diff --git a/docs/ml-features.md b/docs/ml-features.md index 8b00cc652dc7a..158f3f201899c 100644 --- a/docs/ml-features.md +++ b/docs/ml-features.md @@ -63,7 +63,7 @@ the [IDF Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.IDF) for mor `Word2VecModel`. The model maps each word to a unique fixed-size vector. The `Word2VecModel` transforms each document into a vector using the average of all words in the document; this vector can then be used for as features for prediction, document similarity calculations, etc. -Please refer to the [MLlib user guide on Word2Vec](mllib-feature-extraction.html#Word2Vec) for more +Please refer to the [MLlib user guide on Word2Vec](mllib-feature-extraction.html#word2Vec) for more details. In the following code segment, we start with a set of documents, each of which is represented as a sequence of words. For each document, we transform it into a feature vector. This feature vector could then be passed to a learning algorithm. @@ -411,7 +411,7 @@ for more details on the API. Refer to the [DCT Java docs](api/java/org/apache/spark/ml/feature/DCT.html) for more details on the API. -{% include_example java/org/apache/spark/examples/ml/JavaDCTExample.java %}} +{% include_example java/org/apache/spark/examples/ml/JavaDCTExample.java %} @@ -669,7 +669,7 @@ for more details on the API. The following example demonstrates how to load a dataset in libsvm format and then normalize each row to have unit $L^2$ norm and unit $L^\infty$ norm.
-
+
Refer to the [Normalizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.Normalizer) for more details on the API. @@ -677,7 +677,7 @@ for more details on the API. {% include_example scala/org/apache/spark/examples/ml/NormalizerExample.scala %}
-
+
Refer to the [Normalizer Java docs](api/java/org/apache/spark/ml/feature/Normalizer.html) for more details on the API. @@ -685,7 +685,7 @@ for more details on the API. {% include_example java/org/apache/spark/examples/ml/JavaNormalizerExample.java %}
-
+
Refer to the [Normalizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.Normalizer) for more details on the API. @@ -709,7 +709,7 @@ Note that if the standard deviation of a feature is zero, it will return default The following example demonstrates how to load a dataset in libsvm format and then normalize each feature to have unit standard deviation.
-
+
Refer to the [StandardScaler Scala docs](api/scala/index.html#org.apache.spark.ml.feature.StandardScaler) for more details on the API. @@ -717,7 +717,7 @@ for more details on the API. {% include_example scala/org/apache/spark/examples/ml/StandardScalerExample.scala %}
-
+
Refer to the [StandardScaler Java docs](api/java/org/apache/spark/ml/feature/StandardScaler.html) for more details on the API. @@ -725,7 +725,7 @@ for more details on the API. {% include_example java/org/apache/spark/examples/ml/JavaStandardScalerExample.java %}
-
+
Refer to the [StandardScaler Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.StandardScaler) for more details on the API. @@ -788,7 +788,7 @@ More details can be found in the API docs for [Bucketizer](api/scala/index.html# The following example demonstrates how to bucketize a column of `Double`s into another index-wised column.
-
+
Refer to the [Bucketizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.Bucketizer) for more details on the API. @@ -796,7 +796,7 @@ for more details on the API. {% include_example scala/org/apache/spark/examples/ml/BucketizerExample.scala %}
-
+
Refer to the [Bucketizer Java docs](api/java/org/apache/spark/ml/feature/Bucketizer.html) for more details on the API. @@ -804,7 +804,7 @@ for more details on the API. {% include_example java/org/apache/spark/examples/ml/JavaBucketizerExample.java %}
-
+
Refer to the [Bucketizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.Bucketizer) for more details on the API. diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java index 9698cac504371..1eda1f694fc27 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java @@ -59,7 +59,7 @@ public static void main(String[] args) { DataFrame binarizedDataFrame = binarizer.transform(continuousDataFrame); DataFrame binarizedFeatures = binarizedDataFrame.select("binarized_feature"); for (Row r : binarizedFeatures.collect()) { - Double binarized_value = r.getDouble(0); + Double binarized_value = r.getDouble(0); System.out.println(binarized_value); } // $example off$ diff --git a/examples/src/main/python/ml/polynomial_expansion_example.py b/examples/src/main/python/ml/polynomial_expansion_example.py index 3d4fafd1a42e9..89f5cbe8f2f41 100644 --- a/examples/src/main/python/ml/polynomial_expansion_example.py +++ b/examples/src/main/python/ml/polynomial_expansion_example.py @@ -30,9 +30,9 @@ # $example on$ df = sqlContext\ - .createDataFrame([(Vectors.dense([-2.0, 2.3]), ), - (Vectors.dense([0.0, 0.0]), ), - (Vectors.dense([0.6, -1.1]), )], + .createDataFrame([(Vectors.dense([-2.0, 2.3]),), + (Vectors.dense([0.0, 0.0]),), + (Vectors.dense([0.6, -1.1]),)], ["features"]) px = PolynomialExpansion(degree=2, inputCol="features", outputCol="polyFeatures") polyDF = px.transform(df) diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/ElementWiseProductExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/ElementwiseProductExample.scala similarity index 100% rename from examples/src/main/scala/org/apache/spark/examples/ml/ElementWiseProductExample.scala rename to examples/src/main/scala/org/apache/spark/examples/ml/ElementwiseProductExample.scala