From 78209b0ccaf3f22b5e2345dfb2b98edfdb746819 Mon Sep 17 00:00:00 2001 From: somideshmukh Date: Mon, 7 Dec 2015 23:26:34 -0800 Subject: [PATCH] [SPARK-11551][DOC][EXAMPLE] Replace example code in ml-features.md using include_example Made new patch contaning only markdown examples moved to exmaple/folder. Ony three java code were not shfted since they were contaning compliation error ,these classes are 1)StandardScale 2)NormalizerExample 3)VectorIndexer Author: Xusen Yin Author: somideshmukh Closes #10002 from somideshmukh/SomilBranch1.33. --- docs/ml-features.md | 1109 +---------------- .../examples/ml/JavaBinarizerExample.java | 68 + .../examples/ml/JavaBucketizerExample.java | 70 ++ .../spark/examples/ml/JavaDCTExample.java | 65 + .../ml/JavaElementwiseProductExample.java | 75 ++ .../examples/ml/JavaMinMaxScalerExample.java | 50 + .../spark/examples/ml/JavaNGramExample.java | 71 ++ .../examples/ml/JavaNormalizerExample.java | 52 + .../examples/ml/JavaOneHotEncoderExample.java | 77 ++ .../spark/examples/ml/JavaPCAExample.java | 71 ++ .../ml/JavaPolynomialExpansionExample.java | 71 ++ .../examples/ml/JavaRFormulaExample.java | 69 + .../ml/JavaStandardScalerExample.java | 53 + .../ml/JavaStopWordsRemoverExample.java | 65 + .../examples/ml/JavaStringIndexerExample.java | 66 + .../examples/ml/JavaTokenizerExample.java | 75 ++ .../ml/JavaVectorAssemblerExample.java | 67 + .../examples/ml/JavaVectorIndexerExample.java | 60 + .../examples/ml/JavaVectorSlicerExample.java | 73 ++ .../src/main/python/ml/binarizer_example.py | 43 + .../src/main/python/ml/bucketizer_example.py | 42 + .../python/ml/elementwise_product_example.py | 39 + examples/src/main/python/ml/n_gram_example.py | 42 + .../src/main/python/ml/normalizer_example.py | 41 + .../main/python/ml/onehot_encoder_example.py | 47 + examples/src/main/python/ml/pca_example.py | 42 + .../python/ml/polynomial_expansion_example.py | 43 + .../src/main/python/ml/rformula_example.py | 44 + .../main/python/ml/standard_scaler_example.py | 42 + .../python/ml/stopwords_remover_example.py | 40 + .../main/python/ml/string_indexer_example.py | 39 + .../src/main/python/ml/tokenizer_example.py | 44 + .../python/ml/vector_assembler_example.py | 42 + .../main/python/ml/vector_indexer_example.py | 39 + .../spark/examples/ml/BinarizerExample.scala | 48 + .../spark/examples/ml/BucketizerExample.scala | 51 + .../apache/spark/examples/ml/DCTExample.scala | 54 + .../ml/ElementWiseProductExample.scala | 53 + .../examples/ml/MinMaxScalerExample.scala | 49 + .../spark/examples/ml/NGramExample.scala | 47 + .../spark/examples/ml/NormalizerExample.scala | 50 + .../examples/ml/OneHotEncoderExample.scala | 58 + .../apache/spark/examples/ml/PCAExample.scala | 54 + .../ml/PolynomialExpansionExample.scala | 53 + .../spark/examples/ml/RFormulaExample.scala | 49 + .../examples/ml/StandardScalerExample.scala | 51 + .../examples/ml/StopWordsRemoverExample.scala | 48 + .../examples/ml/StringIndexerExample.scala | 49 + .../spark/examples/ml/TokenizerExample.scala | 54 + .../examples/ml/VectorAssemblerExample.scala | 49 + .../examples/ml/VectorIndexerExample.scala | 53 + .../examples/ml/VectorSlicerExample.scala | 58 + 52 files changed, 2806 insertions(+), 1058 deletions(-) create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java create mode 100644 examples/src/main/python/ml/binarizer_example.py create mode 100644 examples/src/main/python/ml/bucketizer_example.py create mode 100644 examples/src/main/python/ml/elementwise_product_example.py create mode 100644 examples/src/main/python/ml/n_gram_example.py create mode 100644 examples/src/main/python/ml/normalizer_example.py create mode 100644 examples/src/main/python/ml/onehot_encoder_example.py create mode 100644 examples/src/main/python/ml/pca_example.py create mode 100644 examples/src/main/python/ml/polynomial_expansion_example.py create mode 100644 examples/src/main/python/ml/rformula_example.py create mode 100644 examples/src/main/python/ml/standard_scaler_example.py create mode 100644 examples/src/main/python/ml/stopwords_remover_example.py create mode 100644 examples/src/main/python/ml/string_indexer_example.py create mode 100644 examples/src/main/python/ml/tokenizer_example.py create mode 100644 examples/src/main/python/ml/vector_assembler_example.py create mode 100644 examples/src/main/python/ml/vector_indexer_example.py create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/BucketizerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/DCTExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/ElementWiseProductExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/NGramExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/OneHotEncoderExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/RFormulaExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/StandardScalerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/StopWordsRemoverExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/StringIndexerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/TokenizerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/VectorAssemblerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/VectorIndexerExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/VectorSlicerExample.scala diff --git a/docs/ml-features.md b/docs/ml-features.md index b499d6ec3b90e..5105a948fec8e 100644 --- a/docs/ml-features.md +++ b/docs/ml-features.md @@ -170,25 +170,7 @@ Refer to the [Tokenizer Scala docs](api/scala/index.html#org.apache.spark.ml.fea and the [RegexTokenizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.Tokenizer) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.{Tokenizer, RegexTokenizer} - -val sentenceDataFrame = sqlContext.createDataFrame(Seq( - (0, "Hi I heard about Spark"), - (1, "I wish Java could use case classes"), - (2, "Logistic,regression,models,are,neat") -)).toDF("label", "sentence") -val tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words") -val regexTokenizer = new RegexTokenizer() - .setInputCol("sentence") - .setOutputCol("words") - .setPattern("\\W") // alternatively .setPattern("\\w+").setGaps(false) - -val tokenized = tokenizer.transform(sentenceDataFrame) -tokenized.select("words", "label").take(3).foreach(println) -val regexTokenized = regexTokenizer.transform(sentenceDataFrame) -regexTokenized.select("words", "label").take(3).foreach(println) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/TokenizerExample.scala %}
@@ -197,44 +179,7 @@ Refer to the [Tokenizer Java docs](api/java/org/apache/spark/ml/feature/Tokenize and the [RegexTokenizer Java docs](api/java/org/apache/spark/ml/feature/RegexTokenizer.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.RegexTokenizer; -import org.apache.spark.ml.feature.Tokenizer; -import org.apache.spark.mllib.linalg.Vector; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaRDD jrdd = jsc.parallelize(Arrays.asList( - RowFactory.create(0, "Hi I heard about Spark"), - RowFactory.create(1, "I wish Java could use case classes"), - RowFactory.create(2, "Logistic,regression,models,are,neat") -)); -StructType schema = new StructType(new StructField[]{ - new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), - new StructField("sentence", DataTypes.StringType, false, Metadata.empty()) -}); -DataFrame sentenceDataFrame = sqlContext.createDataFrame(jrdd, schema); -Tokenizer tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words"); -DataFrame wordsDataFrame = tokenizer.transform(sentenceDataFrame); -for (Row r : wordsDataFrame.select("words", "label").take(3)) { - java.util.List words = r.getList(0); - for (String word : words) System.out.print(word + " "); - System.out.println(); -} - -RegexTokenizer regexTokenizer = new RegexTokenizer() - .setInputCol("sentence") - .setOutputCol("words") - .setPattern("\\W"); // alternatively .setPattern("\\w+").setGaps(false); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaTokenizerExample.java %}
@@ -243,21 +188,7 @@ Refer to the [Tokenizer Python docs](api/python/pyspark.ml.html#pyspark.ml.featu the the [RegexTokenizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.RegexTokenizer) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import Tokenizer, RegexTokenizer - -sentenceDataFrame = sqlContext.createDataFrame([ - (0, "Hi I heard about Spark"), - (1, "I wish Java could use case classes"), - (2, "Logistic,regression,models,are,neat") -], ["label", "sentence"]) -tokenizer = Tokenizer(inputCol="sentence", outputCol="words") -wordsDataFrame = tokenizer.transform(sentenceDataFrame) -for words_label in wordsDataFrame.select("words", "label").take(3): - print(words_label) -regexTokenizer = RegexTokenizer(inputCol="sentence", outputCol="words", pattern="\\W") -# alternatively, pattern="\\w+", gaps(False) -{% endhighlight %} +{% include_example python/ml/tokenizer_example.py %}
@@ -306,19 +237,7 @@ filtered out. Refer to the [StopWordsRemover Scala docs](api/scala/index.html#org.apache.spark.ml.feature.StopWordsRemover) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.StopWordsRemover - -val remover = new StopWordsRemover() - .setInputCol("raw") - .setOutputCol("filtered") -val dataSet = sqlContext.createDataFrame(Seq( - (0, Seq("I", "saw", "the", "red", "baloon")), - (1, Seq("Mary", "had", "a", "little", "lamb")) -)).toDF("id", "raw") - -remover.transform(dataSet).show() -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/StopWordsRemoverExample.scala %}
@@ -326,34 +245,7 @@ remover.transform(dataSet).show() Refer to the [StopWordsRemover Java docs](api/java/org/apache/spark/ml/feature/StopWordsRemover.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.StopWordsRemover; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -StopWordsRemover remover = new StopWordsRemover() - .setInputCol("raw") - .setOutputCol("filtered"); - -JavaRDD rdd = jsc.parallelize(Arrays.asList( - RowFactory.create(Arrays.asList("I", "saw", "the", "red", "baloon")), - RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb")) -)); -StructType schema = new StructType(new StructField[] { - new StructField("raw", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty()) -}); -DataFrame dataset = jsql.createDataFrame(rdd, schema); - -remover.transform(dataset).show(); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java %}
@@ -361,17 +253,7 @@ remover.transform(dataset).show(); Refer to the [StopWordsRemover Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.StopWordsRemover) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import StopWordsRemover - -sentenceData = sqlContext.createDataFrame([ - (0, ["I", "saw", "the", "red", "baloon"]), - (1, ["Mary", "had", "a", "little", "lamb"]) -], ["label", "raw"]) - -remover = StopWordsRemover(inputCol="raw", outputCol="filtered") -remover.transform(sentenceData).show(truncate=False) -{% endhighlight %} +{% include_example python/ml/stopwords_remover_example.py %}
@@ -388,19 +270,7 @@ An [n-gram](https://en.wikipedia.org/wiki/N-gram) is a sequence of $n$ tokens (t Refer to the [NGram Scala docs](api/scala/index.html#org.apache.spark.ml.feature.NGram) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.NGram - -val wordDataFrame = sqlContext.createDataFrame(Seq( - (0, Array("Hi", "I", "heard", "about", "Spark")), - (1, Array("I", "wish", "Java", "could", "use", "case", "classes")), - (2, Array("Logistic", "regression", "models", "are", "neat")) -)).toDF("label", "words") - -val ngram = new NGram().setInputCol("words").setOutputCol("ngrams") -val ngramDataFrame = ngram.transform(wordDataFrame) -ngramDataFrame.take(3).map(_.getAs[Stream[String]]("ngrams").toList).foreach(println) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/NGramExample.scala %}
@@ -408,38 +278,7 @@ ngramDataFrame.take(3).map(_.getAs[Stream[String]]("ngrams").toList).foreach(pri Refer to the [NGram Java docs](api/java/org/apache/spark/ml/feature/NGram.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.NGram; -import org.apache.spark.mllib.linalg.Vector; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaRDD jrdd = jsc.parallelize(Arrays.asList( - RowFactory.create(0.0, Arrays.asList("Hi", "I", "heard", "about", "Spark")), - RowFactory.create(1.0, Arrays.asList("I", "wish", "Java", "could", "use", "case", "classes")), - RowFactory.create(2.0, Arrays.asList("Logistic", "regression", "models", "are", "neat")) -)); -StructType schema = new StructType(new StructField[]{ - new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), - new StructField("words", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty()) -}); -DataFrame wordDataFrame = sqlContext.createDataFrame(jrdd, schema); -NGram ngramTransformer = new NGram().setInputCol("words").setOutputCol("ngrams"); -DataFrame ngramDataFrame = ngramTransformer.transform(wordDataFrame); -for (Row r : ngramDataFrame.select("ngrams", "label").take(3)) { - java.util.List ngrams = r.getList(0); - for (String ngram : ngrams) System.out.print(ngram + " --- "); - System.out.println(); -} -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaNGramExample.java %}
@@ -447,19 +286,7 @@ for (Row r : ngramDataFrame.select("ngrams", "label").take(3)) { Refer to the [NGram Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.NGram) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import NGram - -wordDataFrame = sqlContext.createDataFrame([ - (0, ["Hi", "I", "heard", "about", "Spark"]), - (1, ["I", "wish", "Java", "could", "use", "case", "classes"]), - (2, ["Logistic", "regression", "models", "are", "neat"]) -], ["label", "words"]) -ngram = NGram(inputCol="words", outputCol="ngrams") -ngramDataFrame = ngram.transform(wordDataFrame) -for ngrams_label in ngramDataFrame.select("ngrams", "label").take(3): - print(ngrams_label) -{% endhighlight %} +{% include_example python/ml/n_gram_example.py %}
@@ -476,26 +303,7 @@ Binarization is the process of thresholding numerical features to binary (0/1) f Refer to the [Binarizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.Binarizer) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.Binarizer -import org.apache.spark.sql.DataFrame - -val data = Array( - (0, 0.1), - (1, 0.8), - (2, 0.2) -) -val dataFrame: DataFrame = sqlContext.createDataFrame(data).toDF("label", "feature") - -val binarizer: Binarizer = new Binarizer() - .setInputCol("feature") - .setOutputCol("binarized_feature") - .setThreshold(0.5) - -val binarizedDataFrame = binarizer.transform(dataFrame) -val binarizedFeatures = binarizedDataFrame.select("binarized_feature") -binarizedFeatures.collect().foreach(println) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/BinarizerExample.scala %}
@@ -503,40 +311,7 @@ binarizedFeatures.collect().foreach(println) Refer to the [Binarizer Java docs](api/java/org/apache/spark/ml/feature/Binarizer.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.Binarizer; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaRDD jrdd = jsc.parallelize(Arrays.asList( - RowFactory.create(0, 0.1), - RowFactory.create(1, 0.8), - RowFactory.create(2, 0.2) -)); -StructType schema = new StructType(new StructField[]{ - new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), - new StructField("feature", DataTypes.DoubleType, false, Metadata.empty()) -}); -DataFrame continuousDataFrame = jsql.createDataFrame(jrdd, schema); -Binarizer binarizer = new Binarizer() - .setInputCol("feature") - .setOutputCol("binarized_feature") - .setThreshold(0.5); -DataFrame binarizedDataFrame = binarizer.transform(continuousDataFrame); -DataFrame binarizedFeatures = binarizedDataFrame.select("binarized_feature"); -for (Row r : binarizedFeatures.collect()) { - Double binarized_value = r.getDouble(0); - System.out.println(binarized_value); -} -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaBinarizerExample.java %}
@@ -544,20 +319,7 @@ for (Row r : binarizedFeatures.collect()) { Refer to the [Binarizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.Binarizer) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import Binarizer - -continuousDataFrame = sqlContext.createDataFrame([ - (0, 0.1), - (1, 0.8), - (2, 0.2) -], ["label", "feature"]) -binarizer = Binarizer(threshold=0.5, inputCol="feature", outputCol="binarized_feature") -binarizedDataFrame = binarizer.transform(continuousDataFrame) -binarizedFeatures = binarizedDataFrame.select("binarized_feature") -for binarized_feature, in binarizedFeatures.collect(): - print(binarized_feature) -{% endhighlight %} +{% include_example python/ml/binarizer_example.py %}
@@ -571,25 +333,7 @@ for binarized_feature, in binarizedFeatures.collect(): Refer to the [PCA Scala docs](api/scala/index.html#org.apache.spark.ml.feature.PCA) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.PCA -import org.apache.spark.mllib.linalg.Vectors - -val data = Array( - Vectors.sparse(5, Seq((1, 1.0), (3, 7.0))), - Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0), - Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0) -) -val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") -val pca = new PCA() - .setInputCol("features") - .setOutputCol("pcaFeatures") - .setK(3) - .fit(df) -val pcaDF = pca.transform(df) -val result = pcaDF.select("pcaFeatures") -result.show() -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/PCAExample.scala %}
@@ -597,42 +341,7 @@ result.show() Refer to the [PCA Java docs](api/java/org/apache/spark/ml/feature/PCA.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.ml.feature.PCA -import org.apache.spark.ml.feature.PCAModel -import org.apache.spark.mllib.linalg.VectorUDT; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.SQLContext; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaSparkContext jsc = ... -SQLContext jsql = ... -JavaRDD data = jsc.parallelize(Arrays.asList( - RowFactory.create(Vectors.sparse(5, new int[]{1, 3}, new double[]{1.0, 7.0})), - RowFactory.create(Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0)), - RowFactory.create(Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)) -)); -StructType schema = new StructType(new StructField[] { - new StructField("features", new VectorUDT(), false, Metadata.empty()), -}); -DataFrame df = jsql.createDataFrame(data, schema); -PCAModel pca = new PCA() - .setInputCol("features") - .setOutputCol("pcaFeatures") - .setK(3) - .fit(df); -DataFrame result = pca.transform(df).select("pcaFeatures"); -result.show(); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaPCAExample.java %}
@@ -640,19 +349,7 @@ result.show(); Refer to the [PCA Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.PCA) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import PCA -from pyspark.mllib.linalg import Vectors - -data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),), - (Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]),), - (Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0]),)] -df = sqlContext.createDataFrame(data,["features"]) -pca = PCA(k=3, inputCol="features", outputCol="pcaFeatures") -model = pca.fit(df) -result = model.transform(df).select("pcaFeatures") -result.show(truncate=False) -{% endhighlight %} +{% include_example python/ml/pca_example.py %}
@@ -666,23 +363,7 @@ result.show(truncate=False) Refer to the [PolynomialExpansion Scala docs](api/scala/index.html#org.apache.spark.ml.feature.PolynomialExpansion) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.PolynomialExpansion -import org.apache.spark.mllib.linalg.Vectors - -val data = Array( - Vectors.dense(-2.0, 2.3), - Vectors.dense(0.0, 0.0), - Vectors.dense(0.6, -1.1) -) -val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") -val polynomialExpansion = new PolynomialExpansion() - .setInputCol("features") - .setOutputCol("polyFeatures") - .setDegree(3) -val polyDF = polynomialExpansion.transform(df) -polyDF.select("polyFeatures").take(3).foreach(println) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala %}
@@ -690,43 +371,7 @@ polyDF.select("polyFeatures").take(3).foreach(println) Refer to the [PolynomialExpansion Java docs](api/java/org/apache/spark/ml/feature/PolynomialExpansion.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.mllib.linalg.Vector; -import org.apache.spark.mllib.linalg.VectorUDT; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.SQLContext; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaSparkContext jsc = ... -SQLContext jsql = ... -PolynomialExpansion polyExpansion = new PolynomialExpansion() - .setInputCol("features") - .setOutputCol("polyFeatures") - .setDegree(3); -JavaRDD data = jsc.parallelize(Arrays.asList( - RowFactory.create(Vectors.dense(-2.0, 2.3)), - RowFactory.create(Vectors.dense(0.0, 0.0)), - RowFactory.create(Vectors.dense(0.6, -1.1)) -)); -StructType schema = new StructType(new StructField[] { - new StructField("features", new VectorUDT(), false, Metadata.empty()), -}); -DataFrame df = jsql.createDataFrame(data, schema); -DataFrame polyDF = polyExpansion.transform(df); -Row[] row = polyDF.select("polyFeatures").take(3); -for (Row r : row) { - System.out.println(r.get(0)); -} -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java %}
@@ -734,20 +379,7 @@ for (Row r : row) { Refer to the [PolynomialExpansion Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.PolynomialExpansion) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import PolynomialExpansion -from pyspark.mllib.linalg import Vectors - -df = sqlContext.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) -for expanded in polyDF.select("polyFeatures").take(3): - print(expanded) -{% endhighlight %} +{% include_example python/ml/polynomial_expansion_example.py %}
@@ -771,22 +403,7 @@ $0$th DCT coefficient and _not_ the $N/2$th). Refer to the [DCT Scala docs](api/scala/index.html#org.apache.spark.ml.feature.DCT) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.DCT -import org.apache.spark.mllib.linalg.Vectors - -val data = Seq( - Vectors.dense(0.0, 1.0, -2.0, 3.0), - Vectors.dense(-1.0, 2.0, 4.0, -7.0), - Vectors.dense(14.0, -2.0, -5.0, 1.0)) -val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") -val dct = new DCT() - .setInputCol("features") - .setOutputCol("featuresDCT") - .setInverse(false) -val dctDf = dct.transform(df) -dctDf.select("featuresDCT").show(3) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/DCTExample.scala %}
@@ -794,39 +411,7 @@ dctDf.select("featuresDCT").show(3) Refer to the [DCT Java docs](api/java/org/apache/spark/ml/feature/DCT.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.ml.feature.DCT; -import org.apache.spark.mllib.linalg.Vector; -import org.apache.spark.mllib.linalg.VectorUDT; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.SQLContext; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaRDD data = jsc.parallelize(Arrays.asList( - RowFactory.create(Vectors.dense(0.0, 1.0, -2.0, 3.0)), - RowFactory.create(Vectors.dense(-1.0, 2.0, 4.0, -7.0)), - RowFactory.create(Vectors.dense(14.0, -2.0, -5.0, 1.0)) -)); -StructType schema = new StructType(new StructField[] { - new StructField("features", new VectorUDT(), false, Metadata.empty()), -}); -DataFrame df = jsql.createDataFrame(data, schema); -DCT dct = new DCT() - .setInputCol("features") - .setOutputCol("featuresDCT") - .setInverse(false); -DataFrame dctDf = dct.transform(df); -dctDf.select("featuresDCT").show(3); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaDCTExample.java %}}
@@ -881,18 +466,7 @@ index `2`. Refer to the [StringIndexer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.StringIndexer) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.StringIndexer - -val df = sqlContext.createDataFrame( - Seq((0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")) -).toDF("id", "category") -val indexer = new StringIndexer() - .setInputCol("category") - .setOutputCol("categoryIndex") -val indexed = indexer.fit(df).transform(df) -indexed.show() -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/StringIndexerExample.scala %}
@@ -900,37 +474,7 @@ indexed.show() Refer to the [StringIndexer Java docs](api/java/org/apache/spark/ml/feature/StringIndexer.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.StringIndexer; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; -import static org.apache.spark.sql.types.DataTypes.*; - -JavaRDD jrdd = jsc.parallelize(Arrays.asList( - RowFactory.create(0, "a"), - RowFactory.create(1, "b"), - RowFactory.create(2, "c"), - RowFactory.create(3, "a"), - RowFactory.create(4, "a"), - RowFactory.create(5, "c") -)); -StructType schema = new StructType(new StructField[] { - createStructField("id", DoubleType, false), - createStructField("category", StringType, false) -}); -DataFrame df = sqlContext.createDataFrame(jrdd, schema); -StringIndexer indexer = new StringIndexer() - .setInputCol("category") - .setOutputCol("categoryIndex"); -DataFrame indexed = indexer.fit(df).transform(df); -indexed.show(); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaStringIndexerExample.java %}
@@ -938,16 +482,7 @@ indexed.show(); Refer to the [StringIndexer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.StringIndexer) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import StringIndexer - -df = sqlContext.createDataFrame( - [(0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")], - ["id", "category"]) -indexer = StringIndexer(inputCol="category", outputCol="categoryIndex") -indexed = indexer.fit(df).transform(df) -indexed.show() -{% endhighlight %} +{% include_example python/ml/string_indexer_example.py %}
@@ -961,29 +496,7 @@ indexed.show() Refer to the [OneHotEncoder Scala docs](api/scala/index.html#org.apache.spark.ml.feature.OneHotEncoder) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.{OneHotEncoder, StringIndexer} - -val df = sqlContext.createDataFrame(Seq( - (0, "a"), - (1, "b"), - (2, "c"), - (3, "a"), - (4, "a"), - (5, "c") -)).toDF("id", "category") - -val indexer = new StringIndexer() - .setInputCol("category") - .setOutputCol("categoryIndex") - .fit(df) -val indexed = indexer.transform(df) - -val encoder = new OneHotEncoder().setInputCol("categoryIndex"). - setOutputCol("categoryVec") -val encoded = encoder.transform(indexed) -encoded.select("id", "categoryVec").foreach(println) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/OneHotEncoderExample.scala %}
@@ -991,45 +504,7 @@ encoded.select("id", "categoryVec").foreach(println) Refer to the [OneHotEncoder Java docs](api/java/org/apache/spark/ml/feature/OneHotEncoder.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.OneHotEncoder; -import org.apache.spark.ml.feature.StringIndexer; -import org.apache.spark.ml.feature.StringIndexerModel; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -JavaRDD jrdd = jsc.parallelize(Arrays.asList( - RowFactory.create(0, "a"), - RowFactory.create(1, "b"), - RowFactory.create(2, "c"), - RowFactory.create(3, "a"), - RowFactory.create(4, "a"), - RowFactory.create(5, "c") -)); -StructType schema = new StructType(new StructField[]{ - new StructField("id", DataTypes.DoubleType, false, Metadata.empty()), - new StructField("category", DataTypes.StringType, false, Metadata.empty()) -}); -DataFrame df = sqlContext.createDataFrame(jrdd, schema); -StringIndexerModel indexer = new StringIndexer() - .setInputCol("category") - .setOutputCol("categoryIndex") - .fit(df); -DataFrame indexed = indexer.transform(df); - -OneHotEncoder encoder = new OneHotEncoder() - .setInputCol("categoryIndex") - .setOutputCol("categoryVec"); -DataFrame encoded = encoder.transform(indexed); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java %}
@@ -1037,24 +512,7 @@ DataFrame encoded = encoder.transform(indexed); Refer to the [OneHotEncoder Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.OneHotEncoder) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import OneHotEncoder, StringIndexer - -df = sqlContext.createDataFrame([ - (0, "a"), - (1, "b"), - (2, "c"), - (3, "a"), - (4, "a"), - (5, "c") -], ["id", "category"]) - -stringIndexer = StringIndexer(inputCol="category", outputCol="categoryIndex") -model = stringIndexer.fit(df) -indexed = model.transform(df) -encoder = OneHotEncoder(includeFirst=False, inputCol="categoryIndex", outputCol="categoryVec") -encoded = encoder.transform(indexed) -{% endhighlight %} +{% include_example python/ml/onehot_encoder_example.py %}
@@ -1078,23 +536,7 @@ In the example below, we read in a dataset of labeled points and then use `Vecto Refer to the [VectorIndexer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.VectorIndexer) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.VectorIndexer - -val data = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") -val indexer = new VectorIndexer() - .setInputCol("features") - .setOutputCol("indexed") - .setMaxCategories(10) -val indexerModel = indexer.fit(data) -val categoricalFeatures: Set[Int] = indexerModel.categoryMaps.keys.toSet -println(s"Chose ${categoricalFeatures.size} categorical features: " + - categoricalFeatures.mkString(", ")) - -// Create new column "indexed" with categorical values transformed to indices -val indexedData = indexerModel.transform(data) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/VectorIndexerExample.scala %}
@@ -1102,30 +544,7 @@ val indexedData = indexerModel.transform(data) Refer to the [VectorIndexer Java docs](api/java/org/apache/spark/ml/feature/VectorIndexer.html) for more details on the API. -{% highlight java %} -import java.util.Map; - -import org.apache.spark.ml.feature.VectorIndexer; -import org.apache.spark.ml.feature.VectorIndexerModel; -import org.apache.spark.sql.DataFrame; - -DataFrame data = sqlContext.read().format("libsvm") - .load("data/mllib/sample_libsvm_data.txt"); -VectorIndexer indexer = new VectorIndexer() - .setInputCol("features") - .setOutputCol("indexed") - .setMaxCategories(10); -VectorIndexerModel indexerModel = indexer.fit(data); -Map> categoryMaps = indexerModel.javaCategoryMaps(); -System.out.print("Chose " + categoryMaps.size() + "categorical features:"); -for (Integer feature : categoryMaps.keySet()) { - System.out.print(" " + feature); -} -System.out.println(); - -// Create new column "indexed" with categorical values transformed to indices -DataFrame indexedData = indexerModel.transform(data); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java %}
@@ -1133,17 +552,7 @@ DataFrame indexedData = indexerModel.transform(data); Refer to the [VectorIndexer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.VectorIndexer) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import VectorIndexer - -data = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") -indexer = VectorIndexer(inputCol="features", outputCol="indexed", maxCategories=10) -indexerModel = indexer.fit(data) - -# Create new column "indexed" with categorical values transformed to indices -indexedData = indexerModel.transform(data) -{% endhighlight %} +{% include_example python/ml/vector_indexer_example.py %}
@@ -1160,22 +569,7 @@ The following example demonstrates how to load a dataset in libsvm format and th Refer to the [Normalizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.Normalizer) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.Normalizer - -val dataFrame = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") - -// Normalize each Vector using $L^1$ norm. -val normalizer = new Normalizer() - .setInputCol("features") - .setOutputCol("normFeatures") - .setP(1.0) -val l1NormData = normalizer.transform(dataFrame) - -// Normalize each Vector using $L^\infty$ norm. -val lInfNormData = normalizer.transform(dataFrame, normalizer.p -> Double.PositiveInfinity) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/NormalizerExample.scala %}
@@ -1183,24 +577,7 @@ val lInfNormData = normalizer.transform(dataFrame, normalizer.p -> Double.Positi Refer to the [Normalizer Java docs](api/java/org/apache/spark/ml/feature/Normalizer.html) for more details on the API. -{% highlight java %} -import org.apache.spark.ml.feature.Normalizer; -import org.apache.spark.sql.DataFrame; - -DataFrame dataFrame = sqlContext.read().format("libsvm") - .load("data/mllib/sample_libsvm_data.txt"); - -// Normalize each Vector using $L^1$ norm. -Normalizer normalizer = new Normalizer() - .setInputCol("features") - .setOutputCol("normFeatures") - .setP(1.0); -DataFrame l1NormData = normalizer.transform(dataFrame); - -// Normalize each Vector using $L^\infty$ norm. -DataFrame lInfNormData = - normalizer.transform(dataFrame, normalizer.p().w(Double.POSITIVE_INFINITY)); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaNormalizerExample.java %}
@@ -1208,19 +585,7 @@ DataFrame lInfNormData = Refer to the [Normalizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.Normalizer) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import Normalizer - -dataFrame = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") - -# Normalize each Vector using $L^1$ norm. -normalizer = Normalizer(inputCol="features", outputCol="normFeatures", p=1.0) -l1NormData = normalizer.transform(dataFrame) - -# Normalize each Vector using $L^\infty$ norm. -lInfNormData = normalizer.transform(dataFrame, {normalizer.p: float("inf")}) -{% endhighlight %} +{% include_example python/ml/normalizer_example.py %}
@@ -1244,23 +609,7 @@ The following example demonstrates how to load a dataset in libsvm format and th Refer to the [StandardScaler Scala docs](api/scala/index.html#org.apache.spark.ml.feature.StandardScaler) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.StandardScaler - -val dataFrame = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") -val scaler = new StandardScaler() - .setInputCol("features") - .setOutputCol("scaledFeatures") - .setWithStd(true) - .setWithMean(false) - -// Compute summary statistics by fitting the StandardScaler -val scalerModel = scaler.fit(dataFrame) - -// Normalize each feature to have unit standard deviation. -val scaledData = scalerModel.transform(dataFrame) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/StandardScalerExample.scala %}
@@ -1268,25 +617,7 @@ val scaledData = scalerModel.transform(dataFrame) Refer to the [StandardScaler Java docs](api/java/org/apache/spark/ml/feature/StandardScaler.html) for more details on the API. -{% highlight java %} -import org.apache.spark.ml.feature.StandardScaler; -import org.apache.spark.ml.feature.StandardScalerModel; -import org.apache.spark.sql.DataFrame; - -DataFrame dataFrame = sqlContext.read().format("libsvm") - .load("data/mllib/sample_libsvm_data.txt"); -StandardScaler scaler = new StandardScaler() - .setInputCol("features") - .setOutputCol("scaledFeatures") - .setWithStd(true) - .setWithMean(false); - -// Compute summary statistics by fitting the StandardScaler -StandardScalerModel scalerModel = scaler.fit(dataFrame); - -// Normalize each feature to have unit standard deviation. -DataFrame scaledData = scalerModel.transform(dataFrame); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaStandardScalerExample.java %}
@@ -1294,20 +625,7 @@ DataFrame scaledData = scalerModel.transform(dataFrame); Refer to the [StandardScaler Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.StandardScaler) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import StandardScaler - -dataFrame = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") -scaler = StandardScaler(inputCol="features", outputCol="scaledFeatures", - withStd=True, withMean=False) - -# Compute summary statistics by fitting the StandardScaler -scalerModel = scaler.fit(dataFrame) - -# Normalize each feature to have unit standard deviation. -scaledData = scalerModel.transform(dataFrame) -{% endhighlight %} +{% include_example python/ml/standard_scaler_example.py %}
@@ -1337,21 +655,7 @@ Refer to the [MinMaxScaler Scala docs](api/scala/index.html#org.apache.spark.ml. and the [MinMaxScalerModel Scala docs](api/scala/index.html#org.apache.spark.ml.feature.MinMaxScalerModel) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.MinMaxScaler - -val dataFrame = sqlContext.read.format("libsvm") - .load("data/mllib/sample_libsvm_data.txt") -val scaler = new MinMaxScaler() - .setInputCol("features") - .setOutputCol("scaledFeatures") - -// Compute summary statistics and generate MinMaxScalerModel -val scalerModel = scaler.fit(dataFrame) - -// rescale each feature to range [min, max]. -val scaledData = scalerModel.transform(dataFrame) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala %}
@@ -1360,24 +664,7 @@ Refer to the [MinMaxScaler Java docs](api/java/org/apache/spark/ml/feature/MinMa and the [MinMaxScalerModel Java docs](api/java/org/apache/spark/ml/feature/MinMaxScalerModel.html) for more details on the API. -{% highlight java %} -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.MinMaxScaler; -import org.apache.spark.ml.feature.MinMaxScalerModel; -import org.apache.spark.sql.DataFrame; - -DataFrame dataFrame = sqlContext.read().format("libsvm") - .load("data/mllib/sample_libsvm_data.txt"); -MinMaxScaler scaler = new MinMaxScaler() - .setInputCol("features") - .setOutputCol("scaledFeatures"); - -// Compute summary statistics and generate MinMaxScalerModel -MinMaxScalerModel scalerModel = scaler.fit(dataFrame); - -// rescale each feature to range [min, max]. -DataFrame scaledData = scalerModel.transform(dataFrame); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java %}
@@ -1401,23 +688,7 @@ The following example demonstrates how to bucketize a column of `Double`s into a Refer to the [Bucketizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.Bucketizer) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.Bucketizer -import org.apache.spark.sql.DataFrame - -val splits = Array(Double.NegativeInfinity, -0.5, 0.0, 0.5, Double.PositiveInfinity) - -val data = Array(-0.5, -0.3, 0.0, 0.2) -val dataFrame = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") - -val bucketizer = new Bucketizer() - .setInputCol("features") - .setOutputCol("bucketedFeatures") - .setSplits(splits) - -// Transform original data into its bucket index. -val bucketedData = bucketizer.transform(dataFrame) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/BucketizerExample.scala %}
@@ -1425,38 +696,7 @@ val bucketedData = bucketizer.transform(dataFrame) Refer to the [Bucketizer Java docs](api/java/org/apache/spark/ml/feature/Bucketizer.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -double[] splits = {Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY}; - -JavaRDD data = jsc.parallelize(Arrays.asList( - RowFactory.create(-0.5), - RowFactory.create(-0.3), - RowFactory.create(0.0), - RowFactory.create(0.2) -)); -StructType schema = new StructType(new StructField[] { - new StructField("features", DataTypes.DoubleType, false, Metadata.empty()) -}); -DataFrame dataFrame = jsql.createDataFrame(data, schema); - -Bucketizer bucketizer = new Bucketizer() - .setInputCol("features") - .setOutputCol("bucketedFeatures") - .setSplits(splits); - -// Transform original data into its bucket index. -DataFrame bucketedData = bucketizer.transform(dataFrame); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaBucketizerExample.java %}
@@ -1464,19 +704,7 @@ DataFrame bucketedData = bucketizer.transform(dataFrame); Refer to the [Bucketizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.Bucketizer) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import Bucketizer - -splits = [-float("inf"), -0.5, 0.0, 0.5, float("inf")] - -data = [(-0.5,), (-0.3,), (0.0,), (0.2,)] -dataFrame = sqlContext.createDataFrame(data, ["features"]) - -bucketizer = Bucketizer(splits=splits, inputCol="features", outputCol="bucketedFeatures") - -# Transform original data into its bucket index. -bucketedData = bucketizer.transform(dataFrame) -{% endhighlight %} +{% include_example python/ml/bucketizer_example.py %}
@@ -1508,25 +736,7 @@ This example below demonstrates how to transform vectors using a transforming ve Refer to the [ElementwiseProduct Scala docs](api/scala/index.html#org.apache.spark.ml.feature.ElementwiseProduct) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.ElementwiseProduct -import org.apache.spark.mllib.linalg.Vectors - -// Create some vector data; also works for sparse vectors -val dataFrame = sqlContext.createDataFrame(Seq( - ("a", Vectors.dense(1.0, 2.0, 3.0)), - ("b", Vectors.dense(4.0, 5.0, 6.0)))).toDF("id", "vector") - -val transformingVector = Vectors.dense(0.0, 1.0, 2.0) -val transformer = new ElementwiseProduct() - .setScalingVec(transformingVector) - .setInputCol("vector") - .setOutputCol("transformedVector") - -// Batch transform the vectors to create new column: -transformer.transform(dataFrame).show() - -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/ElementwiseProductExample.scala %}
@@ -1534,41 +744,7 @@ transformer.transform(dataFrame).show() Refer to the [ElementwiseProduct Java docs](api/java/org/apache/spark/ml/feature/ElementwiseProduct.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.ElementwiseProduct; -import org.apache.spark.mllib.linalg.Vector; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.SQLContext; -import org.apache.spark.sql.types.DataTypes; -import org.apache.spark.sql.types.Metadata; -import org.apache.spark.sql.types.StructField; -import org.apache.spark.sql.types.StructType; - -// Create some vector data; also works for sparse vectors -JavaRDD jrdd = jsc.parallelize(Arrays.asList( - RowFactory.create("a", Vectors.dense(1.0, 2.0, 3.0)), - RowFactory.create("b", Vectors.dense(4.0, 5.0, 6.0)) -)); -List fields = new ArrayList(2); -fields.add(DataTypes.createStructField("id", DataTypes.StringType, false)); -fields.add(DataTypes.createStructField("vector", DataTypes.StringType, false)); -StructType schema = DataTypes.createStructType(fields); -DataFrame dataFrame = sqlContext.createDataFrame(jrdd, schema); -Vector transformingVector = Vectors.dense(0.0, 1.0, 2.0); -ElementwiseProduct transformer = new ElementwiseProduct() - .setScalingVec(transformingVector) - .setInputCol("vector") - .setOutputCol("transformedVector"); -// Batch transform the vectors to create new column: -transformer.transform(dataFrame).show(); - -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java %}
@@ -1576,19 +752,8 @@ transformer.transform(dataFrame).show(); Refer to the [ElementwiseProduct Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.ElementwiseProduct) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import ElementwiseProduct -from pyspark.mllib.linalg import Vectors - -data = [(Vectors.dense([1.0, 2.0, 3.0]),), (Vectors.dense([4.0, 5.0, 6.0]),)] -df = sqlContext.createDataFrame(data, ["vector"]) -transformer = ElementwiseProduct(scalingVec=Vectors.dense([0.0, 1.0, 2.0]), - inputCol="vector", outputCol="transformedVector") -transformer.transform(df).show() - -{% endhighlight %} +{% include_example python/ml/elementwise_product_example.py %}
- ## VectorAssembler @@ -1632,19 +797,7 @@ output column to `features`, after transformation we should get the following Da Refer to the [VectorAssembler Scala docs](api/scala/index.html#org.apache.spark.ml.feature.VectorAssembler) for more details on the API. -{% highlight scala %} -import org.apache.spark.mllib.linalg.Vectors -import org.apache.spark.ml.feature.VectorAssembler - -val dataset = sqlContext.createDataFrame( - Seq((0, 18, 1.0, Vectors.dense(0.0, 10.0, 0.5), 1.0)) -).toDF("id", "hour", "mobile", "userFeatures", "clicked") -val assembler = new VectorAssembler() - .setInputCols(Array("hour", "mobile", "userFeatures")) - .setOutputCol("features") -val output = assembler.transform(dataset) -println(output.select("features", "clicked").first()) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/VectorAssemblerExample.scala %}
@@ -1652,36 +805,7 @@ println(output.select("features", "clicked").first()) Refer to the [VectorAssembler Java docs](api/java/org/apache/spark/ml/feature/VectorAssembler.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.mllib.linalg.VectorUDT; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.*; -import static org.apache.spark.sql.types.DataTypes.*; - -StructType schema = createStructType(new StructField[] { - createStructField("id", IntegerType, false), - createStructField("hour", IntegerType, false), - createStructField("mobile", DoubleType, false), - createStructField("userFeatures", new VectorUDT(), false), - createStructField("clicked", DoubleType, false) -}); -Row row = RowFactory.create(0, 18, 1.0, Vectors.dense(0.0, 10.0, 0.5), 1.0); -JavaRDD rdd = jsc.parallelize(Arrays.asList(row)); -DataFrame dataset = sqlContext.createDataFrame(rdd, schema); - -VectorAssembler assembler = new VectorAssembler() - .setInputCols(new String[] {"hour", "mobile", "userFeatures"}) - .setOutputCol("features"); - -DataFrame output = assembler.transform(dataset); -System.out.println(output.select("features", "clicked").first()); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java %}
@@ -1689,19 +813,7 @@ System.out.println(output.select("features", "clicked").first()); Refer to the [VectorAssembler Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.VectorAssembler) for more details on the API. -{% highlight python %} -from pyspark.mllib.linalg import Vectors -from pyspark.ml.feature import VectorAssembler - -dataset = sqlContext.createDataFrame( - [(0, 18, 1.0, Vectors.dense([0.0, 10.0, 0.5]), 1.0)], - ["id", "hour", "mobile", "userFeatures", "clicked"]) -assembler = VectorAssembler( - inputCols=["hour", "mobile", "userFeatures"], - outputCol="features") -output = assembler.transform(dataset) -print(output.select("features", "clicked").first()) -{% endhighlight %} +{% include_example python/ml/vector_assembler_example.py %}
@@ -1831,33 +943,7 @@ Suppose also that we have a potential input attributes for the `userFeatures`, i Refer to the [VectorSlicer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.VectorSlicer) for more details on the API. -{% highlight scala %} -import org.apache.spark.mllib.linalg.Vectors -import org.apache.spark.ml.attribute.{Attribute, AttributeGroup, NumericAttribute} -import org.apache.spark.ml.feature.VectorSlicer -import org.apache.spark.sql.types.StructType -import org.apache.spark.sql.{DataFrame, Row, SQLContext} - -val data = Array( - Vectors.sparse(3, Seq((0, -2.0), (1, 2.3))), - Vectors.dense(-2.0, 2.3, 0.0) -) - -val defaultAttr = NumericAttribute.defaultAttr -val attrs = Array("f1", "f2", "f3").map(defaultAttr.withName) -val attrGroup = new AttributeGroup("userFeatures", attrs.asInstanceOf[Array[Attribute]]) - -val dataRDD = sc.parallelize(data).map(Row.apply) -val dataset = sqlContext.createDataFrame(dataRDD, StructType(attrGroup.toStructField())) - -val slicer = new VectorSlicer().setInputCol("userFeatures").setOutputCol("features") - -slicer.setIndices(1).setNames("f3") -// or slicer.setIndices(Array(1, 2)), or slicer.setNames(Array("f2", "f3")) - -val output = slicer.transform(dataset) -println(output.select("userFeatures", "features").first()) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/VectorSlicerExample.scala %}
@@ -1865,41 +951,7 @@ println(output.select("userFeatures", "features").first()) Refer to the [VectorSlicer Java docs](api/java/org/apache/spark/ml/feature/VectorSlicer.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.*; -import static org.apache.spark.sql.types.DataTypes.*; - -Attribute[] attrs = new Attribute[]{ - NumericAttribute.defaultAttr().withName("f1"), - NumericAttribute.defaultAttr().withName("f2"), - NumericAttribute.defaultAttr().withName("f3") -}; -AttributeGroup group = new AttributeGroup("userFeatures", attrs); - -JavaRDD jrdd = jsc.parallelize(Lists.newArrayList( - RowFactory.create(Vectors.sparse(3, new int[]{0, 1}, new double[]{-2.0, 2.3})), - RowFactory.create(Vectors.dense(-2.0, 2.3, 0.0)) -)); - -DataFrame dataset = jsql.createDataFrame(jrdd, (new StructType()).add(group.toStructField())); - -VectorSlicer vectorSlicer = new VectorSlicer() - .setInputCol("userFeatures").setOutputCol("features"); - -vectorSlicer.setIndices(new int[]{1}).setNames(new String[]{"f3"}); -// or slicer.setIndices(new int[]{1, 2}), or slicer.setNames(new String[]{"f2", "f3"}) - -DataFrame output = vectorSlicer.transform(dataset); - -System.out.println(output.select("userFeatures", "features").first()); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java %}
@@ -1936,21 +988,7 @@ id | country | hour | clicked | features | label Refer to the [RFormula Scala docs](api/scala/index.html#org.apache.spark.ml.feature.RFormula) for more details on the API. -{% highlight scala %} -import org.apache.spark.ml.feature.RFormula - -val dataset = sqlContext.createDataFrame(Seq( - (7, "US", 18, 1.0), - (8, "CA", 12, 0.0), - (9, "NZ", 15, 0.0) -)).toDF("id", "country", "hour", "clicked") -val formula = new RFormula() - .setFormula("clicked ~ country + hour") - .setFeaturesCol("features") - .setLabelCol("label") -val output = formula.fit(dataset).transform(dataset) -output.select("features", "label").show() -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/ml/RFormulaExample.scala %}
@@ -1958,38 +996,7 @@ output.select("features", "label").show() Refer to the [RFormula Java docs](api/java/org/apache/spark/ml/feature/RFormula.html) for more details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.ml.feature.RFormula; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; -import org.apache.spark.sql.RowFactory; -import org.apache.spark.sql.types.*; -import static org.apache.spark.sql.types.DataTypes.*; - -StructType schema = createStructType(new StructField[] { - createStructField("id", IntegerType, false), - createStructField("country", StringType, false), - createStructField("hour", IntegerType, false), - createStructField("clicked", DoubleType, false) -}); -JavaRDD rdd = jsc.parallelize(Arrays.asList( - RowFactory.create(7, "US", 18, 1.0), - RowFactory.create(8, "CA", 12, 0.0), - RowFactory.create(9, "NZ", 15, 0.0) -)); -DataFrame dataset = sqlContext.createDataFrame(rdd, schema); - -RFormula formula = new RFormula() - .setFormula("clicked ~ country + hour") - .setFeaturesCol("features") - .setLabelCol("label"); - -DataFrame output = formula.fit(dataset).transform(dataset); -output.select("features", "label").show(); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/ml/JavaRFormulaExample.java %}
@@ -1997,21 +1004,7 @@ output.select("features", "label").show(); Refer to the [RFormula Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.RFormula) for more details on the API. -{% highlight python %} -from pyspark.ml.feature import RFormula - -dataset = sqlContext.createDataFrame( - [(7, "US", 18, 1.0), - (8, "CA", 12, 0.0), - (9, "NZ", 15, 0.0)], - ["id", "country", "hour", "clicked"]) -formula = RFormula( - formula="clicked ~ country + hour", - featuresCol="features", - labelCol="label") -output = formula.fit(dataset).transform(dataset) -output.select("features", "label").show() -{% endhighlight %} +{% include_example python/ml/rformula_example.py %}
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 new file mode 100644 index 0000000000000..9698cac504371 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java @@ -0,0 +1,68 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.Binarizer; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaBinarizerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaBinarizerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + JavaRDD jrdd = jsc.parallelize(Arrays.asList( + RowFactory.create(0, 0.1), + RowFactory.create(1, 0.8), + RowFactory.create(2, 0.2) + )); + StructType schema = new StructType(new StructField[]{ + new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), + new StructField("feature", DataTypes.DoubleType, false, Metadata.empty()) + }); + DataFrame continuousDataFrame = jsql.createDataFrame(jrdd, schema); + Binarizer binarizer = new Binarizer() + .setInputCol("feature") + .setOutputCol("binarized_feature") + .setThreshold(0.5); + DataFrame binarizedDataFrame = binarizer.transform(continuousDataFrame); + DataFrame binarizedFeatures = binarizedDataFrame.select("binarized_feature"); + for (Row r : binarizedFeatures.collect()) { + Double binarized_value = r.getDouble(0); + System.out.println(binarized_value); + } + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java new file mode 100644 index 0000000000000..b06a23e76d604 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java @@ -0,0 +1,70 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.Bucketizer; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaBucketizerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaBucketizerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + double[] splits = {Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY}; + + JavaRDD data = jsc.parallelize(Arrays.asList( + RowFactory.create(-0.5), + RowFactory.create(-0.3), + RowFactory.create(0.0), + RowFactory.create(0.2) + )); + StructType schema = new StructType(new StructField[]{ + new StructField("features", DataTypes.DoubleType, false, Metadata.empty()) + }); + DataFrame dataFrame = jsql.createDataFrame(data, schema); + + Bucketizer bucketizer = new Bucketizer() + .setInputCol("features") + .setOutputCol("bucketedFeatures") + .setSplits(splits); + + // Transform original data into its bucket index. + DataFrame bucketedData = bucketizer.transform(dataFrame); + // $example off$ + jsc.stop(); + } +} + + diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java new file mode 100644 index 0000000000000..35c0d534a45e9 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java @@ -0,0 +1,65 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.DCT; +import org.apache.spark.mllib.linalg.VectorUDT; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaDCTExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaDCTExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + JavaRDD data = jsc.parallelize(Arrays.asList( + RowFactory.create(Vectors.dense(0.0, 1.0, -2.0, 3.0)), + RowFactory.create(Vectors.dense(-1.0, 2.0, 4.0, -7.0)), + RowFactory.create(Vectors.dense(14.0, -2.0, -5.0, 1.0)) + )); + StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + }); + DataFrame df = jsql.createDataFrame(data, schema); + DCT dct = new DCT() + .setInputCol("features") + .setOutputCol("featuresDCT") + .setInverse(false); + DataFrame dctDf = dct.transform(df); + dctDf.select("featuresDCT").show(3); + // $example off$ + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java new file mode 100644 index 0000000000000..2898accec61b0 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java @@ -0,0 +1,75 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.ElementwiseProduct; +import org.apache.spark.mllib.linalg.Vector; +import org.apache.spark.mllib.linalg.VectorUDT; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaElementwiseProductExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaElementwiseProductExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + // Create some vector data; also works for sparse vectors + JavaRDD jrdd = jsc.parallelize(Arrays.asList( + RowFactory.create("a", Vectors.dense(1.0, 2.0, 3.0)), + RowFactory.create("b", Vectors.dense(4.0, 5.0, 6.0)) + )); + + List fields = new ArrayList(2); + fields.add(DataTypes.createStructField("id", DataTypes.StringType, false)); + fields.add(DataTypes.createStructField("vector", new VectorUDT(), false)); + + StructType schema = DataTypes.createStructType(fields); + + DataFrame dataFrame = sqlContext.createDataFrame(jrdd, schema); + + Vector transformingVector = Vectors.dense(0.0, 1.0, 2.0); + + ElementwiseProduct transformer = new ElementwiseProduct() + .setScalingVec(transformingVector) + .setInputCol("vector") + .setOutputCol("transformedVector"); + + // Batch transform the vectors to create new column: + transformer.transform(dataFrame).show(); + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java new file mode 100644 index 0000000000000..138b3ab6aba44 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java @@ -0,0 +1,50 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import org.apache.spark.ml.feature.MinMaxScaler; +import org.apache.spark.ml.feature.MinMaxScalerModel; +import org.apache.spark.sql.DataFrame; +// $example off$ + +public class JavaMinMaxScalerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JaveMinMaxScalerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + DataFrame dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); + MinMaxScaler scaler = new MinMaxScaler() + .setInputCol("features") + .setOutputCol("scaledFeatures"); + + // Compute summary statistics and generate MinMaxScalerModel + MinMaxScalerModel scalerModel = scaler.fit(dataFrame); + + // rescale each feature to range [min, max]. + DataFrame scaledData = scalerModel.transform(dataFrame); + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java new file mode 100644 index 0000000000000..8fd75ed8b5f4e --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java @@ -0,0 +1,71 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.NGram; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaNGramExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaNGramExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + JavaRDD jrdd = jsc.parallelize(Arrays.asList( + RowFactory.create(0.0, Arrays.asList("Hi", "I", "heard", "about", "Spark")), + RowFactory.create(1.0, Arrays.asList("I", "wish", "Java", "could", "use", "case", "classes")), + RowFactory.create(2.0, Arrays.asList("Logistic", "regression", "models", "are", "neat")) + )); + + StructType schema = new StructType(new StructField[]{ + new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), + new StructField( + "words", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty()) + }); + + DataFrame wordDataFrame = sqlContext.createDataFrame(jrdd, schema); + + NGram ngramTransformer = new NGram().setInputCol("words").setOutputCol("ngrams"); + + DataFrame ngramDataFrame = ngramTransformer.transform(wordDataFrame); + + for (Row r : ngramDataFrame.select("ngrams", "label").take(3)) { + java.util.List ngrams = r.getList(0); + for (String ngram : ngrams) System.out.print(ngram + " --- "); + System.out.println(); + } + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java new file mode 100644 index 0000000000000..6283a355e1fef --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java @@ -0,0 +1,52 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import org.apache.spark.ml.feature.Normalizer; +import org.apache.spark.sql.DataFrame; +// $example off$ + +public class JavaNormalizerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaNormalizerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + DataFrame dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); + + // Normalize each Vector using $L^1$ norm. + Normalizer normalizer = new Normalizer() + .setInputCol("features") + .setOutputCol("normFeatures") + .setP(1.0); + + DataFrame l1NormData = normalizer.transform(dataFrame); + + // Normalize each Vector using $L^\infty$ norm. + DataFrame lInfNormData = + normalizer.transform(dataFrame, normalizer.p().w(Double.POSITIVE_INFINITY)); + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java new file mode 100644 index 0000000000000..172a9cc6feb28 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java @@ -0,0 +1,77 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.OneHotEncoder; +import org.apache.spark.ml.feature.StringIndexer; +import org.apache.spark.ml.feature.StringIndexerModel; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaOneHotEncoderExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaOneHotEncoderExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + JavaRDD jrdd = jsc.parallelize(Arrays.asList( + RowFactory.create(0, "a"), + RowFactory.create(1, "b"), + RowFactory.create(2, "c"), + RowFactory.create(3, "a"), + RowFactory.create(4, "a"), + RowFactory.create(5, "c") + )); + + StructType schema = new StructType(new StructField[]{ + new StructField("id", DataTypes.DoubleType, false, Metadata.empty()), + new StructField("category", DataTypes.StringType, false, Metadata.empty()) + }); + + DataFrame df = sqlContext.createDataFrame(jrdd, schema); + + StringIndexerModel indexer = new StringIndexer() + .setInputCol("category") + .setOutputCol("categoryIndex") + .fit(df); + DataFrame indexed = indexer.transform(df); + + OneHotEncoder encoder = new OneHotEncoder() + .setInputCol("categoryIndex") + .setOutputCol("categoryVec"); + DataFrame encoded = encoder.transform(indexed); + // $example off$ + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java new file mode 100644 index 0000000000000..8282fab084f36 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java @@ -0,0 +1,71 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.PCA; +import org.apache.spark.ml.feature.PCAModel; +import org.apache.spark.mllib.linalg.VectorUDT; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaPCAExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaPCAExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + JavaRDD data = jsc.parallelize(Arrays.asList( + RowFactory.create(Vectors.sparse(5, new int[]{1, 3}, new double[]{1.0, 7.0})), + RowFactory.create(Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0)), + RowFactory.create(Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)) + )); + + StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + }); + + DataFrame df = jsql.createDataFrame(data, schema); + + PCAModel pca = new PCA() + .setInputCol("features") + .setOutputCol("pcaFeatures") + .setK(3) + .fit(df); + + DataFrame result = pca.transform(df).select("pcaFeatures"); + result.show(); + // $example off$ + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java new file mode 100644 index 0000000000000..668f71e64056b --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java @@ -0,0 +1,71 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.PolynomialExpansion; +import org.apache.spark.mllib.linalg.VectorUDT; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaPolynomialExpansionExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaPolynomialExpansionExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + PolynomialExpansion polyExpansion = new PolynomialExpansion() + .setInputCol("features") + .setOutputCol("polyFeatures") + .setDegree(3); + + JavaRDD data = jsc.parallelize(Arrays.asList( + RowFactory.create(Vectors.dense(-2.0, 2.3)), + RowFactory.create(Vectors.dense(0.0, 0.0)), + RowFactory.create(Vectors.dense(0.6, -1.1)) + )); + + StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + }); + + DataFrame df = jsql.createDataFrame(data, schema); + DataFrame polyDF = polyExpansion.transform(df); + + Row[] row = polyDF.select("polyFeatures").take(3); + for (Row r : row) { + System.out.println(r.get(0)); + } + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java new file mode 100644 index 0000000000000..1e1062b541ad9 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java @@ -0,0 +1,69 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.RFormula; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; + +import static org.apache.spark.sql.types.DataTypes.*; +// $example off$ + +public class JavaRFormulaExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaRFormulaExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + StructType schema = createStructType(new StructField[]{ + createStructField("id", IntegerType, false), + createStructField("country", StringType, false), + createStructField("hour", IntegerType, false), + createStructField("clicked", DoubleType, false) + }); + + JavaRDD rdd = jsc.parallelize(Arrays.asList( + RowFactory.create(7, "US", 18, 1.0), + RowFactory.create(8, "CA", 12, 0.0), + RowFactory.create(9, "NZ", 15, 0.0) + )); + + DataFrame dataset = sqlContext.createDataFrame(rdd, schema); + RFormula formula = new RFormula() + .setFormula("clicked ~ country + hour") + .setFeaturesCol("features") + .setLabelCol("label"); + DataFrame output = formula.fit(dataset).transform(dataset); + output.select("features", "label").show(); + // $example off$ + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java new file mode 100644 index 0000000000000..0cbdc97e8ae30 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import org.apache.spark.ml.feature.StandardScaler; +import org.apache.spark.ml.feature.StandardScalerModel; +import org.apache.spark.sql.DataFrame; +// $example off$ + +public class JavaStandardScalerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaStandardScalerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + DataFrame dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); + + StandardScaler scaler = new StandardScaler() + .setInputCol("features") + .setOutputCol("scaledFeatures") + .setWithStd(true) + .setWithMean(false); + + // Compute summary statistics by fitting the StandardScaler + StandardScalerModel scalerModel = scaler.fit(dataFrame); + + // Normalize each feature to have unit standard deviation. + DataFrame scaledData = scalerModel.transform(dataFrame); + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java new file mode 100644 index 0000000000000..b6b201c6b68d2 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java @@ -0,0 +1,65 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.StopWordsRemover; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaStopWordsRemoverExample { + + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaStopWordsRemoverExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + StopWordsRemover remover = new StopWordsRemover() + .setInputCol("raw") + .setOutputCol("filtered"); + + JavaRDD rdd = jsc.parallelize(Arrays.asList( + RowFactory.create(Arrays.asList("I", "saw", "the", "red", "baloon")), + RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb")) + )); + + StructType schema = new StructType(new StructField[]{ + new StructField( + "raw", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty()) + }); + + DataFrame dataset = jsql.createDataFrame(rdd, schema); + remover.transform(dataset).show(); + // $example off$ + jsc.stop(); + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java new file mode 100644 index 0000000000000..05d12c1e702f1 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java @@ -0,0 +1,66 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.StringIndexer; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; + +import static org.apache.spark.sql.types.DataTypes.*; +// $example off$ + +public class JavaStringIndexerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaStringIndexerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + JavaRDD jrdd = jsc.parallelize(Arrays.asList( + RowFactory.create(0, "a"), + RowFactory.create(1, "b"), + RowFactory.create(2, "c"), + RowFactory.create(3, "a"), + RowFactory.create(4, "a"), + RowFactory.create(5, "c") + )); + StructType schema = new StructType(new StructField[]{ + createStructField("id", IntegerType, false), + createStructField("category", StringType, false) + }); + DataFrame df = sqlContext.createDataFrame(jrdd, schema); + StringIndexer indexer = new StringIndexer() + .setInputCol("category") + .setOutputCol("categoryIndex"); + DataFrame indexed = indexer.fit(df).transform(df); + indexed.show(); + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java new file mode 100644 index 0000000000000..617dc3f66e3bf --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java @@ -0,0 +1,75 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.RegexTokenizer; +import org.apache.spark.ml.feature.Tokenizer; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +// $example off$ + +public class JavaTokenizerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaTokenizerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + JavaRDD jrdd = jsc.parallelize(Arrays.asList( + RowFactory.create(0, "Hi I heard about Spark"), + RowFactory.create(1, "I wish Java could use case classes"), + RowFactory.create(2, "Logistic,regression,models,are,neat") + )); + + StructType schema = new StructType(new StructField[]{ + new StructField("label", DataTypes.IntegerType, false, Metadata.empty()), + new StructField("sentence", DataTypes.StringType, false, Metadata.empty()) + }); + + DataFrame sentenceDataFrame = sqlContext.createDataFrame(jrdd, schema); + + Tokenizer tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words"); + + DataFrame wordsDataFrame = tokenizer.transform(sentenceDataFrame); + for (Row r : wordsDataFrame.select("words", "label"). take(3)) { + java.util.List words = r.getList(0); + for (String word : words) System.out.print(word + " "); + System.out.println(); + } + + RegexTokenizer regexTokenizer = new RegexTokenizer() + .setInputCol("sentence") + .setOutputCol("words") + .setPattern("\\W"); // alternatively .setPattern("\\w+").setGaps(false); + // $example off$ + jsc.stop(); + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java new file mode 100644 index 0000000000000..7e230b5897c1e --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java @@ -0,0 +1,67 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.feature.VectorAssembler; +import org.apache.spark.mllib.linalg.VectorUDT; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.*; + +import static org.apache.spark.sql.types.DataTypes.*; +// $example off$ + +public class JavaVectorAssemblerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaVectorAssemblerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext sqlContext = new SQLContext(jsc); + + // $example on$ + StructType schema = createStructType(new StructField[]{ + createStructField("id", IntegerType, false), + createStructField("hour", IntegerType, false), + createStructField("mobile", DoubleType, false), + createStructField("userFeatures", new VectorUDT(), false), + createStructField("clicked", DoubleType, false) + }); + Row row = RowFactory.create(0, 18, 1.0, Vectors.dense(0.0, 10.0, 0.5), 1.0); + JavaRDD rdd = jsc.parallelize(Arrays.asList(row)); + DataFrame dataset = sqlContext.createDataFrame(rdd, schema); + + VectorAssembler assembler = new VectorAssembler() + .setInputCols(new String[]{"hour", "mobile", "userFeatures"}) + .setOutputCol("features"); + + DataFrame output = assembler.transform(dataset); + System.out.println(output.select("features", "clicked").first()); + // $example off$ + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java new file mode 100644 index 0000000000000..06b4bf6bf8ff6 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java @@ -0,0 +1,60 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import java.util.Map; + +import org.apache.spark.ml.feature.VectorIndexer; +import org.apache.spark.ml.feature.VectorIndexerModel; +import org.apache.spark.sql.DataFrame; +// $example off$ + +public class JavaVectorIndexerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaVectorIndexerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + DataFrame data = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); + + VectorIndexer indexer = new VectorIndexer() + .setInputCol("features") + .setOutputCol("indexed") + .setMaxCategories(10); + VectorIndexerModel indexerModel = indexer.fit(data); + + Map> categoryMaps = indexerModel.javaCategoryMaps(); + System.out.print("Chose " + categoryMaps.size() + " categorical features:"); + + for (Integer feature : categoryMaps.keySet()) { + System.out.print(" " + feature); + } + System.out.println(); + + // Create new column "indexed" with categorical values transformed to indices + DataFrame indexedData = indexerModel.transform(data); + // $example off$ + jsc.stop(); + } +} \ No newline at end of file diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java new file mode 100644 index 0000000000000..4d5cb04ff5e2b --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java @@ -0,0 +1,73 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.ml; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SQLContext; + +// $example on$ +import com.google.common.collect.Lists; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.ml.attribute.Attribute; +import org.apache.spark.ml.attribute.AttributeGroup; +import org.apache.spark.ml.attribute.NumericAttribute; +import org.apache.spark.ml.feature.VectorSlicer; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.types.*; +// $example off$ + +public class JavaVectorSlicerExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaVectorSlicerExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + Attribute[] attrs = new Attribute[]{ + NumericAttribute.defaultAttr().withName("f1"), + NumericAttribute.defaultAttr().withName("f2"), + NumericAttribute.defaultAttr().withName("f3") + }; + AttributeGroup group = new AttributeGroup("userFeatures", attrs); + + JavaRDD jrdd = jsc.parallelize(Lists.newArrayList( + RowFactory.create(Vectors.sparse(3, new int[]{0, 1}, new double[]{-2.0, 2.3})), + RowFactory.create(Vectors.dense(-2.0, 2.3, 0.0)) + )); + + DataFrame dataset = jsql.createDataFrame(jrdd, (new StructType()).add(group.toStructField())); + + VectorSlicer vectorSlicer = new VectorSlicer() + .setInputCol("userFeatures").setOutputCol("features"); + + vectorSlicer.setIndices(new int[]{1}).setNames(new String[]{"f3"}); + // or slicer.setIndices(new int[]{1, 2}), or slicer.setNames(new String[]{"f2", "f3"}) + + DataFrame output = vectorSlicer.transform(dataset); + + System.out.println(output.select("userFeatures", "features").first()); + // $example off$ + jsc.stop(); + } +} + diff --git a/examples/src/main/python/ml/binarizer_example.py b/examples/src/main/python/ml/binarizer_example.py new file mode 100644 index 0000000000000..960ad208be12e --- /dev/null +++ b/examples/src/main/python/ml/binarizer_example.py @@ -0,0 +1,43 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import Binarizer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="BinarizerExample") + sqlContext = SQLContext(sc) + + # $example on$ + continuousDataFrame = sqlContext.createDataFrame([ + (0, 0.1), + (1, 0.8), + (2, 0.2) + ], ["label", "feature"]) + binarizer = Binarizer(threshold=0.5, inputCol="feature", outputCol="binarized_feature") + binarizedDataFrame = binarizer.transform(continuousDataFrame) + binarizedFeatures = binarizedDataFrame.select("binarized_feature") + for binarized_feature, in binarizedFeatures.collect(): + print(binarized_feature) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/bucketizer_example.py b/examples/src/main/python/ml/bucketizer_example.py new file mode 100644 index 0000000000000..a12750aa9248a --- /dev/null +++ b/examples/src/main/python/ml/bucketizer_example.py @@ -0,0 +1,42 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import Bucketizer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="BucketizerExample") + sqlContext = SQLContext(sc) + + # $example on$ + splits = [-float("inf"), -0.5, 0.0, 0.5, float("inf")] + + data = [(-0.5,), (-0.3,), (0.0,), (0.2,)] + dataFrame = sqlContext.createDataFrame(data, ["features"]) + + bucketizer = Bucketizer(splits=splits, inputCol="features", outputCol="bucketedFeatures") + + # Transform original data into its bucket index. + bucketedData = bucketizer.transform(dataFrame) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/elementwise_product_example.py b/examples/src/main/python/ml/elementwise_product_example.py new file mode 100644 index 0000000000000..c85cb0d89543c --- /dev/null +++ b/examples/src/main/python/ml/elementwise_product_example.py @@ -0,0 +1,39 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import ElementwiseProduct +from pyspark.mllib.linalg import Vectors +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="ElementwiseProductExample") + sqlContext = SQLContext(sc) + + # $example on$ + data = [(Vectors.dense([1.0, 2.0, 3.0]),), (Vectors.dense([4.0, 5.0, 6.0]),)] + df = sqlContext.createDataFrame(data, ["vector"]) + transformer = ElementwiseProduct(scalingVec=Vectors.dense([0.0, 1.0, 2.0]), + inputCol="vector", outputCol="transformedVector") + transformer.transform(df).show() + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/n_gram_example.py b/examples/src/main/python/ml/n_gram_example.py new file mode 100644 index 0000000000000..f2d85f53e7219 --- /dev/null +++ b/examples/src/main/python/ml/n_gram_example.py @@ -0,0 +1,42 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import NGram +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="NGramExample") + sqlContext = SQLContext(sc) + + # $example on$ + wordDataFrame = sqlContext.createDataFrame([ + (0, ["Hi", "I", "heard", "about", "Spark"]), + (1, ["I", "wish", "Java", "could", "use", "case", "classes"]), + (2, ["Logistic", "regression", "models", "are", "neat"]) + ], ["label", "words"]) + ngram = NGram(inputCol="words", outputCol="ngrams") + ngramDataFrame = ngram.transform(wordDataFrame) + for ngrams_label in ngramDataFrame.select("ngrams", "label").take(3): + print(ngrams_label) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/normalizer_example.py b/examples/src/main/python/ml/normalizer_example.py new file mode 100644 index 0000000000000..833d93e976a7e --- /dev/null +++ b/examples/src/main/python/ml/normalizer_example.py @@ -0,0 +1,41 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import Normalizer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="NormalizerExample") + sqlContext = SQLContext(sc) + + # $example on$ + dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + + # Normalize each Vector using $L^1$ norm. + normalizer = Normalizer(inputCol="features", outputCol="normFeatures", p=1.0) + l1NormData = normalizer.transform(dataFrame) + + # Normalize each Vector using $L^\infty$ norm. + lInfNormData = normalizer.transform(dataFrame, {normalizer.p: float("inf")}) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/onehot_encoder_example.py b/examples/src/main/python/ml/onehot_encoder_example.py new file mode 100644 index 0000000000000..7529dfd09213a --- /dev/null +++ b/examples/src/main/python/ml/onehot_encoder_example.py @@ -0,0 +1,47 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import OneHotEncoder, StringIndexer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="OneHotEncoderExample") + sqlContext = SQLContext(sc) + + # $example on$ + df = sqlContext.createDataFrame([ + (0, "a"), + (1, "b"), + (2, "c"), + (3, "a"), + (4, "a"), + (5, "c") + ], ["id", "category"]) + + stringIndexer = StringIndexer(inputCol="category", outputCol="categoryIndex") + model = stringIndexer.fit(df) + indexed = model.transform(df) + encoder = OneHotEncoder(dropLast=False, inputCol="categoryIndex", outputCol="categoryVec") + encoded = encoder.transform(indexed) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/pca_example.py b/examples/src/main/python/ml/pca_example.py new file mode 100644 index 0000000000000..8b66140a40a7a --- /dev/null +++ b/examples/src/main/python/ml/pca_example.py @@ -0,0 +1,42 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import PCA +from pyspark.mllib.linalg import Vectors +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PCAExample") + sqlContext = SQLContext(sc) + + # $example on$ + data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),), + (Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]),), + (Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0]),)] + df = sqlContext.createDataFrame(data,["features"]) + pca = PCA(k=3, inputCol="features", outputCol="pcaFeatures") + model = pca.fit(df) + result = model.transform(df).select("pcaFeatures") + result.show(truncate=False) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/polynomial_expansion_example.py b/examples/src/main/python/ml/polynomial_expansion_example.py new file mode 100644 index 0000000000000..030a6132a451a --- /dev/null +++ b/examples/src/main/python/ml/polynomial_expansion_example.py @@ -0,0 +1,43 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import PolynomialExpansion +from pyspark.mllib.linalg import Vectors +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PolynomialExpansionExample") + sqlContext = SQLContext(sc) + + # $example on$ + df = sqlContext.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) + for expanded in polyDF.select("polyFeatures").take(3): + print(expanded) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/rformula_example.py b/examples/src/main/python/ml/rformula_example.py new file mode 100644 index 0000000000000..b544a14700762 --- /dev/null +++ b/examples/src/main/python/ml/rformula_example.py @@ -0,0 +1,44 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import RFormula +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="RFormulaExample") + sqlContext = SQLContext(sc) + + # $example on$ + dataset = sqlContext.createDataFrame( + [(7, "US", 18, 1.0), + (8, "CA", 12, 0.0), + (9, "NZ", 15, 0.0)], + ["id", "country", "hour", "clicked"]) + formula = RFormula( + formula="clicked ~ country + hour", + featuresCol="features", + labelCol="label") + output = formula.fit(dataset).transform(dataset) + output.select("features", "label").show() + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/standard_scaler_example.py b/examples/src/main/python/ml/standard_scaler_example.py new file mode 100644 index 0000000000000..139acecbfb53f --- /dev/null +++ b/examples/src/main/python/ml/standard_scaler_example.py @@ -0,0 +1,42 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import StandardScaler +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="StandardScalerExample") + sqlContext = SQLContext(sc) + + # $example on$ + dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + scaler = StandardScaler(inputCol="features", outputCol="scaledFeatures", + withStd=True, withMean=False) + + # Compute summary statistics by fitting the StandardScaler + scalerModel = scaler.fit(dataFrame) + + # Normalize each feature to have unit standard deviation. + scaledData = scalerModel.transform(dataFrame) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/stopwords_remover_example.py b/examples/src/main/python/ml/stopwords_remover_example.py new file mode 100644 index 0000000000000..01f94af8ca752 --- /dev/null +++ b/examples/src/main/python/ml/stopwords_remover_example.py @@ -0,0 +1,40 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import StopWordsRemover +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="StopWordsRemoverExample") + sqlContext = SQLContext(sc) + + # $example on$ + sentenceData = sqlContext.createDataFrame([ + (0, ["I", "saw", "the", "red", "baloon"]), + (1, ["Mary", "had", "a", "little", "lamb"]) + ], ["label", "raw"]) + + remover = StopWordsRemover(inputCol="raw", outputCol="filtered") + remover.transform(sentenceData).show(truncate=False) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/string_indexer_example.py b/examples/src/main/python/ml/string_indexer_example.py new file mode 100644 index 0000000000000..58a8cb5d56b73 --- /dev/null +++ b/examples/src/main/python/ml/string_indexer_example.py @@ -0,0 +1,39 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import StringIndexer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="StringIndexerExample") + sqlContext = SQLContext(sc) + + # $example on$ + df = sqlContext.createDataFrame( + [(0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")], + ["id", "category"]) + indexer = StringIndexer(inputCol="category", outputCol="categoryIndex") + indexed = indexer.fit(df).transform(df) + indexed.show() + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/tokenizer_example.py b/examples/src/main/python/ml/tokenizer_example.py new file mode 100644 index 0000000000000..ce9b225be5357 --- /dev/null +++ b/examples/src/main/python/ml/tokenizer_example.py @@ -0,0 +1,44 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import Tokenizer, RegexTokenizer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="TokenizerExample") + sqlContext = SQLContext(sc) + + # $example on$ + sentenceDataFrame = sqlContext.createDataFrame([ + (0, "Hi I heard about Spark"), + (1, "I wish Java could use case classes"), + (2, "Logistic,regression,models,are,neat") + ], ["label", "sentence"]) + tokenizer = Tokenizer(inputCol="sentence", outputCol="words") + wordsDataFrame = tokenizer.transform(sentenceDataFrame) + for words_label in wordsDataFrame.select("words", "label").take(3): + print(words_label) + regexTokenizer = RegexTokenizer(inputCol="sentence", outputCol="words", pattern="\\W") + # alternatively, pattern="\\w+", gaps(False) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/vector_assembler_example.py b/examples/src/main/python/ml/vector_assembler_example.py new file mode 100644 index 0000000000000..04f64839f188d --- /dev/null +++ b/examples/src/main/python/ml/vector_assembler_example.py @@ -0,0 +1,42 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.mllib.linalg import Vectors +from pyspark.ml.feature import VectorAssembler +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="VectorAssemblerExample") + sqlContext = SQLContext(sc) + + # $example on$ + dataset = sqlContext.createDataFrame( + [(0, 18, 1.0, Vectors.dense([0.0, 10.0, 0.5]), 1.0)], + ["id", "hour", "mobile", "userFeatures", "clicked"]) + assembler = VectorAssembler( + inputCols=["hour", "mobile", "userFeatures"], + outputCol="features") + output = assembler.transform(dataset) + print(output.select("features", "clicked").first()) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/ml/vector_indexer_example.py b/examples/src/main/python/ml/vector_indexer_example.py new file mode 100644 index 0000000000000..cc00d1454f2e0 --- /dev/null +++ b/examples/src/main/python/ml/vector_indexer_example.py @@ -0,0 +1,39 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import VectorIndexer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="VectorIndexerExample") + sqlContext = SQLContext(sc) + + # $example on$ + data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + indexer = VectorIndexer(inputCol="features", outputCol="indexed", maxCategories=10) + indexerModel = indexer.fit(data) + + # Create new column "indexed" with categorical values transformed to indices + indexedData = indexerModel.transform(data) + # $example off$ + + sc.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala new file mode 100644 index 0000000000000..e724aa587294b --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala @@ -0,0 +1,48 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.Binarizer +// $example off$ +import org.apache.spark.sql.{DataFrame, SQLContext} +import org.apache.spark.{SparkConf, SparkContext} + +object BinarizerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("BinarizerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + // $example on$ + val data = Array((0, 0.1), (1, 0.8), (2, 0.2)) + val dataFrame: DataFrame = sqlContext.createDataFrame(data).toDF("label", "feature") + + val binarizer: Binarizer = new Binarizer() + .setInputCol("feature") + .setOutputCol("binarized_feature") + .setThreshold(0.5) + + val binarizedDataFrame = binarizer.transform(dataFrame) + val binarizedFeatures = binarizedDataFrame.select("binarized_feature") + binarizedFeatures.collect().foreach(println) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/BucketizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/BucketizerExample.scala new file mode 100644 index 0000000000000..30c2776d39688 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/BucketizerExample.scala @@ -0,0 +1,51 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.Bucketizer +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object BucketizerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("BucketizerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val splits = Array(Double.NegativeInfinity, -0.5, 0.0, 0.5, Double.PositiveInfinity) + + val data = Array(-0.5, -0.3, 0.0, 0.2) + val dataFrame = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") + + val bucketizer = new Bucketizer() + .setInputCol("features") + .setOutputCol("bucketedFeatures") + .setSplits(splits) + + // Transform original data into its bucket index. + val bucketedData = bucketizer.transform(dataFrame) + // $example off$ + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/DCTExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/DCTExample.scala new file mode 100644 index 0000000000000..314c2c28a2a10 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/DCTExample.scala @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.DCT +import org.apache.spark.mllib.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object DCTExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("DCTExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val data = Seq( + Vectors.dense(0.0, 1.0, -2.0, 3.0), + Vectors.dense(-1.0, 2.0, 4.0, -7.0), + Vectors.dense(14.0, -2.0, -5.0, 1.0)) + + val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") + + val dct = new DCT() + .setInputCol("features") + .setOutputCol("featuresDCT") + .setInverse(false) + + val dctDf = dct.transform(df) + dctDf.select("featuresDCT").show(3) + // $example off$ + sc.stop() + } +} +// scalastyle:on println + 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 new file mode 100644 index 0000000000000..ac50bb7b2b155 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/ElementWiseProductExample.scala @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.ElementwiseProduct +import org.apache.spark.mllib.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object ElementwiseProductExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("ElementwiseProductExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + // Create some vector data; also works for sparse vectors + val dataFrame = sqlContext.createDataFrame(Seq( + ("a", Vectors.dense(1.0, 2.0, 3.0)), + ("b", Vectors.dense(4.0, 5.0, 6.0)))).toDF("id", "vector") + + val transformingVector = Vectors.dense(0.0, 1.0, 2.0) + val transformer = new ElementwiseProduct() + .setScalingVec(transformingVector) + .setInputCol("vector") + .setOutputCol("transformedVector") + + // Batch transform the vectors to create new column: + transformer.transform(dataFrame).show() + // $example off$ + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala new file mode 100644 index 0000000000000..dac3679a5bf7e --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala @@ -0,0 +1,49 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.MinMaxScaler +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object MinMaxScalerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("MinMaxScalerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + + val scaler = new MinMaxScaler() + .setInputCol("features") + .setOutputCol("scaledFeatures") + + // Compute summary statistics and generate MinMaxScalerModel + val scalerModel = scaler.fit(dataFrame) + + // rescale each feature to range [min, max]. + val scaledData = scalerModel.transform(dataFrame) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/NGramExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/NGramExample.scala new file mode 100644 index 0000000000000..8a85f71b56f3d --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/NGramExample.scala @@ -0,0 +1,47 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.NGram +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object NGramExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("NGramExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val wordDataFrame = sqlContext.createDataFrame(Seq( + (0, Array("Hi", "I", "heard", "about", "Spark")), + (1, Array("I", "wish", "Java", "could", "use", "case", "classes")), + (2, Array("Logistic", "regression", "models", "are", "neat")) + )).toDF("label", "words") + + val ngram = new NGram().setInputCol("words").setOutputCol("ngrams") + val ngramDataFrame = ngram.transform(wordDataFrame) + ngramDataFrame.take(3).map(_.getAs[Stream[String]]("ngrams").toList).foreach(println) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala new file mode 100644 index 0000000000000..17571f0aad793 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala @@ -0,0 +1,50 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.Normalizer +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object NormalizerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("NormalizerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + + // Normalize each Vector using $L^1$ norm. + val normalizer = new Normalizer() + .setInputCol("features") + .setOutputCol("normFeatures") + .setP(1.0) + + val l1NormData = normalizer.transform(dataFrame) + + // Normalize each Vector using $L^\infty$ norm. + val lInfNormData = normalizer.transform(dataFrame, normalizer.p -> Double.PositiveInfinity) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/OneHotEncoderExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/OneHotEncoderExample.scala new file mode 100644 index 0000000000000..4512736943dd5 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/OneHotEncoderExample.scala @@ -0,0 +1,58 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.{OneHotEncoder, StringIndexer} +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object OneHotEncoderExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("OneHotEncoderExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val df = sqlContext.createDataFrame(Seq( + (0, "a"), + (1, "b"), + (2, "c"), + (3, "a"), + (4, "a"), + (5, "c") + )).toDF("id", "category") + + val indexer = new StringIndexer() + .setInputCol("category") + .setOutputCol("categoryIndex") + .fit(df) + val indexed = indexer.transform(df) + + val encoder = new OneHotEncoder().setInputCol("categoryIndex"). + setOutputCol("categoryVec") + val encoded = encoder.transform(indexed) + encoded.select("id", "categoryVec").foreach(println) + // $example off$ + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala new file mode 100644 index 0000000000000..a18d4f33973d8 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.PCA +import org.apache.spark.mllib.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object PCAExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("PCAExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val data = Array( + Vectors.sparse(5, Seq((1, 1.0), (3, 7.0))), + Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0), + Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0) + ) + val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") + val pca = new PCA() + .setInputCol("features") + .setOutputCol("pcaFeatures") + .setK(3) + .fit(df) + val pcaDF = pca.transform(df) + val result = pcaDF.select("pcaFeatures") + result.show() + // $example off$ + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala new file mode 100644 index 0000000000000..b8e9e6952a5ea --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.PolynomialExpansion +import org.apache.spark.mllib.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object PolynomialExpansionExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("PolynomialExpansionExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val data = Array( + Vectors.dense(-2.0, 2.3), + Vectors.dense(0.0, 0.0), + Vectors.dense(0.6, -1.1) + ) + val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features") + val polynomialExpansion = new PolynomialExpansion() + .setInputCol("features") + .setOutputCol("polyFeatures") + .setDegree(3) + val polyDF = polynomialExpansion.transform(df) + polyDF.select("polyFeatures").take(3).foreach(println) + // $example off$ + sc.stop() + } +} +// scalastyle:on println + + diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/RFormulaExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/RFormulaExample.scala new file mode 100644 index 0000000000000..286866edea502 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/RFormulaExample.scala @@ -0,0 +1,49 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.RFormula +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object RFormulaExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("RFormulaExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val dataset = sqlContext.createDataFrame(Seq( + (7, "US", 18, 1.0), + (8, "CA", 12, 0.0), + (9, "NZ", 15, 0.0) + )).toDF("id", "country", "hour", "clicked") + val formula = new RFormula() + .setFormula("clicked ~ country + hour") + .setFeaturesCol("features") + .setLabelCol("label") + val output = formula.fit(dataset).transform(dataset) + output.select("features", "label").show() + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/StandardScalerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/StandardScalerExample.scala new file mode 100644 index 0000000000000..646ce0f13ecf5 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/StandardScalerExample.scala @@ -0,0 +1,51 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.StandardScaler +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object StandardScalerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("StandardScalerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + + val scaler = new StandardScaler() + .setInputCol("features") + .setOutputCol("scaledFeatures") + .setWithStd(true) + .setWithMean(false) + + // Compute summary statistics by fitting the StandardScaler. + val scalerModel = scaler.fit(dataFrame) + + // Normalize each feature to have unit standard deviation. + val scaledData = scalerModel.transform(dataFrame) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/StopWordsRemoverExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/StopWordsRemoverExample.scala new file mode 100644 index 0000000000000..655ffce08d3ab --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/StopWordsRemoverExample.scala @@ -0,0 +1,48 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.StopWordsRemover +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object StopWordsRemoverExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("StopWordsRemoverExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val remover = new StopWordsRemover() + .setInputCol("raw") + .setOutputCol("filtered") + + val dataSet = sqlContext.createDataFrame(Seq( + (0, Seq("I", "saw", "the", "red", "baloon")), + (1, Seq("Mary", "had", "a", "little", "lamb")) + )).toDF("id", "raw") + + remover.transform(dataSet).show() + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/StringIndexerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/StringIndexerExample.scala new file mode 100644 index 0000000000000..1be8a5f33f7c0 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/StringIndexerExample.scala @@ -0,0 +1,49 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.StringIndexer +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object StringIndexerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("StringIndexerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val df = sqlContext.createDataFrame( + Seq((0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")) + ).toDF("id", "category") + + val indexer = new StringIndexer() + .setInputCol("category") + .setOutputCol("categoryIndex") + + val indexed = indexer.fit(df).transform(df) + indexed.show() + // $example off$ + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/TokenizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/TokenizerExample.scala new file mode 100644 index 0000000000000..01e0d1388a2f4 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/TokenizerExample.scala @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.{RegexTokenizer, Tokenizer} +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object TokenizerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("TokenizerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val sentenceDataFrame = sqlContext.createDataFrame(Seq( + (0, "Hi I heard about Spark"), + (1, "I wish Java could use case classes"), + (2, "Logistic,regression,models,are,neat") + )).toDF("label", "sentence") + + val tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words") + val regexTokenizer = new RegexTokenizer() + .setInputCol("sentence") + .setOutputCol("words") + .setPattern("\\W") // alternatively .setPattern("\\w+").setGaps(false) + + val tokenized = tokenizer.transform(sentenceDataFrame) + tokenized.select("words", "label").take(3).foreach(println) + val regexTokenized = regexTokenizer.transform(sentenceDataFrame) + regexTokenized.select("words", "label").take(3).foreach(println) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/VectorAssemblerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/VectorAssemblerExample.scala new file mode 100644 index 0000000000000..d527924419f81 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/VectorAssemblerExample.scala @@ -0,0 +1,49 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.VectorAssembler +import org.apache.spark.mllib.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object VectorAssemblerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("VectorAssemblerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val dataset = sqlContext.createDataFrame( + Seq((0, 18, 1.0, Vectors.dense(0.0, 10.0, 0.5), 1.0)) + ).toDF("id", "hour", "mobile", "userFeatures", "clicked") + + val assembler = new VectorAssembler() + .setInputCols(Array("hour", "mobile", "userFeatures")) + .setOutputCol("features") + + val output = assembler.transform(dataset) + println(output.select("features", "clicked").first()) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/VectorIndexerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/VectorIndexerExample.scala new file mode 100644 index 0000000000000..14279d610fda8 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/VectorIndexerExample.scala @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.VectorIndexer +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object VectorIndexerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("VectorIndexerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + + val indexer = new VectorIndexer() + .setInputCol("features") + .setOutputCol("indexed") + .setMaxCategories(10) + + val indexerModel = indexer.fit(data) + + val categoricalFeatures: Set[Int] = indexerModel.categoryMaps.keys.toSet + println(s"Chose ${categoricalFeatures.size} categorical features: " + + categoricalFeatures.mkString(", ")) + + // Create new column "indexed" with categorical values transformed to indices + val indexedData = indexerModel.transform(data) + // $example off$ + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/VectorSlicerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/VectorSlicerExample.scala new file mode 100644 index 0000000000000..04f19829eff87 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/VectorSlicerExample.scala @@ -0,0 +1,58 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.attribute.{Attribute, AttributeGroup, NumericAttribute} +import org.apache.spark.ml.feature.VectorSlicer +import org.apache.spark.mllib.linalg.Vectors +import org.apache.spark.sql.Row +import org.apache.spark.sql.types.StructType +// $example off$ +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkConf, SparkContext} + +object VectorSlicerExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("VectorSlicerExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val data = Array(Row(Vectors.dense(-2.0, 2.3, 0.0))) + + val defaultAttr = NumericAttribute.defaultAttr + val attrs = Array("f1", "f2", "f3").map(defaultAttr.withName) + val attrGroup = new AttributeGroup("userFeatures", attrs.asInstanceOf[Array[Attribute]]) + + val dataRDD = sc.parallelize(data) + val dataset = sqlContext.createDataFrame(dataRDD, StructType(Array(attrGroup.toStructField()))) + + val slicer = new VectorSlicer().setInputCol("userFeatures").setOutputCol("features") + + slicer.setIndices(Array(1)).setNames(Array("f3")) + // or slicer.setIndices(Array(1, 2)), or slicer.setNames(Array("f2", "f3")) + + val output = slicer.transform(dataset) + println(output.select("userFeatures", "features").first()) + // $example off$ + sc.stop() + } +} +// scalastyle:on println