[SPARK-10273] Add @SInCE annotation to pyspark.mllib.feature

Duplicated the since decorator from pyspark.sql into pyspark (also tweaked to handle functions without docstrings).

Added since to methods + "versionadded::" to classes (derived from the git file history in pyspark).

Author: noelsmith <mail@noelsmith.com>

Closes #8633 from noel-smith/SPARK-10273-since-mllib-feature.

python/pyspark/mllib/feature.py

@@ -30,7 +30,7 @@
 
 from py4j.protocol import Py4JJavaError
 
-from pyspark import SparkContext
+from pyspark import SparkContext, since
 from pyspark.rdd import RDD, ignore_unicode_prefix
 from pyspark.mllib.common import callMLlibFunc, JavaModelWrapper
 from pyspark.mllib.linalg import (
@@ -84,11 +84,14 @@ class Normalizer(VectorTransformer):
     >>> nor2 = Normalizer(float("inf"))
     >>> nor2.transform(v)
     DenseVector([0.0, 0.5, 1.0])
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, p=2.0):
         assert p >= 1.0, "p should be greater than 1.0"
         self.p = float(p)
 
+    @since('1.2.0')
     def transform(self, vector):
         """
         Applies unit length normalization on a vector.
@@ -133,7 +136,11 @@ class StandardScalerModel(JavaVectorTransformer):
     .. note:: Experimental
 
     Represents a StandardScaler model that can transform vectors.
+
+    .. versionadded:: 1.2.0
     """
+
+    @since('1.2.0')
     def transform(self, vector):
         """
         Applies standardization transformation on a vector.
@@ -149,6 +156,7 @@ def transform(self, vector):
         """
         return JavaVectorTransformer.transform(self, vector)
 
+    @since('1.4.0')
     def setWithMean(self, withMean):
         """
         Setter of the boolean which decides
@@ -157,6 +165,7 @@ def setWithMean(self, withMean):
         self.call("setWithMean", withMean)
         return self
 
+    @since('1.4.0')
     def setWithStd(self, withStd):
         """
         Setter of the boolean which decides
@@ -189,13 +198,16 @@ class StandardScaler(object):
     >>> for r in result.collect(): r
     DenseVector([-0.7071, 0.7071, -0.7071])
     DenseVector([0.7071, -0.7071, 0.7071])
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, withMean=False, withStd=True):
         if not (withMean or withStd):
             warnings.warn("Both withMean and withStd are false. The model does nothing.")
         self.withMean = withMean
         self.withStd = withStd
 
+    @since('1.2.0')
     def fit(self, dataset):
         """
         Computes the mean and variance and stores as a model to be used
@@ -215,7 +227,11 @@ class ChiSqSelectorModel(JavaVectorTransformer):
     .. note:: Experimental
 
     Represents a Chi Squared selector model.
+
+    .. versionadded:: 1.4.0
     """
+
+    @since('1.4.0')
     def transform(self, vector):
         """
         Applies transformation on a vector.
@@ -245,10 +261,13 @@ class ChiSqSelector(object):
     SparseVector(1, {0: 6.0})
     >>> model.transform(DenseVector([8.0, 9.0, 5.0]))
     DenseVector([5.0])
+
+    .. versionadded:: 1.4.0
     """
     def __init__(self, numTopFeatures):
         self.numTopFeatures = int(numTopFeatures)
 
+    @since('1.4.0')
     def fit(self, data):
         """
         Returns a ChiSquared feature selector.
@@ -265,6 +284,8 @@ def fit(self, data):
 class PCAModel(JavaVectorTransformer):
     """
     Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA.
+
+    .. versionadded:: 1.5.0
     """
 
 
@@ -281,13 +302,16 @@ class PCA(object):
     1.648...
     >>> pcArray[1]
     -4.013...
+
+    .. versionadded:: 1.5.0
     """
     def __init__(self, k):
         """
         :param k: number of principal components.
         """
         self.k = int(k)
 
+    @since('1.5.0')
     def fit(self, data):
         """
         Computes a [[PCAModel]] that contains the principal components of the input vectors.
@@ -312,14 +336,18 @@ class HashingTF(object):
     >>> doc = "a a b b c d".split(" ")
     >>> htf.transform(doc)
     SparseVector(100, {...})
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, numFeatures=1 << 20):
         self.numFeatures = numFeatures
 
+    @since('1.2.0')
     def indexOf(self, term):
         """ Returns the index of the input term. """
         return hash(term) % self.numFeatures
 
+    @since('1.2.0')
     def transform(self, document):
         """
         Transforms the input document (list of terms) to term frequency
@@ -339,7 +367,10 @@ def transform(self, document):
 class IDFModel(JavaVectorTransformer):
     """
     Represents an IDF model that can transform term frequency vectors.
+
+    .. versionadded:: 1.2.0
     """
+    @since('1.2.0')
     def transform(self, x):
         """
         Transforms term frequency (TF) vectors to TF-IDF vectors.
@@ -358,6 +389,7 @@ def transform(self, x):
         """
         return JavaVectorTransformer.transform(self, x)
 
+    @since('1.4.0')
     def idf(self):
         """
         Returns the current IDF vector.
@@ -401,10 +433,13 @@ class IDF(object):
     DenseVector([0.0, 0.0, 1.3863, 0.863])
     >>> model.transform(Vectors.sparse(n, (1, 3), (1.0, 2.0)))
     SparseVector(4, {1: 0.0, 3: 0.5754})
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, minDocFreq=0):
         self.minDocFreq = minDocFreq
 
+    @since('1.2.0')
     def fit(self, dataset):
         """
         Computes the inverse document frequency.
@@ -420,7 +455,10 @@ def fit(self, dataset):
 class Word2VecModel(JavaVectorTransformer, JavaSaveable, JavaLoader):
     """
     class for Word2Vec model
+
+    .. versionadded:: 1.2.0
     """
+    @since('1.2.0')
     def transform(self, word):
         """
         Transforms a word to its vector representation
@@ -435,6 +473,7 @@ def transform(self, word):
         except Py4JJavaError:
             raise ValueError("%s not found" % word)
 
+    @since('1.2.0')
     def findSynonyms(self, word, num):
         """
         Find synonyms of a word
@@ -450,14 +489,19 @@ def findSynonyms(self, word, num):
         words, similarity = self.call("findSynonyms", word, num)
         return zip(words, similarity)
 
+    @since('1.4.0')
     def getVectors(self):
         """
         Returns a map of words to their vector representations.
         """
         return self.call("getVectors")
 
     @classmethod
+    @since('1.5.0')
     def load(cls, sc, path):
+        """
+        Load a model from the given path.
+        """
         jmodel = sc._jvm.org.apache.spark.mllib.feature \
             .Word2VecModel.load(sc._jsc.sc(), path)
         return Word2VecModel(jmodel)
@@ -507,6 +551,8 @@ class Word2Vec(object):
     ...     rmtree(path)
     ... except OSError:
     ...     pass
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self):
         """
@@ -519,20 +565,23 @@ def __init__(self):
         self.seed = random.randint(0, sys.maxsize)
         self.minCount = 5
 
+    @since('1.2.0')
     def setVectorSize(self, vectorSize):
         """
         Sets vector size (default: 100).
         """
         self.vectorSize = vectorSize
         return self
 
+    @since('1.2.0')
     def setLearningRate(self, learningRate):
         """
         Sets initial learning rate (default: 0.025).
         """
         self.learningRate = learningRate
         return self
 
+    @since('1.2.0')
     def setNumPartitions(self, numPartitions):
         """
         Sets number of partitions (default: 1). Use a small number for
@@ -541,6 +590,7 @@ def setNumPartitions(self, numPartitions):
         self.numPartitions = numPartitions
         return self
 
+    @since('1.2.0')
     def setNumIterations(self, numIterations):
         """
         Sets number of iterations (default: 1), which should be smaller
@@ -549,13 +599,15 @@ def setNumIterations(self, numIterations):
         self.numIterations = numIterations
         return self
 
+    @since('1.2.0')
     def setSeed(self, seed):
         """
         Sets random seed.
         """
         self.seed = seed
         return self
 
+    @since('1.4.0')
     def setMinCount(self, minCount):
         """
         Sets minCount, the minimum number of times a token must appear
@@ -564,6 +616,7 @@ def setMinCount(self, minCount):
         self.minCount = minCount
         return self
 
+    @since('1.2.0')
     def fit(self, data):
         """
         Computes the vector representation of each word in vocabulary.
@@ -596,10 +649,13 @@ class ElementwiseProduct(VectorTransformer):
     >>> rdd = sc.parallelize([a, b])
     >>> eprod.transform(rdd).collect()
     [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])]
+
+    .. versionadded:: 1.5.0
     """
     def __init__(self, scalingVector):
         self.scalingVector = _convert_to_vector(scalingVector)
 
+    @since('1.5.0')
     def transform(self, vector):
         """
         Computes the Hadamard product of the vector.