createStream:[5,5,1,""]},"pyspark.streaming.kinesis":{InitialPositionInStream:[5,1,1,""],KinesisUtils:[5,1,1,""],utf8_decoder:[5,6,1,""]},"pyspark.streaming.kinesis.InitialPositionInStream":{LATEST:[5,3,1,""],TRIM_HORIZON:[5,3,1,""]},"pyspark.streaming.kinesis.KinesisUtils":{createStream:[5,5,1,""]},pyspark:{Accumulator:[1,1,1,""],AccumulatorParam:[1,1,1,""],BasicProfiler:[1,1,1,""],Broadcast:[1,1,1,""],MarshalSerializer:[1,1,1,""],PickleSerializer:[1,1,1,""],Profiler:[1,1,1,""],RDD:[1,1,1,""],SparkConf:[1,1,1,""],SparkContext:[1,1,1,""],SparkFiles:[1,1,1,""],SparkJobInfo:[1,1,1,""],SparkStageInfo:[1,1,1,""],StatusTracker:[1,1,1,""],StorageLevel:[1,1,1,""],TaskContext:[1,1,1,""],ml:[2,0,0,"-"],sql:[4,0,0,"-"],streaming:[5,0,0,"-"]}},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","attribute","Python attribute"],"4":["py","classmethod","Python class method"],"5":["py","staticmethod","Python static method"],"6":["py","function","Python function"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:attribute","4":"py:classmethod","5":"py:staticmethod","6":"py:function"},terms:{"16be":4,"16le":4,"1a2s3a":4,"1e4":4,"1e6":4,"2nd":2,"3bc51062973c458d5a6f2d8d64a023246354ad7e064b1e4e009ec8a0699a3043":4,"3c01bdbb26f358bab27f267924aa2c9a03fcfdb8":4,"56e":3,"902fbdd2b1df0c4f70b4a5d23525e932":4,"abstract":[0,1,2,3,5],"boolean":[2,3,4],"byte":[1,4,5],"case":[1,2,3,4,5],"char":4,"class":[1,2,3,4,5],"default":[1,2,3,4,5],"final":[1,3,4],"float":[1,2,3,4],"function":[0,1,2,3,5],"import":[1,2,3,4],"int":[1,2,3,4],"long":[1,3,4,5],"new":[1,2,3,4,5],"null":[1,2,3,4,5],"public":1,"return":[1,2,3,4,5],"short":4,"static":[1,2,3,4,5],"switch":1,"throw":[2,3,4,5],"true":[1,2,3,4,5],"try":[1,3,4],"while":[1,2,4,5],ALS:[2,3],AND:4,AWS:5,Abs:2,Added:[1,4],And:[1,2],But:3,For:[1,2,3,4,5],IDs:[2,3,4],Ids:2,Its:1,NOT:[1,2,3],Not:[1,2],One:2,STS:5,THEN:4,TRs:3,That:4,The:[1,2,3,4,5],Then:2,There:[2,4],These:[1,2,4],Use:[1,2,3,4],Used:[1,3],Using:[1,3,4],With:2,__this__:2,_c0:4,_c1:4,_jconf:1,_jvm:1,aaaac:4,ab12cd:4,ababab:4,abc:4,abcd123:4,abcd:4,about:[1,2,4],abov:3,abs:[1,2,3,4],absenc:5,absolut:[1,2,3,4],absqrow:3,acceler:2,accept:[2,4],access:[1,3,4,5],accesskeyid:5,accord:[1,2,3,4],accordingli:4,accum_param:1,accumul:1,accumulatorparam:1,accuraci:[1,2,3],achiev:[2,4],aco:4,acquir:1,across:[1,2,3,4],act:2,action:[1,3],activ:[1,2,3,4,5],actual:[1,2,3,4],adapt:2,add:[1,2,3,4,5],add_month:4,add_on:4,added:[1,2,3],addfil:1,addgrid:2,adding:[2,4,5],addinplac:1,addit:[1,2,3,4,5],addition:[2,4],addpyfil:1,address:5,addstreaminglisten:5,adel:2,adjac:[2,3],adjust:2,advanc:3,advis:[1,2],affect:[1,2],affin:3,aft:2,after:[1,2,3,4,5],aftsr2:2,aftsr:2,aftsr_model:2,aftsr_path:2,aftsurvivalregress:2,aftsurvivalregressionmodel:2,again:[1,2,4],against:[2,3,4,5],againt:3,age2:4,age3:4,age:4,agecol:4,agent:5,ages:4,agg:4,aggreg:[1,2,4],aggregatebykei:1,aggregationdepth:2,aic:2,aid:1,aka:[2,4],akaik:2,alan:2,algebra:[2,3],algo:2,algorithm:[1,2,3,4],ali:4,alia:[1,2,4],alias:4,alic:4,align:4,all:[1,2,3,4,5],allclos:2,alloc:[1,2,3],allow:[1,2,3,4,5],allowbackslashescapinganycharact:4,allowcom:4,allowloc:1,allownumericleadingzero:4,allowsinglequot:4,allowunquotedfieldnam:4,almost:3,along:1,alpha:[2,3],alreadi:[1,2,3,4],als2:2,als:2,als_model:2,als_path:2,alsmodel:2,also:[1,2,3,4],alter:4,altern:[2,3,4],although:1,alwai:[1,3,4,5],amazonaw:5,among:4,amount:[2,3,4],analysi:4,analysisexcept:4,analyz:4,anexponenti:2,angl:4,ani:[1,2,3,4],anint:4,anoth:[1,2,3,4,5],answer:4,anteced:2,anthoni:3,antiton:3,apach:[1,2,4,5],api:[1,4,5],app:1,appear:[2,3],append:[1,2,3,4],appendbia:3,appl:1,applebi:2,appli:[1,2,3,4,5],applic:[1,2,3,4,5],application_1433865536131_34483:1,applicationid:1,appnam:[1,4],approach:[2,3],approx_count_distinct:4,approxcountdistinct:4,approxim:[1,2,3,4],approxnearestneighbor:2,approxquantil:[2,4],approxsimilarityjoin:2,arbitrari:[1,4],architectur:3,area:[2,3],areaunderpr:[2,3],areaunderroc:[2,3],arg1:4,arg2:4,arg:[1,2,3],argmax:2,argument:[1,2,3,4,5],arithmet:[2,3],ariti:3,arn:5,arnoldi:3,around:[2,3,4],arr:4,arrai:[1,2,3,4],array_contain:4,arraytyp:4,arriv:4,art:1,asc:4,ascend:[1,2,3,4],ascii:4,asdict:4,asin:4,asml:3,assembl:2,assert_almost_equ:3,assert_equ:3,assertionerror:[2,3],assess:5,assign:[1,2,3,4],associ:[1,2,3,4,5],associationrul:2,assum:[1,3,4,5],assumpt:4,astyp:4,asymptot:2,atan2:4,atan:4,atom:4,attach:2,attempt:[1,2],attemptnumb:1,attribut:[2,3,4],augment:3,austin:2,auto:[2,3],autobatchedseri:1,automat:[1,2,4],avaialbl:1,avail:[1,2,3,4,5],averag:[1,2,3,4],avg:4,avgmetr:2,avoid:[1,2,4],awaitanytermin:4,awaittermin:[4,5],awaitterminationortimeout:5,awsaccesskeyid:5,awssecretkei:5,back:[2,3,4],background:4,backslash:4,backward:4,bad:[1,2],bag:3,bahmani:2,banana:1,bandwidth:3,bar:1,base64:4,base:[1,2,3,4,5],baseon:2,basic:[0,1,5],basicprofil:1,batch:[1,2,3,4,5],batchcomplet:5,batchdur:5,batchsiz:1,batchstart:5,batchsubmit:5,bay:[2,3],bce:2,bce_path:2,bdf:2,bea:3,becaus:[2,3,4],becom:[3,4],been:[1,2,3,4,5],befor:[1,2,3,4,5],begin:[4,5],behav:1,behavior:[2,4],behind:4,being:[1,3,4,5],belong:[1,3,4],below:[2,3,4],benefit:4,benjamini:[2,3],bernoulli:[2,3],best:2,bestmodel:2,beta:[2,3],better:[1,2],between:[1,2,3,4,5],beyond:4,bfg:[2,3],bia:[1,3],bias:2,bigint:4,billion:4,bin:[2,3,4],binar:2,binari:[1,2,3,4,5],binarizerpath:2,binaryclassificationevalu:2,binaryclassificationmetr:3,binaryfil:1,binarylogisticregressionsummari:2,binarylogisticregressiontrainingsummari:2,binaryrecord:1,binaryrecordsstream:5,binarysearch:3,binarytyp:4,binomi:2,bisect:[2,3],bisectingkmean:[2,3],bisectingkmeansmodel:[2,3],bisectingkmeanssummari:2,bit:[2,3,4],bitwis:4,bitwiseand:4,bitwisenot:4,bitwiseor:4,bitwisexor:4,bkm2:2,bkm:2,bkm_model:2,bkm_path:2,blanklin:[3,4],blei:[2,3],block:[1,2,3,4],blockcolindex:3,blockmatrix:3,blockrowindex:3,blocks1:3,blocks2:3,blocks3:3,blocksiz:2,blor:2,blormodel:2,bob:4,bodi:5,bodydecod:5,bohman:2,bool:[2,4],booleantyp:4,boost:[2,3],bootstrap:3,both:[1,2,4,5],bottom:[2,3],bound:[2,3,4],boundari:[2,3,4],breiman:2,broadcast:[1,2,4],broker:5,bround:4,brp2:2,brp:2,brppath:2,brute:3,bskm:3,bucket:[1,2,4],bucketedrandomprojectionlsh:2,bucketedrandomprojectionlshmodel:2,bucketizerpath:2,bucketlength:2,build:[1,2,3],builder:[2,4],built:[1,4],builtin:4,bypass:3,bytearrai:4,bytebuff:1,bytetyp:4,bzip2:4,c_t:3,cach:[1,2,3,4,5],cachedexecutoridletimeout:1,cachenodeid:2,cachet:4,calcul:[2,3,4,5],calibr:2,call:[1,2,3,4,5],caller:4,came:4,can:[1,2,3,4,5],cancel:1,cancelalljob:1,canceljobgroup:1,candid:2,cannot:[1,2,3,4],captur:1,cardin:[1,3],care:[2,3],carri:[2,3],cartesian:[1,4],casesensit:2,cast:[2,4],cat:1,catalog:4,categor:[2,3],categori:[2,3],categoricalfeaturesinfo:3,categorymap:2,caus:[1,2,3],caution:1,cbrt:4,cd9fb1e148ccd8442e5aa74904cc73bf6fb54d1d54d333bd596aa9bb4bb4e961:4,cdf:[3,4],ceil:4,cell:4,censor:2,censorcol:2,center:[2,3],centr:3,centroid:3,certain:[2,3,4],chain:1,chang:[1,2,3,4,5],charact:[2,4],character:[2,5],characterist:[2,3],charset:4,cheaper:3,check:[1,2,4],checkcod:1,checkpoint:[1,2,3,4,5],checkpointinterv:[2,3,5],checkpointloc:4,checkpointpath:5,chi:[2,3],child:[2,3],chisqresult:2,chisqselector:[2,3],chisqselectormodel:[2,3],chisqselectorpath:2,chisqtest:3,chisqtestresult:3,chisquar:3,chisquaredtest:3,chisquaretest:2,choic:2,choos:[1,2,3],chosen:[1,2],chunk:2,claim:4,classif:0,classifi:[2,3],classmethod:[1,2,3,4,5],classnam:1,classof:3,classpath:4,claus:4,clazz:2,clean:2,clear:[1,2,3,4],clearcach:4,clearthreshold:3,client:5,cloglog:2,clone:1,close:[1,3,4],closest:[2,3,4],cloudwatch:5,cluster:[0,1,4,5],clustercent:[2,3],clusterdata_1:3,clusterdata_2:3,clusters:2,clusterweight:3,cmu:3,coalesc:[1,4],code:[2,3,4],codec:[1,4],coeffici:[2,3,4],coefficient_of_determin:2,coefficientmatrix:2,coefficientstandarderror:2,cogroup:[1,5],cohen:3,col1:4,col1_:4,col2:4,col:[2,3,4],coldstartstrategi:2,colin:2,collabor:2,collect:[0,1,2,3,4,5],collect_list:4,collect_set:4,collectasmap:1,colnam:4,colptr:[2,3],colsperblock:3,colstat:3,column:[0,2,3,4],columnnameofcorruptrecord:4,columnsimilar:3,com:[3,5],combfunc:1,combin:[1,2,4],combinator:2,combinebykei:[1,5],combop:1,come:4,command:[1,4],comment:4,commit:4,common:[2,3],commonli:[1,2,3],commun:2,commut:[1,5],companion:2,compar:[1,3],comparison:[2,3],compat:[1,2,3,4,5],competit:4,compil:2,complet:[1,2,3,4,5],compon:[2,3],composit:2,composition:3,compress:[1,4],compressioncodecclass:1,compris:3,comput:[1,2,3,4,5],computecolumnsummarystatist:3,computecost:[2,3],computecovari:3,computegramianmatrix:3,computeprincipalcompon:3,computeq:3,computesvd:3,computeu:3,concat:4,concat_w:4,concaten:4,concentr:[2,3],concept:[2,3],concis:4,concret:4,concurr:5,cond:4,condit:[2,3,4],conduct:[2,3],conf:[1,4],confid:[1,2,3],config:4,configur:[1,2,3,4],conflict:[2,4],confus:3,confusionmatrix:3,connect:[1,4,5],consecut:4,consequ:2,consid:[1,2,3,4],consist:[1,2,3,4],consol:4,constant:[1,2,3],constantin:3,constraint:[2,3,5],construct:[2,3,4],consum:[1,4,5],contain:[1,2,3,4,5],containsnul:4,content:[0,4],context:[0,1,2,3,5],contextu:1,conting:[2,3,4],continu:[2,3,4,5],contribut:[2,3],control:[1,2,3,4],conv:4,converg:[2,3],convergencetol:[2,3],convers:[2,4],convert:[1,2,3,4,5],convertmatrixcolumnsfromml:3,convertmatrixcolumnstoml:3,convertvectorcolumnsfromml:3,convertvectorcolumnstoml:3,cooper:2,coordin:[3,4,5],coordinatematrix:3,copi:[1,2,3,5],core:[4,5],corpu:[2,3],corr:[2,3,4],correct:[1,2,3],correctli:[3,4],correl:[2,3,4],correspond:[2,3,4,5],corrupt:4,cos:[3,4],cosh:4,cosin:[2,3,4],cosinesimilar:3,cost:[2,3,4],costli:2,could:[1,2,3,4,5],count:[1,2,3,4,5],countapprox:1,countapproxdistinct:1,countbykei:1,countbyvalu:[1,5],countbyvalueandwindow:5,countbywindow:5,countdistinct:4,counter:1,countri:4,countvector:2,countvectorizermodel:2,countvectorizerpath:2,cours:4,cov:[2,4],covar_pop:4,covar_samp:4,covari:[3,4],cover:2,covert:[2,3],cprofil:1,crash:4,crc32:4,creat:[1,2,3,4,5],create_map:4,createcombin:[1,5],createdatafram:[2,3,4],createdirectstream:5,createexternalt:4,createglobaltempview:4,createorreplaceglobaltempview:4,createorreplacetempview:4,createpollingstream:5,createrdd:5,createstream:5,createtempview:4,creation:4,credenti:5,criterion:[2,3],cross:[2,4],crossjoin:4,crosstab:4,crossvalid:2,crossvalidatormodel:2,crpc:3,csc:[2,3],cstat:3,csv:4,csv_sdf:4,ctx:1,cube:4,cume_dist:4,cumul:[3,4],currenlti:2,current:[1,2,3,4,5],current_d:4,current_timestamp:4,currentrow:4,curv:[2,3],custom:[1,4],cutler:2,cvmodel:2,cyclic:4,dai:4,danish:2,data2:2,data:[0,1,2,3,4,5],data_path:2,data_typ:4,databas:[3,4],datafram:[0,1,2,3,4],dataframenafunct:4,dataframeread:4,dataframestatfunct:4,dataframewrit:4,dataset:[0,1,2,3,4],dataseta:2,datasetb:2,datasourc:4,datastreamread:4,datastreamwrit:4,datatyp:[1,4],date1:4,date2:4,date:4,date_add:4,date_format:4,date_sub:4,datediff:4,dateformat:4,datetim:[4,5],datetyp:4,david:3,dayofmonth:4,dayofweek:4,dayofyear:4,dbname:4,dcg:3,dct:2,dctpath:2,dead:1,deal:[2,4],debug:[1,4],decai:[2,3],decayfactor:3,decid:[3,4],decim:4,decimaltyp:4,decis:[2,3],decisiontre:3,decisiontreeclassifi:2,decisiontreeclassificationmodel:2,decisiontreemodel:3,decisiontreeregressionmodel:2,decisiontreeregressor:2,declar:2,decod:[1,4,5],decomp:3,decompos:3,decomposit:3,decompress:5,decreas:[1,2,3,5],dedupl:4,deep:2,deeper:2,def:[1,3,4],defaultawscredentialsproviderchain:5,defaultminpartit:1,defaultparallel:[1,3],defaultvalu:[1,4],defin:[1,2,3,4,5],deflat:4,degre:[2,3,4],degreesoffreedom:[2,3],delai:4,delaythreshold:4,deleg:[2,3],delet:[1,2,3],delim:4,delimit:[3,4,5],dens:[2,3],dense1:[2,3],dense2:[2,3],dense3:[2,3],dense_rank:4,densematrix:[2,3],densevector:[2,3],densiti:3,depart:4,depend:[1,2,3,4,5],deploi:5,deprec:[1,2,3,4],depth:[1,2,3],deptid:4,deriv:[2,3],desc:4,descend:[1,3,4],descent:[2,3],describ:[2,3,4],describetop:[2,3],descript:[1,2],deseri:1,design:[2,3],desir:[2,3,4],destroi:[1,2],detail:[1,2,3,5],determin:[2,3,4],determinist:[3,4],develop:[3,5],developerapi:[1,2],devianc:2,devianceresidu:2,deviat:[1,2,3,4],df0:4,df1:[2,4],df2:[2,4],df3:[2,4],df4:4,df_as1:4,df_as2:4,dialect:2,dict:[1,3,4,5],dictionari:[1,2,3,4],did:[1,4],diff:4,differ:[1,2,3,4,5],difficult:2,digest:4,digit:4,dim:3,dimens:[1,2,3],dimension:[2,3,4],dir:[2,3],directli:[1,3,4,5],directori:[1,3,4,5],dirichlet:[2,3],dirnam:1,dirpath:1,disabl:[2,4],discard:2,discount:3,discoveri:[2,3],discret:[0,2,3,5],disk:[1,3,4],disk_onli:1,disk_only_2:[1,4],dispers:2,dist2:3,distanc:[2,3,4],distcol:2,distinct:[1,2,3,4,5],distnam:3,distribut:[0,1,2,4],distributed_model_path:2,distributedldamodel:2,distributedmatrix:3,divid:[1,2,3],divis:[2,3],dm1:3,dm2:3,dm3:3,dm4:3,doc:[1,2,3],docclusterkddtmw00:3,docconcentr:[2,3],doctest:[1,3,4],document:[2,3,4,5],doe:[1,2,3,4,5],doesn:4,doi:[2,3,4],doing:4,domain:4,don:[1,4],done:[1,4,5],dot:[2,3,4],dotnet:4,doubl:[2,4],doubletyp:[2,4],down:1,download:1,downweight:2,drastic:4,drawn:3,driver:[1,2,3,4,5],drop:[1,2,4],drop_dupl:4,dropdupl:4,dropglobaltempview:4,droplast:2,dropmalform:4,dropna:4,droptempt:4,droptempview:4,dsl:4,dstream:[0,3,5],dt2:2,dtc:[2,3],dtc_model:2,dtc_path:2,dtr:2,dtr_model:2,dtr_path:2,dtype:[2,4],due:[1,2,3,4],dummi:2,dump:1,dump_profil:1,duplic:[1,2,4],durat:[4,5],dure:[1,2,3,4,5],dutch:2,dynam:1,dynamicalloc:1,dynamodb:5,e_i:2,e_max:2,e_min:2,each:[1,2,3,4,5],eager:4,earli:2,earlier:5,earn:4,east:5,ecdf:3,edf:4,edit:2,edu:3,effect:[1,2,3],effici:[1,2,3,4,5],egg:1,eigenvalu:3,eigenvector:3,either:[1,2,3,4,5],elaps:5,elast:2,elasticnet:2,elasticnetparam:[2,3],electron:2,element:[1,2,3,4,5],elementtyp:4,elementwis:[2,3],elementwiseproduct:[2,3],elementwiseproductpath:2,elimin:[4,5],ellipsi:1,els:[3,4],embed:[2,3],emit:4,empir:3,empti:[1,2,3,4,5],emptyrdd:1,enabl:[4,5],enabledecompress:5,enablehivesupport:4,enclos:4,encod:[1,2,4,5],end:[1,3,4,5],endpointurl:5,endswith:4,engin:1,english:2,enough:[2,3,4],ensembl:[2,3],ensu:3,ensur:[1,5],enter:5,entir:[2,4],entri:[0,1,2,3,4,5],entropi:[2,3],env:1,environ:[1,2,3],ephemer:1,epoch:[1,4],epoch_ordin:4,eprod:[2,3],eps:3,epsilon:3,equal:[2,3,4],equat:[2,3],equi:4,equival:[1,2,3,4,5],err:4,error:[1,2,3,4,5],escap:4,escapequot:4,especi:4,essenti:2,estim:[1,2,3],estimateddocconcentr:2,estimatorparammap:2,eta:[2,3],etc:[1,4,5],euclidean:[2,3],euclideandist:2,evalu:[0,4],evaluator2:2,even:[1,2,3,4],evenli:[1,2,4],event:[2,4,5],eventtim:4,ever:4,everi:[1,2,3,4,5],everyth:4,evolv:4,exact:4,exactli:[1,2,3,4],exampl:[1,2,3,4],exce:[2,3],except:[1,2,3,4,5],exclud:2,exclus:[1,4],execut:[1,2,4,5],executor:[1,2,4],exist:[1,2,3,4,5],existingrdd:4,exp:[3,4],expand:[2,4],expans:2,expect:[1,2,3,4],expens:[1,4],experiment:[1,2,4,5],expir:5,explain:[2,3,4],explainedvari:[2,3],explainparam:2,explan:2,explicit:2,explicitli:[2,4],explod:4,exploratori:4,expm1:4,expmean:3,exponenti:[3,4],exponentialrdd:3,exponentialvectorrdd:3,expos:1,expr:4,express:[2,3,4],expstd:3,extend:[1,4],extens:2,extern:[1,4,5],extra:[2,4],extract:[2,4],extractparammap:2,fact:2,factor:[2,3],factori:[2,3,4],factoris:3,fail:[1,4],failfast:4,failur:[1,2,5],fair:1,fairli:2,fall:[1,3],fallback:1,fals:[1,2,3,4,5],falsepositiver:3,famili:[2,3,4],fast:[1,4],faster:1,fatal:1,fault:[1,5],fdr:[2,3],featur:[0,1],featureimport:2,featureindex:2,featurescol:2,featuresubsetstrategi:[2,3],feedback:2,fetch:3,few:[2,5],fewer:[1,2,3,4],field1:4,field2:4,field:[2,4],fifth:4,file1:1,file2:1,file:[1,2,3,4,5],fileinput:[1,3],filenam:1,filesystem:1,filev:1,fill:4,fillna:4,filter:[1,2,3,4,5],filterfunc:5,finalstoragelevel:2,find:[1,2,3,4],findsynonym:[2,3],finer:1,finish:1,finit:2,finnish:2,first:[1,2,3,4,5],first_product:3,first_us:3,fit:[2,3,4],fitintercept:2,five:4,fix:[1,2,3,4,5],flag:[1,4],flat:[1,2,5],flatmap:[1,5],flatmapvalu:[1,5],flatten:[1,5],fleec:1,floattyp:[2,4],floor:4,flume:0,flumeutil:5,flush:3,fmeasur:3,fmeasurebythreshold:2,fmt:2,fold:[1,2],foldbykei:1,follow:[1,2,3,4],foo:[1,4],forc:[1,2,3],forceindexlabel:2,foreach:[1,4],foreachpartit:[1,4],foreachrdd:5,forest:[2,3],forev:4,forget:[3,4],forgotten:3,fork:1,form:[1,3,4],format:[1,2,3,4],format_numb:[2,4],format_str:4,former:1,formul:3,formula:[2,3],found:[1,2,3,4],fpgrowth:[2,3],fpgrowthmodel:[2,3],fpm:0,fpr:[2,3],fraction:[1,2,3,4],frame:4,freedom:[2,3],french:2,freq:[2,3],freqitem:4,freqitemset:[2,3],freqsequ:3,frequenc:[2,3,4],frequent:[2,3,4],fri:4,friedman:2,friez:2,from:[1,2,3,4,5],from_json:4,from_unixtim:4,from_utc_timestamp:4,frombas:4,fromintern:4,fromjson:4,fromml:3,fromoffset:5,ftp:1,full:[2,3,4,5],full_out:4,fulli:[1,4],fullouterjoin:[1,5],func:[1,5],further:2,futur:[1,2],fwe:[2,3],gain:[2,3],gamma:[2,3],gammardd:3,gammavectorrdd:3,gap:[1,2,4],garbag:[1,5],gatewai:1,gaussian:[2,3],gaussianmixtur:[2,3],gaussianmixturemodel:[2,3],gaussianmixturesummari:2,gaussiansdf:2,gbt2:2,gbt:2,gbtc:2,gbtc_model:2,gbtc_path:2,gbtclassifi:2,gbtclassificationmodel:2,gbtr:2,gbtr_model:2,gbtr_path:2,gbtregressionmodel:2,gbtregressor:2,gdf:4,gencircl:3,gender:4,gener:[1,2,3,4,5],generalizedlinearregress:2,generalizedlinearregressionmodel:2,generalizedlinearregressionsummari:2,generalizedlinearregressiontrainingsummari:2,generatelinearinput:3,generatelinearrdd:3,german:2,get:[1,2,3,4,5],get_json_object:4,getact:5,getactivejobsid:1,getactiveorcr:5,getactivestageid:1,getaggregationdepth:2,getal:1,getalpha:2,getbinari:2,getblocks:2,getbucketlength:2,getcachenodeid:2,getcasesensit:2,getcensorcol:2,getcheckpointfil:[1,2],getcheckpointinterv:2,getclassifi:2,getcoldstartstrategi:2,getconf:[1,4],getdegre:2,getdocconcentr:2,getdroplast:2,getelasticnetparam:2,getestim:2,getestimatorparammap:2,getevalu:2,getfamili:2,getfdr:2,getfeatureindex:2,getfeaturescol:2,getfeaturesubsetstrategi:2,getfield:4,getfinalstoragelevel:2,getfitintercept:2,getforceindexlabel:2,getformula:2,getfpr:2,getfw:2,getgap:2,gethandleinvalid:2,getimplicitpref:2,getimpur:2,getindic:2,getinitialweight:2,getinitmod:2,getinitstep:2,getinputcol:2,getintermediatestoragelevel:2,getinvers:2,getisoton:2,getitem:4,getitemcol:2,getitemscol:2,getjobidsforgroup:1,getjobinfo:1,getk:2,getkeeplastcheckpoint:2,getlabel:2,getlabelcol:2,getlay:2,getlearningdecai:2,getlearningoffset:2,getlink:2,getlinkpow:2,getlinkpredictioncol:2,getlocalproperti:1,getlosstyp:2,getmax:2,getmaxbin:2,getmaxcategori:2,getmaxdepth:2,getmaxit:2,getmaxmemoryinmb:2,getmaxsentencelength:2,getmetricnam:2,getmin:2,getminconfid:2,getmincount:2,getmindf:2,getmindivisibleclusters:2,getmindocfreq:2,getmininfogain:2,getmininstancespernod:2,getminsupport:2,getmintf:2,getmintokenlength:2,getmissingvalu:2,getmodeltyp:2,getn:2,getnam:[2,3],getnonneg:2,getnumbucket:2,getnumfeatur:2,getnumfold:2,getnumhasht:2,getnumitemblock:2,getnumpartit:[1,2,3,4],getnumtopfeatur:2,getnumtre:2,getnumuserblock:2,getoffset:4,getoptim:2,getoptimizedocconcentr:2,getorcr:[1,4,5],getordefault:2,getoutputcol:2,getp:2,getparam:2,getpattern:2,getpercentil:2,getpredictioncol:2,getprobabilitycol:2,getquantileprob:2,getquantilescol:2,getrank:2,getratingcol:2,getrawpredictioncol:2,getregparam:2,getrelativeerror:2,getrootdirectori:1,getscalingvec:2,getse:2,getselectortyp:2,getsmooth:2,getsolv:2,getsplit:2,getstag:2,getstageinfo:1,getstandard:2,getstat:2,getsteps:2,getstopword:2,getstoragelevel:1,getstrategi:2,getsubsamplingr:2,getthreshold:2,gettol:2,gettolowercas:2,gettopicconcentr:2,gettopicdistributioncol:2,gettrainratio:2,getusercol:2,getvariancecol:2,getvariancepow:2,getvector:[2,3],getvectors:2,getvocabs:2,getweightcol:2,getwindows:2,getwithmean:2,getwithstd:2,gini:[2,3],give:[1,2,3,4],given:[1,2,3,4,5],gkhome:3,glaro:3,gleich:3,glm:2,glob:[1,3],global:[1,2,4],global_temp:4,glom:[1,5],glr2:2,glr:2,glr_model:2,glr_path:2,gm2:2,gmm:[2,3],gmm_model:2,gmm_path:2,goe:4,going:[1,4],good:3,googl:3,gracefulli:5,gradient:[2,3],gradientboostedtre:3,gradientboostedtreesmodel:3,grain:1,gram:[2,3],gramian:3,grape:1,graph:[3,5],graphx:1,greater:[1,3,4],greatest:[3,4],greenwald:4,grid:2,ground:3,group:[0,1,2,3,4,5],groupbi:[1,4],groupbykei:[1,5],groupbykeyandwindow:5,groupeddata:4,groupid:[1,5],grouping_id:4,groupwith:1,grow:4,growth:[2,3],guarante:[1,2,3,4],guid:5,gzip:4,gzipcodec:1,had:[1,4],hadamard:[2,3],hadoop:[1,3,4,5],hadoopfil:1,hadooprdd:1,half:3,half_even:4,half_up:4,halflif:3,han2000:2,han:2,hand:3,handl:[1,2,3,4],handleinvalid:2,happen:4,hard:4,has:[1,2,3,4,5],hasdefault:2,hash:[1,2,3,4,5],hashabl:3,hashingtf:[2,3],hashingtfpath:2,hasintercept:2,hasparam:2,hassummari:2,hasti:2,hat:[2,3],have:[1,2,3,4,5],hdf:[1,5],head:[2,4],header:4,height:4,held:2,hello:[1,4],help:[1,2],helper:[1,3],henc:[2,3],here:[1,2,3,4],hex:4,hexadecim:4,hidden:2,hierarch:3,high:[1,2,3],higher:[2,3,5],highest:[2,3],hing:2,hint:4,histogram:[1,2],histori:2,hive:4,hivecontext:4,hiveql:4,hochberg:[2,3],hoefl:3,hoffman:2,hold:[2,3],holger:3,hook_compress:1,host:5,hostnam:5,hot:2,hour:[4,5],hourli:4,how:[1,2,3,4,5],howev:[1,3,4],htf:3,html:1,http:[1,2,3,4,5],human:3,hungarian:2,hyper:2,hyperbol:4,hyperloglog:1,hyperparamet:2,hypot:4,hypothesi:[2,3],iam:5,icd:3,ice:4,icml2010:3,ida:2,idb:2,idea:2,ident:[2,4],identifi:[1,2,3,5],idf:[2,3],idfmodel:[2,3],idfpath:2,ids:[1,2],idx:4,iff:4,ignor:[2,3,4,5],ignore_exception_detail:4,ignoreleadingwhitespac:4,ignorenul:4,ignoretrailingwhitespac:4,ill:3,immedi:[1,4],immut:1,implement:[1,2,3,4,5],implicit:[2,3],implicitli:4,implicitpref:2,improv:2,impur:[2,3],imput:2,imputermodel:2,imputerpath:2,includ:[1,2,3,4,5],inclus:[4,5],incom:3,incomplet:1,inconsist:3,incorrect:2,increas:[1,2,3,4,5],increment:[1,4,5],incur:3,independ:[2,3,4],indeterminist:4,index1:3,index2:3,index:[1,2,3,4],indexedrow:3,indexedrowmatrix:3,indexof:3,indextostr:2,indextostringpath:2,indic:[1,2,3,4],individu:[1,2,3],inf:[2,3,4],infer:[1,2,3,4],inferschema:4,infin:[1,2,4],info:[1,2,3,5],inform:[1,2,3,4,5],inherit:[1,3],initcap:4,initcent:3,initi:[1,2,3,5],initializationmod:3,initializationmodel:3,initializationstep:3,initialmodel:3,initialpositioninstream:5,initialrdd:5,initialweight:[2,3],initmod:[2,3],initstep:2,initweight:3,inner:4,inout:3,input:[1,2,3,4,5],input_file_nam:4,inputcol:2,inputformat:1,inputformatclass:1,inputtoken:2,insensit:[2,4],inser:1,insert:4,insertinto:4,insid:[1,4],instal:[1,4],instanc:[1,2,3,4],instanti:[1,4],instead:[1,2,3,4],instr:4,integ:[1,2,3,4],integertyp:4,integr:4,intend:4,intent:5,intention:1,intercept:[2,3],interceptvector:2,interfac:4,intermedi:[2,3,4],intermediatestoragelevel:2,intern:[1,2,3,4,5],interoper:5,interpol:3,interpret:[1,4,5],interrupt:1,interruptoncancel:1,intersect:[1,4],interv:[2,3,4,5],intlist:4,intuit:3,intwrit:1,invalid:[2,4],invers:[2,3,4,5],invert:[2,5],invfunc:5,invoc:[1,4],invok:[1,3,4],involv:2,invreducefunc:5,ir2:2,ir_model:2,ir_path:2,irl:2,irm:3,irrecover:1,is_cach:1,isact:4,ischeckpoint:1,isdefin:2,isdistribut:2,isempti:1,isin:4,isinst:3,islargerbett:2,isloc:4,islocallycheckpoint:1,isn:4,isnan:[3,4],isnotnul:4,isnul:4,iso:4,isoton:[2,3],isotonicregress:[2,3],isotonicregressionmodel:[2,3],isset:2,isstream:4,issu:[2,3],istemporari:4,istranspos:[2,3],italian:2,itd:2,item:[1,2,3,4],item_rec:2,itemcol:2,itemfactor:2,itemscol:2,itemset:[2,3],iter:[1,2,3,4],its:[1,2,3,4,5],itself:[4,5],jaccard:2,jaccarddist:2,jar:1,java:[1,2,3,4,5],java_model:[2,3],java_obj:2,javaclassnam:4,javaload:3,javamlread:2,javamlwrit:2,javamodel:2,javamodelwrapp:3,javaparam:2,javapredictionmodel:2,javardd:5,javasav:3,javastreamingcontext:5,javastringlength2:4,javastringlength:4,javatowritableconvert:1,javavectortransform:3,jdbc:4,jdf:4,jdstream:5,jgd:4,jhivecontext:4,jmlr:[2,3],job:[1,5],job_to_cancel:1,jobgroup:1,jobid:1,john:4,join:[1,2,3,4,5],joined_df:4,jordan:[2,3],journal:[2,3],jrdd:1,jrdd_deseri:[1,5],jsc:1,json:[3,4],json_sdf:4,json_tupl:4,jsonvalu:4,jsparksess:4,jspec:4,jsq:4,jsqlcontext:4,jsqm:4,jssc:5,jstring:4,jtracker:1,just:[2,3,4],jvm:4,kafka:0,kafkamessageandmetadata:5,kafkaparam:5,kafkautil:5,karp:4,karypi:[2,3],kcl:5,kdd:3,kearslei:3,keep:[1,2,3,4],keeplastcheckpoint:2,keepseri:5,kei:[1,2,3,4,5],kept:[1,2],kerneldens:3,key1:4,key2:4,keybi:1,keyclass:1,keyconvert:1,keydecod:5,keyfunc:1,keytyp:4,keyword:[2,4],khanna:4,kind:[3,4],kinesi:0,kinesisappnam:5,kinesisutil:5,kitten:4,kmean:[2,3],kmeans2:2,kmeans_model:2,kmeans_path:2,kmeansmodel:[2,3],knob:3,know:4,known:[1,2,3,4],kolmogorov:3,kolmogorovsmirnovtest:3,kolmogorovsmirnovtestresult:3,ksmodel:3,kstest:3,kth:1,kumar:[2,3],kurtosi:4,kwarg:4,l_1:3,l_2:3,label2:2,label:[2,3],labelcol:2,labeledpoint:3,lag:4,laid:4,lamb:1,lambda:[1,2,3,4],lambda_:3,languag:[1,2,3,4],larg:[1,2,3,4,5],large_broadcast:1,larger:[2,3,4],largest:[1,2,3,4],lasso:2,lassomodel:3,lassowithsgd:3,last:[1,2,3,4,5],last_dai:4,lastprogress:4,late:4,latent:[2,3],later:[2,3,4],latest:[3,4,5],latestmodel:3,latter:[1,2,3,4],layer:[1,2],lazi:3,lbfg:3,lda:[2,3],lda_distributed_model:2,lda_local_model:2,lda_path:2,ldamodel:[2,3],ldaoptim:3,lead:[3,4],leader:5,leaf:[2,3],learn:[2,3],learningdecai:2,learningoffset:2,learningr:3,leas:5,least:[1,2,3,4],leastabsoluteerror:3,leastsquareserror:3,leav:4,left:[1,2,3,4,5],left_anti:4,left_out:4,left_semi:4,leftouterjoin:[1,5],lemon:1,len:[1,2,3,4],length:[1,2,3,4,5],leo:2,less:[2,3,4],lesser:3,let:[2,3],letter:4,level:[1,2,3,4,5],levenshtein:4,li2008:2,lib:1,liblinear:3,librari:[1,4,5],libsvm:[2,3],lifetim:4,like:[1,2,3,4],likelihood:[2,3],limit:[1,2,4,5],lin:3,linalg:0,line:[1,3,4,5],lineag:[1,2],linear:[2,3],lineardatagener:3,linearli:2,linearmodel:3,linearregress:[2,3],linearregressionmodel:[2,3],linearregressionsummari:2,linearregressiontrainingsummari:2,linearregressionwithsgd:3,linearsvc:2,linearsvcmodel:2,link:2,linkpow:2,linkpredictioncol:2,list:[1,2,3,4,5],lit:4,liter:4,literatur:2,littl:1,live:5,load:[1,2,3,4,5],loaddefault:1,loaddefaultstopword:2,loadedassembl:2,loadedbinar:2,loadedbucket:2,loadedcv:2,loadeddtc:2,loadedencod:2,loadedep:2,loadedhashingtf:2,loadedidf:2,loadedimput:2,loadedindex:2,loadedinvert:2,loadedmascal:2,loadedmmscal:2,loadedmodel:2,loadedngram:2,loadednorm:2,loadedpca:2,loadedpx:2,loadedqd:2,loadedremov:2,loadedretoken:2,loadedrf:2,loadedselector:2,loadedsqltran:2,loadedstandardscal:2,loadedtoken:2,loadedv:2,loadedword2vec:2,loader:3,loadlabeledpoint:3,loadlibsvmfil:3,loadvector:3,local:[1,2,3,4],local_model_path:2,localcheckpoint:1,localdoc:3,localldamodel:2,localmodel:2,locat:[1,2,4,5],lock:1,log10:4,log1p:4,log2:[2,3,4],log:[1,2,3,4],logarithm:4,logic:4,logist:[2,3],logisticregress:[2,3],logisticregressionmodel:[2,3],logisticregressionsummari:2,logisticregressiontrainingsummari:2,logisticregressionwithlbfg:3,logisticregressionwithsgd:3,logit:2,loglevel:1,loglikelihood:2,logloss:3,lognormalrdd:3,lognormalvectorrdd:3,logperplex:2,logprior:2,longer:[1,2,4],longtyp:[2,4],longwrit:1,look:[3,4,5],lookup:1,loss:[2,3],losstyp:2,lost:2,low:[1,2,3],lower:[1,2,3,4],lowerbound:4,lowercas:2,lowest:3,lpad:4,lr2:2,lr_model:2,lr_path:2,lrm:3,lsdw6p:3,lsh:2,ltrim:4,lz4:4,lzo:4,m_t:3,machin:[2,3,5],made:[1,4],mae:2,magnitud:3,mai:[1,2,3,4,5],main:[0,1,4,5],maintain:2,major:[2,3],make:[2,3,4,5],malform:4,manag:[2,4],mani:[1,2,4],manipul:4,manner:1,map:[1,2,3,4,5],map_func:1,mapfield:4,mappartit:[1,4,5],mappartitionswithindex:[1,5],mappartitionswithsplit:1,mapper:1,mapr:1,mapreduc:[1,3],maptyp:4,mapvalu:[1,5],mari:1,mark:[1,2,4],marshal:1,marshalseri:1,mascal:2,master:[1,4,5],mat1:3,mat2:3,mat3:3,mat:3,mat_transpos:3,match:[1,2,3,4],materi:1,math:3,mathemat:[2,3,4],matric:[2,3],matrix:[2,3],matrixentri:3,matrixfactorizationmodel:3,matter:1,max:[1,2,3,4],maxab:2,maxabsscal:2,maxabsscalermodel:2,maxbatchs:5,maxbin:[2,3],maxcategori:2,maxcharspercolumn:4,maxcolumn:4,maxdepth:[2,3],maxim:[2,3],maximum:[1,2,3,4,5],maxit:2,maxiter:3,maxlocalprojdbs:3,maxmalformedlogperpartit:4,maxmemoryinmb:2,maxpatternlength:3,maxsentencelength:2,maxsiz:4,maxtermspertop:[2,3],mce:2,mce_path:2,mcm:3,md5:4,mdf:2,mean:[1,2,3,4],meanabsoluteerror:[2,3],meanapprox:1,meanaverageprecis:3,meaning:3,meansquarederror:[2,3],meant:4,measur:[2,3,4],mechan:[1,4],median:[2,4],meet:[1,4],membership:3,memori:[1,2,4],memory_and_disk:[1,2,4],memory_and_disk_2:[1,5],memory_and_disk_s:1,memory_and_disk_ser_2:1,memory_onli:[1,5],memory_only_2:1,memory_only_s:1,memory_only_ser_2:1,merg:[1,2,4],mergecombin:[1,5],mergeschema:4,mergevalu:[1,5],messag:[2,5],messagehandl:5,meta:5,metadata:[1,2,3,4,5],metastor:4,meth:3,method:[1,2,3,4,5],methodnam:2,metric:[2,3,5],metricnam:2,mh2:2,mhpath:2,michael:3,microsecond:4,might:[1,3,4],mike:4,millisecond:4,min:[1,2,3,4],minconfid:2,mincount:[2,3],mindf:2,mindivisibleclusters:[2,3],mindocfreq:[2,3],mine:[2,3],minhash:2,minhashlsh:2,minhashlshmodel:2,mini:2,minibatchfract:3,minim:[2,3,4],minimum:[1,2,3,4,5],mininfogain:[2,3],mininstancespernod:[2,3],minmaxscal:2,minmaxscalermodel:2,minmaxscalerpath:2,minpartit:[1,3],minsplit:1,minsupport:[2,3],mintf:2,mintokenlength:2,minu:4,minut:4,mismatch:[2,3],miss:[1,2,4],missingvalu:2,mix:2,mixin:[2,3],mixtur:[2,3],mkdir:1,mkdtemp:[3,4],mllib:[0,1,2],mlor:2,mlormodel:2,mlp2:2,mlp:2,mlp_model:2,mlp_path:2,mlreadabl:2,mlreader:2,mlutil:3,mlwritabl:2,mlwriter:2,mmscaler:2,mode:[2,3,4],model2:2,model3:2,model:[2,3],model_path:[2,3],modelpath:2,modeltyp:2,modif:[2,3],modifi:[1,2],modul:[0,1],modulo:2,moment:4,mon:4,monitor:[1,5],monoton:[2,3,4],monotonically_increasing_id:4,month:4,months_between:4,more:[1,2,3,4,5],most:[1,2,3,4],move:[3,5],mse:2,much:[1,4],multi:[1,2,4],multi_class_data:3,multiclass:[2,3],multiclassclassificationevalu:2,multiclassmetr:3,multilay:2,multilayerperceptronclassifi:2,multilayerperceptronclassificationmodel:2,multilin:4,multinomi:[2,3],multipl:[1,2,3,4,5],multipli:[2,3],multivari:[2,3],multivariategaussian:3,multivariatestatisticalsummari:3,murmurhash3_x86_32:2,murmurhash:2,mus:3,must:[1,2,3,4,5],mutat:1,mycustomprofil:1,mypassword:4,myrdd:1,n_t:3,n_th:3,naiv:[2,3],naivebay:[2,3],naivebayesmodel:[2,3],name:[0,1,2,3,4,5],namedtemporaryfil:[1,3],namedtupl:4,nan:[2,3,4],nanvalu:4,nanvl:4,narrow:4,nativ:4,natur:[2,3,4],nb2:2,nb_model:2,nb_path:2,nbar:1,ndarrai:[2,3],ndcg:3,ndcgat:3,nearest:[2,3],neariso:3,nearli:[1,3],necessari:2,need:[1,2,3,4],needconvers:4,neg:[2,3,4],negativeinf:4,neighbor:2,neither:2,nest:[3,4],net:2,netflix:3,netti:5,neuron:2,neutral:1,new_data:2,newapihadoopfil:1,newapihadooprdd:1,newli:[2,4],newlin:[3,4],newsess:4,nexampl:3,next:[2,4],next_dai:4,nfeatur:3,nfoo:1,ngram:2,ngrampath:2,nnnnn:1,node:[1,2,3,4],nois:3,nomin:2,non:[1,2,3,4],none:[1,2,3,4,5],nonneg:[2,3],nonposit:3,nonzero:[2,3],noqa:1,nor2:3,nor:3,norm:[2,3],normal:[1,2,3,4],normalize_whitespac:3,normalizerpath:2,normalrdd:3,normalvectorrdd:3,norml1:3,norml2:3,norwegian:2,notat:3,note:[2,3,4,5],now:[2,4],npart:3,npoint:3,ntile:4,nullabl:4,nulldevi:2,nullhypothesi:3,nulltyp:4,nullvalu:4,num:[1,2,3,4,5],number:[1,2,3,4,5],numbit:4,numbucket:2,numclass:[2,3],numcol:[2,3],numcolblock:3,numer:[1,2,3,4],numfeatur:[2,3],numfold:2,numhasht:2,numinst:2,numitem:2,numitemblock:2,numiter:[2,3],numlabel:2,numnearestneighbor:2,numnod:[2,3],numnonzero:[2,3],numpartit:[1,2,3,4,5],numpi:[2,3],numrecentprogressupd:4,numrow:[2,3],numrowblock:3,numslic:1,numtopfeatur:[2,3],numtre:[2,3],numus:2,numuserblock:2,obj:[1,4],object:[1,2,3,4,5],objectivehistori:2,observ:[2,3],obtain:[2,3],occur:[2,3],occurr:[2,4],off:[1,3,4],off_heap:1,offset:[4,5],offsetrang:5,often:[1,2,4],old:[1,3,5],older:4,omit:4,onbatchcomplet:5,onbatchstart:5,onbatchsubmit:5,onc:[1,2,4,5],one:[1,2,3,4,5],oneatatim:5,onehot:2,onehotencod:2,onehotencoderpath:2,ones:3,onethird:[2,3],onevsrest:2,onevsrestmodel:2,onli:[1,2,3,4,5],onlin:[2,3,4],onoutputoperationcomplet:5,onoutputoperationstart:5,onreceivererror:5,onreceiverstart:5,onreceiverstop:5,open:1,openhook:1,oper:[1,2,3,4,5],opt1:4,opt2:4,opt3:4,optim:[2,3,4],optimizedocconcentr:2,optimum:2,option:[1,2,3,4,5],orantiton:2,orc:4,orc_df:4,orc_partit:4,order:[1,2,3,4,5],orderbi:[2,4],ordin:4,ordinari:2,org:[1,2,3,4,5],orient:3,origin:[1,2,3],originalmax:2,originalmin:2,origvec:2,orthogon:3,oserror:3,other:[1,2,3,4,5],otherwis:[1,2,3,4],our:[1,3],out:[1,2,3,4],out_a:2,out_b:2,outcom:[2,3],outer:[1,4,5],output:[1,2,3,4],outputcol:2,outputformat:1,outputformatclass:1,outputmod:4,outputoperationcomplet:5,outputoperationstart:5,outsid:[2,4,5],over:[1,2,3,4,5],overflow:4,overlap:2,overrid:[1,2,4],overwrit:[2,4],ovr:2,ovr_model:2,owlqn:2,own:[2,4,5],p362:4,p7c96j6:3,packag:0,package_extens:1,pad:[2,4],page:0,pair:[1,2,3,4,5],panda:4,papadimitri:4,paper:[2,3],parallel:[1,2,3,4,5],param:[0,3,4,5],paramet:[1,2,3,4,5],parametr:2,paramgridbuild:2,parammap:2,paramnam:2,paramt:2,parent:[1,2,3,5],parquet:[3,4],parquet_partit:4,parquet_sdf:4,pars:[3,4],part:[1,3,4],particular:[1,3],partit:[1,2,3,4,5],partition:[1,5],partitionbi:[1,4,5],partitionfunc:[1,5],partitionid:1,pass:[1,2,3,4],password:4,past:4,path:[1,2,3,4],pattern:[1,2,3,4],paul:3,pav:3,pca:[2,3],pca_featur:2,pcamodel:2,pcapath:2,pdf:3,pearson:[2,3,4],pearsoncorr:[2,3],pei:3,penalti:[2,3],peopl:4,people1:4,per:[1,2,3,4,5],percent_rank:4,percentil:[2,3,4],perceptron:2,perform:[1,2,3,4],period:[1,3,5],permiss:4,permit:2,permut:2,perplex:2,persist:[1,3,4,5],person:4,peter:4,pfp:2,phrase:3,physic:4,physica:3,pic:3,pick:[2,5],pickl:1,pickle_registri:1,picklefil:1,pickleseri:1,pid:4,piec:2,piecewis:3,pipe:1,pipelin:0,pipelinemodel:2,pivot:4,pivot_col:4,place:[1,2,3,4],placehold:2,plan:[2,4],pleas:[3,4],plu:[3,4],poi:3,point:[0,1,2,3,4,5],poisson:[2,3],poissonrdd:3,poissonvectorrdd:3,poli:2,polici:5,poll:5,polyexpansionpath:2,polynomi:2,polynomialexpans:2,pool:[1,2,3],poorli:2,popul:[3,4],port:5,portable_hash:[1,5],portugues:2,pos:4,posexplod:4,posit:[2,3,4,5],positiveinf:4,possibl:[2,3,4],potenti:1,pow:4,power:[2,3,4],poweriterationclust:3,poweriterationclusteringmodel:3,pprint:5,practic:[1,2],pre:[2,3],preced:[2,4],precis:[2,3,4],precisionat:3,precisionbythreshold:2,predic:[1,4,5],predict:[2,3],predictal:3,predictionandlabel:3,predictionandobserv:3,predictioncol:2,predicton:3,predictonvalu:3,predictor:2,predictquantil:2,predictsoft:3,prefer:[1,2,3],prefersdecim:4,prefix:[3,5],prefixspan:3,prefixspanmodel:3,prepar:1,prepend:2,present:[2,3,4],preserv:2,preservespartit:[1,5],prevent:3,previou:[3,4,5],previous:1,prime:2,primit:[1,4],primitivesasstr:4,princip:[2,3],print:[1,2,3,4,5],printabl:1,printf:4,printschema:4,prior:[2,3,4],prioriti:[1,2,3],privat:2,probabilist:2,probabilitycol:2,probabilti:3,probabl:[1,2,3,4],probit:2,problem:[2,3],procedur:[2,3],process:[1,2,3,4,5],processallavail:4,processingtim:4,produc:[1,2,3,4],product:[1,2,3,4],productfeatur:3,productid:3,products_for_us:3,profil:1,profiler_cl:1,program:[1,4,5],programm:1,progress:[1,4],project:[2,3,4],propag:[1,4],properti:[1,3,4,5],proport:[2,3],propos:4,provid:[1,2,3,4,5],pst:4,pstat:1,pub:3,pull:5,purpos:4,put:[2,4],pvalu:[2,3],py4jjavaerror:4,pyfil:1,pyrolit:1,pyspark:0,python:[1,2,3,4],pythonstreaminglisten:5,qds:2,qrdecomposit:3,quadrat:[2,3],qualifi:[1,4],qualiti:3,quantil:[2,4],quantilediscret:2,quantilediscretizerpath:2,quantileprob:2,quantilescol:2,quarter:4,queri:[2,3,4,5],query_explain:4,querynam:4,queue:5,queuestream:5,quickli:2,quorum:5,quot:4,quotat:4,quoteal:4,r26:2,radian:4,rais:[1,2,3,4],rand:4,randn:4,random:[0,1,2,4],randomforest:3,randomforestclassifi:2,randomforestclassificationmodel:2,randomforestmodel:3,randomforestregressionmodel:2,randomforestregressor:2,randomli:[1,2,4],randomrdd:3,randomsplit:[1,4],rang:[1,2,3,4,5],range0:4,rangebetween:4,rank:[2,3,4],rankingmetr:3,rare:2,rate:[1,2,3],rather:[1,2,3,4],ratingcol:2,ratio:[2,4],raw:[2,3],rawpredict:2,rawpredictioncol:2,rcond:3,rdd1:1,rdd2:1,rdd:[0,1,2,3,4,5],rdd_a:5,rdd_b:5,re_path:2,reach:[2,3],read:[1,2,4,5],readabl:3,readlin:1,readstream:4,real:[2,3,4],reason:4,recal:[2,3],recallbythreshold:2,receiv:[1,2,3,5],receivererror:5,receiverstart:5,receiverstop:5,recent:[1,2,3,4],recentprogress:4,reciproc:3,recogn:[3,5],recommend:[0,1,4],recommendforallitem:2,recommendforallus:2,recommendproduct:3,recommendproductsforus:3,recommendus:3,recommendusersforproduct:3,recomput:[1,2],record:[1,3,4,5],recordlength:[1,5],recov:5,recreat:5,rectangular:4,recurs:[1,4],redistribut:1,reduc:[1,2,5],reducebykei:[1,5],reducebykeyandwindow:5,reducebykeyloc:1,reducebywindow:5,reducefunc:5,reduct:[2,5],redund:4,refer:[1,2,3],reflect:4,refresh:4,refresht:4,regex:[2,4],regexp:4,regexp_extract:4,regexp_replac:4,regextoken:2,regextokenizerpath:2,region:5,regionnam:5,regist:[1,4],registerdataframeast:4,registerfunct:4,registerjavafunct:4,registertempt:4,registr:4,regparam:[2,3],regress:0,regressionevalu:2,regressionmetr:3,regtyp:3,regular:[2,3,4],reimplement:3,rel:[1,2,3,4],relat:[1,2,4,5],relationship:2,relativeerror:[2,4],relativesd:1,releas:[1,2,5],relev:[3,4],reliabl:[1,5],remain:2,rememb:5,remov:[1,2,3,4],renam:4,rep:4,repartit:[1,4,5],repartitionandsortwithinpartit:1,repeat:4,repeatedli:2,replac:[1,2,3,4],replic:1,report:[1,3,5],repres:[1,2,3,4,5],represent:[1,2,3,4,5],request:[4,5],requir:[1,2,3,4],rescal:[2,3],research:3,reseri:1,resettermin:4,reshap:[2,3],residu:2,residualdegreeoffreedom:2,residualdegreeoffreedomnul:2,residualstyp:2,resili:[0,1],resolv:[1,4],resolvedrformula:2,respect:[3,4,5],respond:1,respons:2,restart:4,result:[1,2,3,4,5],resultvec:2,retain:[1,4,5],retainedjob:1,retainedstag:1,retoken:2,retriev:[2,3,4],returntyp:4,reus:1,revers:4,rf2:2,rfc:2,rfc_model:2,rfc_path:2,rformula:2,rformulamodel:2,rformulapath:2,rfr:2,rfr_model:2,rfr_path:2,rice:3,richard:3,ridg:2,ridgeregressionmod:3,ridgeregressionmodel:3,ridgeregressionwithsgd:3,right:[1,2,3,4,5],right_out:4,rightouterjoin:[1,5],rint:4,rise:3,risk:[2,3],ritz:3,rlike:4,rmse:2,rmtree:3,rng:3,rnlt:4,robert:3,roc:[2,3],role:5,rollup:4,root:[1,2,3,4],rootmeansquarederror:[2,3],roughli:1,round:[2,3,4],row1:4,row2:4,row3:4,row:[2,3,4],row_numb:4,rowindic:[2,3],rowmatrix:3,rowsbetween:4,rowsperblock:3,rpad:4,rpc:5,rsd:4,rtrim:4,rule:[2,3],run:[1,2,3,4,5],runid:4,runjob:1,runtim:4,russian:2,ryan:3,ryantib:3,sacrific:1,safe:[1,4],sai:4,said:2,salari:4,same:[1,2,3,4,5],samelda:2,samelocalmodel:2,samemodel:[2,3],samemu:3,samesigma:3,sampl:[1,2,3,4],sample_fpgrowth:2,sample_multiclass_classification_data:2,samplebi:4,samplebykei:1,samplestdev:1,samplevari:1,samplingratio:4,sat:4,satisfi:[1,5],save:[1,2,3,4,5],saveabl:3,saveashadoopdataset:1,saveashadoopfil:1,saveaslibsvmfil:3,saveasnewapihadoopdataset:1,saveasnewapihadoopfil:1,saveaspicklefil:1,saveassequencefil:1,saveast:4,saveastextfil:[1,3,5],savemod:4,scala:[1,3,4],scalabl:3,scalar:[2,4],scale:[2,3,4],scaler:2,scalerpath:2,scalingvec:2,scalingvector:3,scan:[1,2,3,4],scenario:2,schedul:[1,4,5],schema:4,scheme:4,schenker:4,scikit:2,scipi:[2,3],scope:2,score:[2,3],scoreandlabel:[2,3],sdf:4,sdf_schema:4,search:[0,1,2,4],second:[1,3,4,5],secretkei:5,secur:5,see:[1,2,3,4,5],seed:[1,2,3,4],seen:[2,4,5],select:[2,3,4],selectedfeatur:2,selectexpr:4,selector:[2,3],selectortyp:[2,3],self:[1,2],semant:1,send:[1,2,5],sensit:[2,4],sent:[1,2,5],sentenc:[2,3,4],sep:4,separ:[2,3,4],seqfunc:1,seqop:1,sequenc:[1,2,3,4,5],sequencefil:1,sequencefileoutputformat:1,sequenti:[1,3,4],sequncefil:1,serd:4,serial:1,server:5,servic:5,session:[2,4,5],set:[1,2,3,4,5],setaggregationdepth:2,setal:1,setalpha:2,setappnam:1,setbandwidth:3,setbinari:[2,3],setblocks:2,setbucketlength:2,setcachenodeid:2,setcasesensit:2,setcensorcol:2,setcheckpointdir:[1,4],setcheckpointinterv:2,setclassifi:2,setcoldstartstrategi:2,setconf:4,setdecayfactor:3,setdegre:2,setdocconcentr:2,setdroplast:2,setelasticnetparam:2,setestim:2,setestimatorparammap:2,setevalu:2,setexecutorenv:1,setfamili:2,setfdr:[2,3],setfeatureindex:2,setfeaturescol:2,setfeaturesubsetstrategi:2,setfinalstoragelevel:2,setfitintercept:2,setforceindexlabel:2,setformula:2,setfpr:[2,3],setfw:[2,3],setgap:2,sethalflif:3,sethandleinvalid:2,setifmiss:1,setimplicitpref:2,setimpur:2,setindic:2,setinitialcent:3,setinitialweight:[2,3],setinitmod:2,setinitstep:2,setinputcol:2,setintermediatestoragelevel:2,setinvers:2,setisoton:2,setitemcol:2,setitemscol:2,setjobgroup:1,setk:[2,3],setkeeplastcheckpoint:2,setlabel:2,setlabelcol:2,setlay:2,setlearningdecai:2,setlearningoffset:2,setlearningr:3,setlink:2,setlinkpow:2,setlinkpredictioncol:2,setlocalproperti:1,setloglevel:1,setlosstyp:2,setmast:1,setmax:2,setmaxbin:2,setmaxcategori:2,setmaxdepth:2,setmaxit:2,setmaxmemoryinmb:2,setmaxsentencelength:2,setmetricnam:2,setmin:2,setminconfid:2,setmincount:[2,3],setmindf:2,setmindivisibleclusters:2,setmindocfreq:2,setmininfogain:2,setmininstancespernod:2,setminsupport:2,setmintf:2,setmintokenlength:2,setmissingvalu:2,setmodeltyp:2,setn:2,setnam:[1,2],setnonneg:2,setnumblock:2,setnumbucket:2,setnumfeatur:2,setnumfold:2,setnumhasht:2,setnumitemblock:2,setnumiter:3,setnumpartit:[2,3],setnumtopfeatur:[2,3],setnumtre:2,setnumuserblock:2,setoptim:2,setoptimizedocconcentr:2,setoutputcol:2,setp:2,setparam:2,setpattern:2,setpercentil:[2,3],setpredictioncol:2,setprobabilitycol:2,setquantileprob:2,setquantilescol:2,setrandomcent:3,setrank:2,setratingcol:2,setrawpredictioncol:2,setregparam:2,setrelativeerror:2,setsampl:3,setscalingvec:2,setse:[2,3],setselectortyp:[2,3],setsmooth:2,setsolv:2,setsparkhom:1,setsplit:2,setstag:2,setstandard:2,setstat:2,setsteps:2,setstopword:2,setstrategi:2,setsubsamplingr:2,setsystemproperti:1,setter:[1,3],setthreshold:[2,3],settol:2,settolowercas:2,settopicconcentr:2,settopicdistributioncol:2,settrainratio:2,setup:5,setupfunc:5,setusercol:2,setvariancecol:2,setvariancepow:2,setvectors:[2,3],setvocabs:2,setweightcol:2,setwindows:[2,3],setwithmean:[2,3],setwithstd:[2,3],sever:4,sgd:3,sha1:4,sha2:4,sha:4,shallow:2,shape:3,share:[1,3,4],shell:1,shift:[2,4],shiftleft:4,shiftright:4,shiftrightunsign:4,ship:1,shortcut:2,shorten:4,shorter:4,shorthand:4,shorttyp:4,should:[1,2,3,4,5],shouldn:3,show:[1,2,4],show_profil:1,shown:4,shrink:3,shuffl:[1,3,4],shut:1,shutil:3,si_model:2,side:[1,2,3,4],sigma:3,sigmoid:2,sign:4,signum:4,silent:4,sim:3,similar:[2,3,4,5],similarli:1,simpl:[2,3,4],simpledateformat:4,simplestr:4,simpli:[2,3,4],sin:[3,4],sinc:[1,2,3,4],sine:4,singl:[1,2,3,4,5],singleton:1,singular:3,singularvaluedecomposit:3,sinh:4,sink:[4,5],sit:4,site:4,size:[1,2,3,4],skew:4,skinni:3,skip:[1,2,3,4],slave:5,sleep:1,slen:4,slice:[2,4,5],slicer:2,slide:5,slidedur:[4,5],slow:1,slower:5,small:[1,2,3,4],smaller:[1,2,3],smallest:3,smirnov:3,smooth:[2,3],snappi:4,socket:5,sockettextstream:5,soft:3,softlib:3,softmax:[2,3],softpredict:3,solv:[2,3],solver:2,some:[1,2,3,4],someth:1,somewhat:1,sort:[1,2,3,4],sort_arrai:4,sortbi:1,sortbykei:1,sortwithinpartit:4,soundex:4,sourc:[1,2,3,4,5],space:[1,2,3,4],span:4,spanish:2,spark:[1,2,3,4,5],spark_partition_id:4,spark_us:1,sparkconf:[1,4],sparkcontext:[0,1,3,4,5],sparkfil:1,sparkhom:1,sparkjobinfo:1,sparksess:[2,4],sparkstageinfo:1,sparkui:1,sparkus:1,spars:[2,3],sparse1:[2,3],sparse_data:3,sparsematrix:[2,3],sparsevector:[2,3],sparsiti:2,spearman:[2,3],spearmancorr:[2,3],special:[1,2,4],specif:[1,2,3,4,5],specifi:[1,2,3,4,5],speed:[2,4],split:[1,2,3,4],splitindex:1,sql:[0,1,2],sql_ctx:4,sqlconf:4,sqlcontext:[0,2,3,4],sqlqueri:4,sqltran:2,sqltransform:2,sqltransformerpath:2,sqm:4,sqrt:[2,3,4],squar:[2,3,4],squared_dist:[2,3],srccol:4,ssc:5,sssxxx:4,stabil:2,stabl:2,stack:[2,3],stage:[1,2],stageid:1,stai:4,stamp:4,standalon:4,standard:[1,2,3,4],standardscal:[2,3],standardscalarmodel:3,standardscalermodel:[2,3],standardscalerpath:2,start:[1,2,3,4,5],start_job:1,startpo:4,startswith:4,starttim:[1,4],stat:[0,1,4],statcount:1,state:[1,4,5],statement:[2,4],statist:[2,3,4],statu:[1,4],statustrack:1,std:[2,3],stddev:4,stddev_pop:4,stddev_samp:4,stdev:[1,3],stdout:1,steinbach:[2,3],step:[1,2,3,4],stepsiz:[2,3],still:4,stkm:3,stochast:[2,3],stop:[1,2,3,4,5],stop_job:1,stopgracefulli:5,stopsparkcontext:5,stopword:2,stopwordremov:2,stopwordsremov:2,stopwordsremoverpath:2,storag:[1,2,3,4,5],storagelevel:[1,2,3,4,5],store:[2,3,4,5],str:[1,2,3,4],strata:4,strategi:2,stratifi:[1,4],stratum:4,stream:[0,1,3],streaming_queri:4,streamingcontext:[0,5],streamingkmean:3,streamingkmeansmodel:3,streaminglinearalgorithm:3,streaminglinearregressionwithsgd:3,streaminglisten:5,streaminglogisticregressionwithsgd:3,streamingqueri:4,streamingqueryexcept:4,streamingquerymanag:4,streamingqueryprogress:4,streamlib:1,streamnam:5,strength:2,strictli:[2,3],stride:4,string:[1,2,3,4,5],stringifi:3,stringinddf:2,stringindex:2,stringindexermodel:2,stringindexerpath:2,stringlengthint:4,stringlengthstr:4,stringtyp:4,strongli:1,struct1:4,struct2:4,struct:4,structfield:4,structtyp:4,structur:[2,4],stsassumerolearn:5,stsexternalid:5,stssessionnam:5,style:4,sub:3,subarrai:2,subclass:2,submit:[1,5],subnam:4,subpackag:0,subprotocol:4,subsamplingr:2,subsequ:[1,4],subset:[1,2,3,4],substr:4,substring_index:4,subtract:[1,3,4,5],subtractbykei:1,suffici:2,suffix:5,suggest:[1,2],suitabl:4,sum:[1,2,3,4],sumapprox:1,sumdistinct:4,summari:[2,3,4],sun:4,suppli:[2,3],support:[1,2,3,4],supportedfeaturesubsetstrategi:[2,3],supportedimpur:2,supportedlosstyp:2,supress:1,sure:5,surrog:2,surrogatedf:2,survei:2,surviv:2,svd:3,svd_model:3,svec:2,svm2:2,svm:[2,3],svm_model:2,svm_path:2,svmmodel:3,svmwithsgd:3,swedish:2,sym:3,symbol:2,symmetr:3,synchron:4,synonym:3,syntax:2,sys:4,system:[1,3,4,5],tabl:[2,4],table1:4,tablenam:4,take:[1,2,3,4],taken:2,takeord:1,takesampl:1,tall:3,tallskinnyqr:3,tan:4,tangent:4,tanh:4,tapia:3,target:[1,2,3,4],task:[1,2,4],taskattemptid:1,taskcontext:1,tcp:5,techniqu:[2,3],technometr:3,temp:4,temp_path:[2,3],tempdir:1,tempfil:[1,3,4],tempfile2:1,tempfile3:1,temporari:4,temporarili:2,temptablealreadyexistsexcept:4,ten:4,term:[1,2,3],termin:[2,3,4,5],termindic:2,terminolog:[2,3],termweight:2,test0:2,test1:2,test2:2,test:[1,2,3,4],test_support:4,testdf:2,testfil:1,testset:3,text:[1,2,3,4,5],text_sdf:4,textfil:[1,4],textfilestream:5,textinputformat:1,tfidf:3,than:[1,2,3,4,5],that_queri:4,thei:[1,2,3,4,5],them:[1,2,3,4,5],theoret:[2,3],therefor:3,theta:[2,3,4],thi:[1,2,3,4,5],third:4,this_queri:4,those:[1,2,3,4],thread:[1,4,5],three:[1,2,4,5],thresh:4,threshold:[2,3],through:[1,2,3,4],thrown:[2,4],thu:[1,2,3,4],tibshirani:[2,3],tie:4,tied:4,ties:4,time:[1,2,3,4,5],timecolumn:4,timeout:[1,4,5],timestamp:4,timestampformat:4,timestamptyp:4,timeunit:3,timezon:4,tinyint:4,tinyurl:3,tip:5,tmp2:1,tmp:1,tmpfile:1,tmptabl:4,to_dat:4,to_json:4,to_list:1,to_profil:1,to_replac:4,to_timestamp:4,to_upp:4,to_utc_timestamp:4,toarrai:[2,3],tobas:4,toblockmatrix:3,toboolean:2,tocoordinatematrix:3,todebugstr:[1,2,3],todegre:4,todens:[2,3],todf:[2,4],todo:2,tofloat:2,togeth:[1,2,3,4],toggl:2,toindexedrowmatrix:3,toint:2,tointern:4,tointernald:4,tojson:4,token:[2,3,4],tokenizerpath:2,tol:2,toler:[1,2,3,5],tolist:[2,3],tolistfloat:2,tolistint:2,toliststr:2,toloc:2,tolocaliter:[1,4],tolocalmatrix:3,tolowercas:2,tom:[2,4],too:[2,4],tool:5,top:[1,2,3,4],topanda:4,topic:[2,3,5],topic_nam:5,topicandpartit:5,topicconcentr:[2,3],topicdistribut:2,topicdistributioncol:2,topics_expect:3,topicsmatrix:[2,3],topolar:4,toradian:4,torowmatrix:3,tospars:[2,3],tostr:[1,2],total:[1,2,3,4],totaliter:2,totalnumnod:[2,3],tovector:2,tpr:2,tr96640:3,trace:[1,2],traceback:[1,2,3,4],track:[1,2,4,5],trade:3,trail:4,train:[2,3],trainclassifi:3,trainer:2,trainimplicit:3,trainingloglikelihood:2,trainingsummari:2,trainon:3,trainratio:2,trainregressor:3,trainvalidationsplit:2,trainvalidationsplitmodel:2,trait:3,transact:3,transform:[2,3,5],transformfunc:5,transformwith:5,translat:[1,4],transpos:3,treat:[2,3,4],tree:[0,1,2,4],treeaggreg:[1,2],treeboost:2,treeensemblemodel:3,treereduc:1,treeweight:2,tri:2,triangular:3,trick:[2,3],trigger:[1,4],trim:4,trim_horizon:5,trosset:3,truepositiver:3,trunc:4,truncat:[1,2,3,4],trust:5,truth:3,tue:4,tumbl:4,tune:0,tupl:[1,2,3,4],turkish:2,turn:[1,4],tvalu:2,tvs:2,tvsmodel:2,tweedi:2,two:[1,2,3,4,5],txt:[1,2,4],type:[0,1,2,3,5],typeconvert:2,typeerror:[2,3],typenam:4,typic:2,u612:4,udf:4,udfregistr:4,uhrbach:4,uid:2,uiweburl:1,umn:3,unbase64:4,unbias:[2,4],unbound:4,unboundedfollow:4,unboundedpreced:4,uncachet:4,uncensor:2,unchang:2,undefin:[2,3],under:[1,2,3],underflow:4,underli:[2,3,4],unhex:4,unicod:[1,5],unifi:5,uniform:3,uniformrdd:3,uniformvectorrdd:3,union:[1,4,5],unional:4,uniqu:[1,2,3,4,5],unit:[1,2,3,4],unitari:2,univari:[2,3],unix:4,unix_timestamp:[4,5],unknown:[2,3,4],unless:2,unlimit:4,unmatch:4,unnecessari:4,unpars:4,unpersist:[1,3,4],unpredict:3,unquot:4,unset:2,unsign:4,unspecifi:3,unsupport:4,until:[1,2,3,4],untiloffset:5,updat:[1,2,3,4,5],updatefunc:5,updatestatebykei:5,upon:2,upper:[2,3,4],upperbound:4,upstream:4,uri:[1,3],url:[1,4,5],usabl:1,usag:[1,2,3,4],use:[1,2,3,4,5],use_unicod:[1,4],used:[1,2,3,4,5],usedisk:1,useful:[1,2,3,4],usememori:1,useoffheap:1,user:[1,2,3,4],user_product:3,user_rec:2,usercol:2,userfactor:2,userfeatur:3,userid:3,users_for_product:3,uses:[1,2,3,4,5],using:[1,2,3,4,5],usual:2,utc:4,utf8:5,utf8_decod:5,utf:[1,4,5],util:[0,4],val:4,valid:[1,2,3,4,5],validatedata:3,validationmetr:2,valu:[1,2,3,4,5],value12:4,value1:[1,3,4],value2:[1,3,4],valueclass:1,valuecontainsnul:4,valueconvert:1,valuedecod:5,valueerror:1,valuetyp:4,var_pop:4,var_samp:4,vari:[1,3],variabl:[1,2,3],varianc:[1,2,3,4],variancecol:2,variancepow:2,variant:[2,4],variat:[2,4],variou:[1,4,5],vec:[2,3],vecassembl:2,vector:[1,2,3],vectorassembl:2,vectorassemblerpath:2,vectorindex:2,vectorindexermodel:2,vectorindexerpath:2,vectors:[2,3],vectorslic:2,vectorslicerpath:2,vectortransform:3,vectorudt:2,veri:[1,2,3,4],verifi:4,verifyschema:4,verlag:3,version:[1,2,3,4],vertex:3,via:[1,2,4],view:4,violat:[2,3],vocabs:[2,3],vocabulari:[2,3],wai:[1,2],wait:[4,5],want:[2,3,4,5],warin:3,warn:[1,2,3],watermark:4,weak:1,web:[1,4],wed:4,week:4,weekofyear:4,weibul:2,weight:[1,2,3,4],weightag:3,weightcol:2,weightedfalsepositiver:3,weightedfmeasur:3,weightedprecis:[2,3],weightedrecal:[2,3],weightedtruepositiver:3,well:[1,2,3],were:4,what:1,whatev:4,when:[1,2,3,4,5],where:[1,2,3,4,5],wherea:2,whether:[1,2,3,4],which:[1,2,3,4,5],white:[1,2],whitespac:4,who:1,whole:4,wholetextfil:1,whose:[1,2,3,4],width:[4,5],wiki:2,wikipedia:[2,3],window:[2,3,4,5],windowdur:[4,5],windows:[2,3],windowspec:4,wise:[2,3,4],wish:[1,5],withcolumn:4,withcolumnrenam:4,within:[1,2,3,4,5],withmean:[2,3],without:[1,2,3,4,5],withreplac:[1,4],withstd:[2,3],withwatermark:4,won:1,word2vec:[2,3],word2vecmodel:[2,3],word2vecpath:2,word:[2,3,4],work:[1,2,3,4],worker:[1,2,5],workshop:3,world:1,would:[1,2,3,4],wrap:4,wrapper:[2,3,4],writabl:1,write:[1,2,3,4],writer:4,writestream:4,written:[1,4,5],wrong_kei:4,wrriten:5,www:3,x_t:3,xmean:3,xml:4,xrang:1,xvarianc:3,yarn:1,year:4,yes:4,yet:[1,4],yield:1,you:[1,2,3,4,5],your:[1,4,5],yourself:5,yyi:4,yyyi:4,zero:[1,2,3,4],zerovalu:1,zip:[1,3,4],zipwithindex:1,zipwithuniqueid:1,zkquorum:5,zlib:4,zone:4,zookeep:5},titles:["Welcome to Spark Python API Docs!","pyspark package","pyspark.ml package","pyspark.mllib package","pyspark.sql module","pyspark.streaming module"],titleterms:{"class":0,"function":4,api:[0,2],classif:[2,3],cluster:[2,3],content:[1,5],context:4,core:0,distribut:3,doc:0,evalu:[2,3],featur:[2,3],flume:5,fpm:[2,3],indic:0,kafka:5,kinesi:5,linalg:[2,3],mllib:3,modul:[2,3,4,5],packag:[1,2,3],param:2,pipelin:2,pyspark:[1,2,3,4,5],python:0,random:3,recommend:[2,3],regress:[2,3],spark:0,sql:4,stat:[2,3],stream:[4,5],subpackag:1,tabl:0,tree:3,tune:2,type:4,util:[2,3],welcom:0}})
\ No newline at end of file