From 98c614d66275d36308400e2b6dde842c5cfe37ad Mon Sep 17 00:00:00 2001 From: Rishabh Bhardwaj Date: Fri, 13 Nov 2015 08:36:46 -0800 Subject: [PATCH] [SPARK-11445][DOCS] Replaced example code in mllib-ensembles.md using include_example I have made the required changes and tested. Kindly review the changes. Author: Rishabh Bhardwaj Closes #9407 from rishabhbhardwaj/SPARK-11445. (cherry picked from commit 61a28486ccbcdd37461419df958aea222c8b9f09) Signed-off-by: Xiangrui Meng --- docs/mllib-ensembles.md | 526 +----------------- ...GradientBoostingClassificationExample.java | 92 +++ ...JavaGradientBoostingRegressionExample.java | 96 ++++ ...JavaRandomForestClassificationExample.java | 89 +++ .../JavaRandomForestRegressionExample.java | 95 ++++ ...radient_boosting_classification_example.py | 57 ++ .../gradient_boosting_regression_example.py | 57 ++ .../random_forest_classification_example.py | 58 ++ .../mllib/random_forest_regression_example.py | 59 ++ ...radientBoostingClassificationExample.scala | 69 +++ .../GradientBoostingRegressionExample.scala | 66 +++ .../RandomForestClassificationExample.scala | 67 +++ .../mllib/RandomForestRegressionExample.scala | 68 +++ 13 files changed, 885 insertions(+), 514 deletions(-) create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java create mode 100644 examples/src/main/python/mllib/gradient_boosting_classification_example.py create mode 100644 examples/src/main/python/mllib/gradient_boosting_regression_example.py create mode 100644 examples/src/main/python/mllib/random_forest_classification_example.py create mode 100644 examples/src/main/python/mllib/random_forest_regression_example.py create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala diff --git a/docs/mllib-ensembles.md b/docs/mllib-ensembles.md index fc587298f7d2e..50450e05d2abb 100644 --- a/docs/mllib-ensembles.md +++ b/docs/mllib-ensembles.md @@ -98,144 +98,19 @@ The test error is calculated to measure the algorithm accuracy.
Refer to the [`RandomForest` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.RandomForest) and [`RandomForestModel` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.model.RandomForestModel) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.tree.RandomForest -import org.apache.spark.mllib.tree.model.RandomForestModel -import org.apache.spark.mllib.util.MLUtils - -// Load and parse the data file. -val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") -// Split the data into training and test sets (30% held out for testing) -val splits = data.randomSplit(Array(0.7, 0.3)) -val (trainingData, testData) = (splits(0), splits(1)) - -// Train a RandomForest model. -// Empty categoricalFeaturesInfo indicates all features are continuous. -val numClasses = 2 -val categoricalFeaturesInfo = Map[Int, Int]() -val numTrees = 3 // Use more in practice. -val featureSubsetStrategy = "auto" // Let the algorithm choose. -val impurity = "gini" -val maxDepth = 4 -val maxBins = 32 - -val model = RandomForest.trainClassifier(trainingData, numClasses, categoricalFeaturesInfo, - numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins) - -// Evaluate model on test instances and compute test error -val labelAndPreds = testData.map { point => - val prediction = model.predict(point.features) - (point.label, prediction) -} -val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count() -println("Test Error = " + testErr) -println("Learned classification forest model:\n" + model.toDebugString) - -// Save and load model -model.save(sc, "myModelPath") -val sameModel = RandomForestModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala %}
Refer to the [`RandomForest` Java docs](api/java/org/apache/spark/mllib/tree/RandomForest.html) and [`RandomForestModel` Java docs](api/java/org/apache/spark/mllib/tree/model/RandomForestModel.html) for details on the API. -{% highlight java %} -import scala.Tuple2; -import java.util.HashMap; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaPairRDD; -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.api.java.function.Function; -import org.apache.spark.api.java.function.PairFunction; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.mllib.tree.RandomForest; -import org.apache.spark.mllib.tree.model.RandomForestModel; -import org.apache.spark.mllib.util.MLUtils; - -SparkConf sparkConf = new SparkConf().setAppName("JavaRandomForestClassification"); -JavaSparkContext sc = new JavaSparkContext(sparkConf); - -// Load and parse the data file. -String datapath = "data/mllib/sample_libsvm_data.txt"; -JavaRDD data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD(); -// Split the data into training and test sets (30% held out for testing) -JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); -JavaRDD trainingData = splits[0]; -JavaRDD testData = splits[1]; - -// Train a RandomForest model. -// Empty categoricalFeaturesInfo indicates all features are continuous. -Integer numClasses = 2; -HashMap categoricalFeaturesInfo = new HashMap(); -Integer numTrees = 3; // Use more in practice. -String featureSubsetStrategy = "auto"; // Let the algorithm choose. -String impurity = "gini"; -Integer maxDepth = 5; -Integer maxBins = 32; -Integer seed = 12345; - -final RandomForestModel model = RandomForest.trainClassifier(trainingData, numClasses, - categoricalFeaturesInfo, numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins, - seed); - -// Evaluate model on test instances and compute test error -JavaPairRDD predictionAndLabel = - testData.mapToPair(new PairFunction() { - @Override - public Tuple2 call(LabeledPoint p) { - return new Tuple2(model.predict(p.features()), p.label()); - } - }); -Double testErr = - 1.0 * predictionAndLabel.filter(new Function, Boolean>() { - @Override - public Boolean call(Tuple2 pl) { - return !pl._1().equals(pl._2()); - } - }).count() / testData.count(); -System.out.println("Test Error: " + testErr); -System.out.println("Learned classification forest model:\n" + model.toDebugString()); - -// Save and load model -model.save(sc.sc(), "myModelPath"); -RandomForestModel sameModel = RandomForestModel.load(sc.sc(), "myModelPath"); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java %}
Refer to the [`RandomForest` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.RandomForest) and [`RandomForest` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.RandomForestModel) for more details on the API. -{% highlight python %} -from pyspark.mllib.tree import RandomForest, RandomForestModel -from pyspark.mllib.util import MLUtils - -# Load and parse the data file into an RDD of LabeledPoint. -data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt') -# Split the data into training and test sets (30% held out for testing) -(trainingData, testData) = data.randomSplit([0.7, 0.3]) - -# Train a RandomForest model. -# Empty categoricalFeaturesInfo indicates all features are continuous. -# Note: Use larger numTrees in practice. -# Setting featureSubsetStrategy="auto" lets the algorithm choose. -model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={}, - numTrees=3, featureSubsetStrategy="auto", - impurity='gini', maxDepth=4, maxBins=32) - -# Evaluate model on test instances and compute test error -predictions = model.predict(testData.map(lambda x: x.features)) -labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) -testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count()) -print('Test Error = ' + str(testErr)) -print('Learned classification forest model:') -print(model.toDebugString()) - -# Save and load model -model.save(sc, "myModelPath") -sameModel = RandomForestModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example python/mllib/random_forest_classification_example.py %}
@@ -254,147 +129,19 @@ The Mean Squared Error (MSE) is computed at the end to evaluate
Refer to the [`RandomForest` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.RandomForest) and [`RandomForestModel` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.model.RandomForestModel) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.tree.RandomForest -import org.apache.spark.mllib.tree.model.RandomForestModel -import org.apache.spark.mllib.util.MLUtils - -// Load and parse the data file. -val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") -// Split the data into training and test sets (30% held out for testing) -val splits = data.randomSplit(Array(0.7, 0.3)) -val (trainingData, testData) = (splits(0), splits(1)) - -// Train a RandomForest model. -// Empty categoricalFeaturesInfo indicates all features are continuous. -val numClasses = 2 -val categoricalFeaturesInfo = Map[Int, Int]() -val numTrees = 3 // Use more in practice. -val featureSubsetStrategy = "auto" // Let the algorithm choose. -val impurity = "variance" -val maxDepth = 4 -val maxBins = 32 - -val model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo, - numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins) - -// Evaluate model on test instances and compute test error -val labelsAndPredictions = testData.map { point => - val prediction = model.predict(point.features) - (point.label, prediction) -} -val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean() -println("Test Mean Squared Error = " + testMSE) -println("Learned regression forest model:\n" + model.toDebugString) - -// Save and load model -model.save(sc, "myModelPath") -val sameModel = RandomForestModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala %}
Refer to the [`RandomForest` Java docs](api/java/org/apache/spark/mllib/tree/RandomForest.html) and [`RandomForestModel` Java docs](api/java/org/apache/spark/mllib/tree/model/RandomForestModel.html) for details on the API. -{% highlight java %} -import java.util.HashMap; -import scala.Tuple2; -import org.apache.spark.api.java.function.Function2; -import org.apache.spark.api.java.JavaPairRDD; -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.api.java.function.Function; -import org.apache.spark.api.java.function.PairFunction; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.mllib.tree.RandomForest; -import org.apache.spark.mllib.tree.model.RandomForestModel; -import org.apache.spark.mllib.util.MLUtils; -import org.apache.spark.SparkConf; - -SparkConf sparkConf = new SparkConf().setAppName("JavaRandomForest"); -JavaSparkContext sc = new JavaSparkContext(sparkConf); - -// Load and parse the data file. -String datapath = "data/mllib/sample_libsvm_data.txt"; -JavaRDD data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD(); -// Split the data into training and test sets (30% held out for testing) -JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); -JavaRDD trainingData = splits[0]; -JavaRDD testData = splits[1]; - -// Set parameters. -// Empty categoricalFeaturesInfo indicates all features are continuous. -Map categoricalFeaturesInfo = new HashMap(); -String impurity = "variance"; -Integer maxDepth = 4; -Integer maxBins = 32; - -// Train a RandomForest model. -final RandomForestModel model = RandomForest.trainRegressor(trainingData, - categoricalFeaturesInfo, impurity, maxDepth, maxBins); - -// Evaluate model on test instances and compute test error -JavaPairRDD predictionAndLabel = - testData.mapToPair(new PairFunction() { - @Override - public Tuple2 call(LabeledPoint p) { - return new Tuple2(model.predict(p.features()), p.label()); - } - }); -Double testMSE = - predictionAndLabel.map(new Function, Double>() { - @Override - public Double call(Tuple2 pl) { - Double diff = pl._1() - pl._2(); - return diff * diff; - } - }).reduce(new Function2() { - @Override - public Double call(Double a, Double b) { - return a + b; - } - }) / testData.count(); -System.out.println("Test Mean Squared Error: " + testMSE); -System.out.println("Learned regression forest model:\n" + model.toDebugString()); - -// Save and load model -model.save(sc.sc(), "myModelPath"); -RandomForestModel sameModel = RandomForestModel.load(sc.sc(), "myModelPath"); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java %}
Refer to the [`RandomForest` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.RandomForest) and [`RandomForest` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.RandomForestModel) for more details on the API. -{% highlight python %} -from pyspark.mllib.tree import RandomForest, RandomForestModel -from pyspark.mllib.util import MLUtils - -# Load and parse the data file into an RDD of LabeledPoint. -data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt') -# Split the data into training and test sets (30% held out for testing) -(trainingData, testData) = data.randomSplit([0.7, 0.3]) - -# Train a RandomForest model. -# Empty categoricalFeaturesInfo indicates all features are continuous. -# Note: Use larger numTrees in practice. -# Setting featureSubsetStrategy="auto" lets the algorithm choose. -model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo={}, - numTrees=3, featureSubsetStrategy="auto", - impurity='variance', maxDepth=4, maxBins=32) - -# Evaluate model on test instances and compute test error -predictions = model.predict(testData.map(lambda x: x.features)) -labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) -testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(testData.count()) -print('Test Mean Squared Error = ' + str(testMSE)) -print('Learned regression forest model:') -print(model.toDebugString()) - -# Save and load model -model.save(sc, "myModelPath") -sameModel = RandomForestModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example python/mllib/random_forest_regression_example.py %}
@@ -492,141 +239,19 @@ The test error is calculated to measure the algorithm accuracy.
Refer to the [`GradientBoostedTrees` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.GradientBoostedTrees) and [`GradientBoostedTreesModel` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.model.GradientBoostedTreesModel) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.tree.GradientBoostedTrees -import org.apache.spark.mllib.tree.configuration.BoostingStrategy -import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel -import org.apache.spark.mllib.util.MLUtils - -// Load and parse the data file. -val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") -// Split the data into training and test sets (30% held out for testing) -val splits = data.randomSplit(Array(0.7, 0.3)) -val (trainingData, testData) = (splits(0), splits(1)) - -// Train a GradientBoostedTrees model. -// The defaultParams for Classification use LogLoss by default. -val boostingStrategy = BoostingStrategy.defaultParams("Classification") -boostingStrategy.numIterations = 3 // Note: Use more iterations in practice. -boostingStrategy.treeStrategy.numClasses = 2 -boostingStrategy.treeStrategy.maxDepth = 5 -// Empty categoricalFeaturesInfo indicates all features are continuous. -boostingStrategy.treeStrategy.categoricalFeaturesInfo = Map[Int, Int]() - -val model = GradientBoostedTrees.train(trainingData, boostingStrategy) - -// Evaluate model on test instances and compute test error -val labelAndPreds = testData.map { point => - val prediction = model.predict(point.features) - (point.label, prediction) -} -val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count() -println("Test Error = " + testErr) -println("Learned classification GBT model:\n" + model.toDebugString) - -// Save and load model -model.save(sc, "myModelPath") -val sameModel = GradientBoostedTreesModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala %}
Refer to the [`GradientBoostedTrees` Java docs](api/java/org/apache/spark/mllib/tree/GradientBoostedTrees.html) and [`GradientBoostedTreesModel` Java docs](api/java/org/apache/spark/mllib/tree/model/GradientBoostedTreesModel.html) for details on the API. -{% highlight java %} -import scala.Tuple2; -import java.util.HashMap; -import java.util.Map; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaPairRDD; -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.api.java.function.Function; -import org.apache.spark.api.java.function.PairFunction; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.mllib.tree.GradientBoostedTrees; -import org.apache.spark.mllib.tree.configuration.BoostingStrategy; -import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel; -import org.apache.spark.mllib.util.MLUtils; - -SparkConf sparkConf = new SparkConf().setAppName("JavaGradientBoostedTrees"); -JavaSparkContext sc = new JavaSparkContext(sparkConf); - -// Load and parse the data file. -String datapath = "data/mllib/sample_libsvm_data.txt"; -JavaRDD data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD(); -// Split the data into training and test sets (30% held out for testing) -JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); -JavaRDD trainingData = splits[0]; -JavaRDD testData = splits[1]; - -// Train a GradientBoostedTrees model. -// The defaultParams for Classification use LogLoss by default. -BoostingStrategy boostingStrategy = BoostingStrategy.defaultParams("Classification"); -boostingStrategy.setNumIterations(3); // Note: Use more iterations in practice. -boostingStrategy.getTreeStrategy().setNumClassesForClassification(2); -boostingStrategy.getTreeStrategy().setMaxDepth(5); -// Empty categoricalFeaturesInfo indicates all features are continuous. -Map categoricalFeaturesInfo = new HashMap(); -boostingStrategy.treeStrategy().setCategoricalFeaturesInfo(categoricalFeaturesInfo); - -final GradientBoostedTreesModel model = - GradientBoostedTrees.train(trainingData, boostingStrategy); - -// Evaluate model on test instances and compute test error -JavaPairRDD predictionAndLabel = - testData.mapToPair(new PairFunction() { - @Override - public Tuple2 call(LabeledPoint p) { - return new Tuple2(model.predict(p.features()), p.label()); - } - }); -Double testErr = - 1.0 * predictionAndLabel.filter(new Function, Boolean>() { - @Override - public Boolean call(Tuple2 pl) { - return !pl._1().equals(pl._2()); - } - }).count() / testData.count(); -System.out.println("Test Error: " + testErr); -System.out.println("Learned classification GBT model:\n" + model.toDebugString()); - -// Save and load model -model.save(sc.sc(), "myModelPath"); -GradientBoostedTreesModel sameModel = GradientBoostedTreesModel.load(sc.sc(), "myModelPath"); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java %}
Refer to the [`GradientBoostedTrees` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.GradientBoostedTrees) and [`GradientBoostedTreesModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.GradientBoostedTreesModel) for more details on the API. -{% highlight python %} -from pyspark.mllib.tree import GradientBoostedTrees, GradientBoostedTreesModel -from pyspark.mllib.util import MLUtils - -# Load and parse the data file. -data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") -# Split the data into training and test sets (30% held out for testing) -(trainingData, testData) = data.randomSplit([0.7, 0.3]) - -# Train a GradientBoostedTrees model. -# Notes: (a) Empty categoricalFeaturesInfo indicates all features are continuous. -# (b) Use more iterations in practice. -model = GradientBoostedTrees.trainClassifier(trainingData, - categoricalFeaturesInfo={}, numIterations=3) - -# Evaluate model on test instances and compute test error -predictions = model.predict(testData.map(lambda x: x.features)) -labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) -testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count()) -print('Test Error = ' + str(testErr)) -print('Learned classification GBT model:') -print(model.toDebugString()) - -# Save and load model -model.save(sc, "myModelPath") -sameModel = GradientBoostedTreesModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example python/mllib/gradient_boosting_classification_example.py %}
@@ -645,146 +270,19 @@ The Mean Squared Error (MSE) is computed at the end to evaluate
Refer to the [`GradientBoostedTrees` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.GradientBoostedTrees) and [`GradientBoostedTreesModel` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.model.GradientBoostedTreesModel) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.tree.GradientBoostedTrees -import org.apache.spark.mllib.tree.configuration.BoostingStrategy -import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel -import org.apache.spark.mllib.util.MLUtils - -// Load and parse the data file. -val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") -// Split the data into training and test sets (30% held out for testing) -val splits = data.randomSplit(Array(0.7, 0.3)) -val (trainingData, testData) = (splits(0), splits(1)) - -// Train a GradientBoostedTrees model. -// The defaultParams for Regression use SquaredError by default. -val boostingStrategy = BoostingStrategy.defaultParams("Regression") -boostingStrategy.numIterations = 3 // Note: Use more iterations in practice. -boostingStrategy.treeStrategy.maxDepth = 5 -// Empty categoricalFeaturesInfo indicates all features are continuous. -boostingStrategy.treeStrategy.categoricalFeaturesInfo = Map[Int, Int]() - -val model = GradientBoostedTrees.train(trainingData, boostingStrategy) - -// Evaluate model on test instances and compute test error -val labelsAndPredictions = testData.map { point => - val prediction = model.predict(point.features) - (point.label, prediction) -} -val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean() -println("Test Mean Squared Error = " + testMSE) -println("Learned regression GBT model:\n" + model.toDebugString) - -// Save and load model -model.save(sc, "myModelPath") -val sameModel = GradientBoostedTreesModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala %}
Refer to the [`GradientBoostedTrees` Java docs](api/java/org/apache/spark/mllib/tree/GradientBoostedTrees.html) and [`GradientBoostedTreesModel` Java docs](api/java/org/apache/spark/mllib/tree/model/GradientBoostedTreesModel.html) for details on the API. -{% highlight java %} -import scala.Tuple2; -import java.util.HashMap; -import java.util.Map; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.function.Function2; -import org.apache.spark.api.java.JavaPairRDD; -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.api.java.function.Function; -import org.apache.spark.api.java.function.PairFunction; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.mllib.tree.GradientBoostedTrees; -import org.apache.spark.mllib.tree.configuration.BoostingStrategy; -import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel; -import org.apache.spark.mllib.util.MLUtils; - -SparkConf sparkConf = new SparkConf().setAppName("JavaGradientBoostedTrees"); -JavaSparkContext sc = new JavaSparkContext(sparkConf); - -// Load and parse the data file. -String datapath = "data/mllib/sample_libsvm_data.txt"; -JavaRDD data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD(); -// Split the data into training and test sets (30% held out for testing) -JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); -JavaRDD trainingData = splits[0]; -JavaRDD testData = splits[1]; - -// Train a GradientBoostedTrees model. -// The defaultParams for Regression use SquaredError by default. -BoostingStrategy boostingStrategy = BoostingStrategy.defaultParams("Regression"); -boostingStrategy.setNumIterations(3); // Note: Use more iterations in practice. -boostingStrategy.getTreeStrategy().setMaxDepth(5); -// Empty categoricalFeaturesInfo indicates all features are continuous. -Map categoricalFeaturesInfo = new HashMap(); -boostingStrategy.treeStrategy().setCategoricalFeaturesInfo(categoricalFeaturesInfo); - -final GradientBoostedTreesModel model = - GradientBoostedTrees.train(trainingData, boostingStrategy); - -// Evaluate model on test instances and compute test error -JavaPairRDD predictionAndLabel = - testData.mapToPair(new PairFunction() { - @Override - public Tuple2 call(LabeledPoint p) { - return new Tuple2(model.predict(p.features()), p.label()); - } - }); -Double testMSE = - predictionAndLabel.map(new Function, Double>() { - @Override - public Double call(Tuple2 pl) { - Double diff = pl._1() - pl._2(); - return diff * diff; - } - }).reduce(new Function2() { - @Override - public Double call(Double a, Double b) { - return a + b; - } - }) / data.count(); -System.out.println("Test Mean Squared Error: " + testMSE); -System.out.println("Learned regression GBT model:\n" + model.toDebugString()); - -// Save and load model -model.save(sc.sc(), "myModelPath"); -GradientBoostedTreesModel sameModel = GradientBoostedTreesModel.load(sc.sc(), "myModelPath"); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java %}
Refer to the [`GradientBoostedTrees` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.GradientBoostedTrees) and [`GradientBoostedTreesModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.GradientBoostedTreesModel) for more details on the API. -{% highlight python %} -from pyspark.mllib.tree import GradientBoostedTrees, GradientBoostedTreesModel -from pyspark.mllib.util import MLUtils - -# Load and parse the data file. -data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") -# Split the data into training and test sets (30% held out for testing) -(trainingData, testData) = data.randomSplit([0.7, 0.3]) - -# Train a GradientBoostedTrees model. -# Notes: (a) Empty categoricalFeaturesInfo indicates all features are continuous. -# (b) Use more iterations in practice. -model = GradientBoostedTrees.trainRegressor(trainingData, - categoricalFeaturesInfo={}, numIterations=3) - -# Evaluate model on test instances and compute test error -predictions = model.predict(testData.map(lambda x: x.features)) -labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) -testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(testData.count()) -print('Test Mean Squared Error = ' + str(testMSE)) -print('Learned regression GBT model:') -print(model.toDebugString()) - -# Save and load model -model.save(sc, "myModelPath") -sameModel = GradientBoostedTreesModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example python/mllib/gradient_boosting_regression_example.py %}
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java new file mode 100644 index 0000000000000..80faabd2325d0 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java @@ -0,0 +1,92 @@ +/* + * 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.mllib; + +// $example on$ +import java.util.HashMap; +import java.util.Map; + +import scala.Tuple2; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.api.java.function.PairFunction; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.tree.GradientBoostedTrees; +import org.apache.spark.mllib.tree.configuration.BoostingStrategy; +import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel; +import org.apache.spark.mllib.util.MLUtils; +// $example off$ + +public class JavaGradientBoostingClassificationExample { + public static void main(String[] args) { + // $example on$ + SparkConf sparkConf = new SparkConf() + .setAppName("JavaGradientBoostedTreesClassificationExample"); + JavaSparkContext jsc = new JavaSparkContext(sparkConf); + + // Load and parse the data file. + String datapath = "data/mllib/sample_libsvm_data.txt"; + JavaRDD data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD(); + // Split the data into training and test sets (30% held out for testing) + JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); + JavaRDD trainingData = splits[0]; + JavaRDD testData = splits[1]; + + // Train a GradientBoostedTrees model. + // The defaultParams for Classification use LogLoss by default. + BoostingStrategy boostingStrategy = BoostingStrategy.defaultParams("Classification"); + boostingStrategy.setNumIterations(3); // Note: Use more iterations in practice. + boostingStrategy.getTreeStrategy().setNumClasses(2); + boostingStrategy.getTreeStrategy().setMaxDepth(5); + // Empty categoricalFeaturesInfo indicates all features are continuous. + Map categoricalFeaturesInfo = new HashMap(); + boostingStrategy.treeStrategy().setCategoricalFeaturesInfo(categoricalFeaturesInfo); + + final GradientBoostedTreesModel model = + GradientBoostedTrees.train(trainingData, boostingStrategy); + + // Evaluate model on test instances and compute test error + JavaPairRDD predictionAndLabel = + testData.mapToPair(new PairFunction() { + @Override + public Tuple2 call(LabeledPoint p) { + return new Tuple2(model.predict(p.features()), p.label()); + } + }); + Double testErr = + 1.0 * predictionAndLabel.filter(new Function, Boolean>() { + @Override + public Boolean call(Tuple2 pl) { + return !pl._1().equals(pl._2()); + } + }).count() / testData.count(); + System.out.println("Test Error: " + testErr); + System.out.println("Learned classification GBT model:\n" + model.toDebugString()); + + // Save and load model + model.save(jsc.sc(), "target/tmp/myGradientBoostingClassificationModel"); + GradientBoostedTreesModel sameModel = GradientBoostedTreesModel.load(jsc.sc(), + "target/tmp/myGradientBoostingClassificationModel"); + // $example off$ + } + +} diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java new file mode 100644 index 0000000000000..216895b368202 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java @@ -0,0 +1,96 @@ +/* + * 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.mllib; + +// $example on$ +import java.util.HashMap; +import java.util.Map; + +import scala.Tuple2; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.api.java.function.PairFunction; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.tree.GradientBoostedTrees; +import org.apache.spark.mllib.tree.configuration.BoostingStrategy; +import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel; +import org.apache.spark.mllib.util.MLUtils; +// $example off$ + +public class JavaGradientBoostingRegressionExample { + public static void main(String[] args) { + // $example on$ + SparkConf sparkConf = new SparkConf() + .setAppName("JavaGradientBoostedTreesRegressionExample"); + JavaSparkContext jsc = new JavaSparkContext(sparkConf); + // Load and parse the data file. + String datapath = "data/mllib/sample_libsvm_data.txt"; + JavaRDD data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD(); + // Split the data into training and test sets (30% held out for testing) + JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); + JavaRDD trainingData = splits[0]; + JavaRDD testData = splits[1]; + + // Train a GradientBoostedTrees model. + // The defaultParams for Regression use SquaredError by default. + BoostingStrategy boostingStrategy = BoostingStrategy.defaultParams("Regression"); + boostingStrategy.setNumIterations(3); // Note: Use more iterations in practice. + boostingStrategy.getTreeStrategy().setMaxDepth(5); + // Empty categoricalFeaturesInfo indicates all features are continuous. + Map categoricalFeaturesInfo = new HashMap(); + boostingStrategy.treeStrategy().setCategoricalFeaturesInfo(categoricalFeaturesInfo); + + final GradientBoostedTreesModel model = + GradientBoostedTrees.train(trainingData, boostingStrategy); + + // Evaluate model on test instances and compute test error + JavaPairRDD predictionAndLabel = + testData.mapToPair(new PairFunction() { + @Override + public Tuple2 call(LabeledPoint p) { + return new Tuple2(model.predict(p.features()), p.label()); + } + }); + Double testMSE = + predictionAndLabel.map(new Function, Double>() { + @Override + public Double call(Tuple2 pl) { + Double diff = pl._1() - pl._2(); + return diff * diff; + } + }).reduce(new Function2() { + @Override + public Double call(Double a, Double b) { + return a + b; + } + }) / data.count(); + System.out.println("Test Mean Squared Error: " + testMSE); + System.out.println("Learned regression GBT model:\n" + model.toDebugString()); + + // Save and load model + model.save(jsc.sc(), "target/tmp/myGradientBoostingRegressionModel"); + GradientBoostedTreesModel sameModel = GradientBoostedTreesModel.load(jsc.sc(), + "target/tmp/myGradientBoostingRegressionModel"); + // $example off$ + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java new file mode 100644 index 0000000000000..9219eef1ad2d6 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java @@ -0,0 +1,89 @@ +/* + * 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.mllib; + +// $example on$ +import java.util.HashMap; + +import scala.Tuple2; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.api.java.function.PairFunction; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.tree.RandomForest; +import org.apache.spark.mllib.tree.model.RandomForestModel; +import org.apache.spark.mllib.util.MLUtils; +// $example off$ + +public class JavaRandomForestClassificationExample { + public static void main(String[] args) { + // $example on$ + SparkConf sparkConf = new SparkConf().setAppName("JavaRandomForestClassificationExample"); + JavaSparkContext jsc = new JavaSparkContext(sparkConf); + // Load and parse the data file. + String datapath = "data/mllib/sample_libsvm_data.txt"; + JavaRDD data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD(); + // Split the data into training and test sets (30% held out for testing) + JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); + JavaRDD trainingData = splits[0]; + JavaRDD testData = splits[1]; + + // Train a RandomForest model. + // Empty categoricalFeaturesInfo indicates all features are continuous. + Integer numClasses = 2; + HashMap categoricalFeaturesInfo = new HashMap(); + Integer numTrees = 3; // Use more in practice. + String featureSubsetStrategy = "auto"; // Let the algorithm choose. + String impurity = "gini"; + Integer maxDepth = 5; + Integer maxBins = 32; + Integer seed = 12345; + + final RandomForestModel model = RandomForest.trainClassifier(trainingData, numClasses, + categoricalFeaturesInfo, numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins, + seed); + + // Evaluate model on test instances and compute test error + JavaPairRDD predictionAndLabel = + testData.mapToPair(new PairFunction() { + @Override + public Tuple2 call(LabeledPoint p) { + return new Tuple2(model.predict(p.features()), p.label()); + } + }); + Double testErr = + 1.0 * predictionAndLabel.filter(new Function, Boolean>() { + @Override + public Boolean call(Tuple2 pl) { + return !pl._1().equals(pl._2()); + } + }).count() / testData.count(); + System.out.println("Test Error: " + testErr); + System.out.println("Learned classification forest model:\n" + model.toDebugString()); + + // Save and load model + model.save(jsc.sc(), "target/tmp/myRandomForestClassificationModel"); + RandomForestModel sameModel = RandomForestModel.load(jsc.sc(), + "target/tmp/myRandomForestClassificationModel"); + // $example off$ + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java new file mode 100644 index 0000000000000..4db926a4218ff --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java @@ -0,0 +1,95 @@ +/* + * 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.mllib; + +// $example on$ +import java.util.HashMap; +import java.util.Map; + +import scala.Tuple2; + +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.api.java.function.PairFunction; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.tree.RandomForest; +import org.apache.spark.mllib.tree.model.RandomForestModel; +import org.apache.spark.mllib.util.MLUtils; +import org.apache.spark.SparkConf; +// $example off$ + +public class JavaRandomForestRegressionExample { + public static void main(String[] args) { + // $example on$ + SparkConf sparkConf = new SparkConf().setAppName("JavaRandomForestRegressionExample"); + JavaSparkContext jsc = new JavaSparkContext(sparkConf); + // Load and parse the data file. + String datapath = "data/mllib/sample_libsvm_data.txt"; + JavaRDD data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD(); + // Split the data into training and test sets (30% held out for testing) + JavaRDD[] splits = data.randomSplit(new double[]{0.7, 0.3}); + JavaRDD trainingData = splits[0]; + JavaRDD testData = splits[1]; + + // Set parameters. + // Empty categoricalFeaturesInfo indicates all features are continuous. + Map categoricalFeaturesInfo = new HashMap(); + Integer numTrees = 3; // Use more in practice. + String featureSubsetStrategy = "auto"; // Let the algorithm choose. + String impurity = "variance"; + Integer maxDepth = 4; + Integer maxBins = 32; + Integer seed = 12345; + // Train a RandomForest model. + final RandomForestModel model = RandomForest.trainRegressor(trainingData, + categoricalFeaturesInfo, numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins, seed); + + // Evaluate model on test instances and compute test error + JavaPairRDD predictionAndLabel = + testData.mapToPair(new PairFunction() { + @Override + public Tuple2 call(LabeledPoint p) { + return new Tuple2(model.predict(p.features()), p.label()); + } + }); + Double testMSE = + predictionAndLabel.map(new Function, Double>() { + @Override + public Double call(Tuple2 pl) { + Double diff = pl._1() - pl._2(); + return diff * diff; + } + }).reduce(new Function2() { + @Override + public Double call(Double a, Double b) { + return a + b; + } + }) / testData.count(); + System.out.println("Test Mean Squared Error: " + testMSE); + System.out.println("Learned regression forest model:\n" + model.toDebugString()); + + // Save and load model + model.save(jsc.sc(), "target/tmp/myRandomForestRegressionModel"); + RandomForestModel sameModel = RandomForestModel.load(jsc.sc(), + "target/tmp/myRandomForestRegressionModel"); + // $example off$ + } +} diff --git a/examples/src/main/python/mllib/gradient_boosting_classification_example.py b/examples/src/main/python/mllib/gradient_boosting_classification_example.py new file mode 100644 index 0000000000000..a94ea0d582e59 --- /dev/null +++ b/examples/src/main/python/mllib/gradient_boosting_classification_example.py @@ -0,0 +1,57 @@ +# +# 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. +# + +""" +Gradient Boosted Trees Classification Example. +""" +from __future__ import print_function + +import sys + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.tree import GradientBoostedTrees, GradientBoostedTreesModel +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PythonGradientBoostedTreesClassificationExample") + # $example on$ + # Load and parse the data file. + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") + # Split the data into training and test sets (30% held out for testing) + (trainingData, testData) = data.randomSplit([0.7, 0.3]) + + # Train a GradientBoostedTrees model. + # Notes: (a) Empty categoricalFeaturesInfo indicates all features are continuous. + # (b) Use more iterations in practice. + model = GradientBoostedTrees.trainClassifier(trainingData, + categoricalFeaturesInfo={}, numIterations=3) + + # Evaluate model on test instances and compute test error + predictions = model.predict(testData.map(lambda x: x.features)) + labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) + testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count()) + print('Test Error = ' + str(testErr)) + print('Learned classification GBT model:') + print(model.toDebugString()) + + # Save and load model + model.save(sc, "target/tmp/myGradientBoostingClassificationModel") + sameModel = GradientBoostedTreesModel.load(sc, + "target/tmp/myGradientBoostingClassificationModel") + # $example off$ diff --git a/examples/src/main/python/mllib/gradient_boosting_regression_example.py b/examples/src/main/python/mllib/gradient_boosting_regression_example.py new file mode 100644 index 0000000000000..86040799dc1d9 --- /dev/null +++ b/examples/src/main/python/mllib/gradient_boosting_regression_example.py @@ -0,0 +1,57 @@ +# +# 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. +# + +""" +Gradient Boosted Trees Regression Example. +""" +from __future__ import print_function + +import sys + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.tree import GradientBoostedTrees, GradientBoostedTreesModel +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PythonGradientBoostedTreesRegressionExample") + # $example on$ + # Load and parse the data file. + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") + # Split the data into training and test sets (30% held out for testing) + (trainingData, testData) = data.randomSplit([0.7, 0.3]) + + # Train a GradientBoostedTrees model. + # Notes: (a) Empty categoricalFeaturesInfo indicates all features are continuous. + # (b) Use more iterations in practice. + model = GradientBoostedTrees.trainRegressor(trainingData, + categoricalFeaturesInfo={}, numIterations=3) + + # Evaluate model on test instances and compute test error + predictions = model.predict(testData.map(lambda x: x.features)) + labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) + testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() /\ + float(testData.count()) + print('Test Mean Squared Error = ' + str(testMSE)) + print('Learned regression GBT model:') + print(model.toDebugString()) + + # Save and load model + model.save(sc, "target/tmp/myGradientBoostingRegressionModel") + sameModel = GradientBoostedTreesModel.load(sc, "target/tmp/myGradientBoostingRegressionModel") + # $example off$ diff --git a/examples/src/main/python/mllib/random_forest_classification_example.py b/examples/src/main/python/mllib/random_forest_classification_example.py new file mode 100644 index 0000000000000..324ba50625d25 --- /dev/null +++ b/examples/src/main/python/mllib/random_forest_classification_example.py @@ -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. +# + +""" +Random Forest Classification Example. +""" +from __future__ import print_function + +import sys + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.tree import RandomForest, RandomForestModel +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PythonRandomForestClassificationExample") + # $example on$ + # Load and parse the data file into an RDD of LabeledPoint. + data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt') + # Split the data into training and test sets (30% held out for testing) + (trainingData, testData) = data.randomSplit([0.7, 0.3]) + + # Train a RandomForest model. + # Empty categoricalFeaturesInfo indicates all features are continuous. + # Note: Use larger numTrees in practice. + # Setting featureSubsetStrategy="auto" lets the algorithm choose. + model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={}, + numTrees=3, featureSubsetStrategy="auto", + impurity='gini', maxDepth=4, maxBins=32) + + # Evaluate model on test instances and compute test error + predictions = model.predict(testData.map(lambda x: x.features)) + labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) + testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count()) + print('Test Error = ' + str(testErr)) + print('Learned classification forest model:') + print(model.toDebugString()) + + # Save and load model + model.save(sc, "target/tmp/myRandomForestClassificationModel") + sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestClassificationModel") + # $example off$ diff --git a/examples/src/main/python/mllib/random_forest_regression_example.py b/examples/src/main/python/mllib/random_forest_regression_example.py new file mode 100644 index 0000000000000..f7aa6114eceb3 --- /dev/null +++ b/examples/src/main/python/mllib/random_forest_regression_example.py @@ -0,0 +1,59 @@ +# +# 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. +# + +""" +Random Forest Regression Example. +""" +from __future__ import print_function + +import sys + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.tree import RandomForest, RandomForestModel +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PythonRandomForestRegressionExample") + # $example on$ + # Load and parse the data file into an RDD of LabeledPoint. + data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt') + # Split the data into training and test sets (30% held out for testing) + (trainingData, testData) = data.randomSplit([0.7, 0.3]) + + # Train a RandomForest model. + # Empty categoricalFeaturesInfo indicates all features are continuous. + # Note: Use larger numTrees in practice. + # Setting featureSubsetStrategy="auto" lets the algorithm choose. + model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo={}, + numTrees=3, featureSubsetStrategy="auto", + impurity='variance', maxDepth=4, maxBins=32) + + # Evaluate model on test instances and compute test error + predictions = model.predict(testData.map(lambda x: x.features)) + labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions) + testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() /\ + float(testData.count()) + print('Test Mean Squared Error = ' + str(testMSE)) + print('Learned regression forest model:') + print(model.toDebugString()) + + # Save and load model + model.save(sc, "target/tmp/myRandomForestRegressionModel") + sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestRegressionModel") + # $example off$ diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala new file mode 100644 index 0000000000000..139e1f909bdce --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala @@ -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. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkContext, SparkConf} +// $example on$ +import org.apache.spark.mllib.tree.GradientBoostedTrees +import org.apache.spark.mllib.tree.configuration.BoostingStrategy +import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel +import org.apache.spark.mllib.util.MLUtils +// $example off$ + +object GradientBoostingClassificationExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("GradientBoostedTreesClassificationExample") + val sc = new SparkContext(conf) + // $example on$ + // Load and parse the data file. + val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") + // Split the data into training and test sets (30% held out for testing) + val splits = data.randomSplit(Array(0.7, 0.3)) + val (trainingData, testData) = (splits(0), splits(1)) + + // Train a GradientBoostedTrees model. + // The defaultParams for Classification use LogLoss by default. + val boostingStrategy = BoostingStrategy.defaultParams("Classification") + boostingStrategy.numIterations = 3 // Note: Use more iterations in practice. + boostingStrategy.treeStrategy.numClasses = 2 + boostingStrategy.treeStrategy.maxDepth = 5 + // Empty categoricalFeaturesInfo indicates all features are continuous. + boostingStrategy.treeStrategy.categoricalFeaturesInfo = Map[Int, Int]() + + val model = GradientBoostedTrees.train(trainingData, boostingStrategy) + + // Evaluate model on test instances and compute test error + val labelAndPreds = testData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) + } + val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count() + println("Test Error = " + testErr) + println("Learned classification GBT model:\n" + model.toDebugString) + + // Save and load model + model.save(sc, "target/tmp/myGradientBoostingClassificationModel") + val sameModel = GradientBoostedTreesModel.load(sc, + "target/tmp/myGradientBoostingClassificationModel") + // $example off$ + } +} +// scalastyle:on println + + diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala new file mode 100644 index 0000000000000..3dc86da8e4d2b --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala @@ -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. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkContext, SparkConf} +// $example on$ +import org.apache.spark.mllib.tree.GradientBoostedTrees +import org.apache.spark.mllib.tree.configuration.BoostingStrategy +import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel +import org.apache.spark.mllib.util.MLUtils +// $example off$ + +object GradientBoostingRegressionExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("GradientBoostedTreesRegressionExample") + val sc = new SparkContext(conf) + // $example on$ + // Load and parse the data file. + val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") + // Split the data into training and test sets (30% held out for testing) + val splits = data.randomSplit(Array(0.7, 0.3)) + val (trainingData, testData) = (splits(0), splits(1)) + + // Train a GradientBoostedTrees model. + // The defaultParams for Regression use SquaredError by default. + val boostingStrategy = BoostingStrategy.defaultParams("Regression") + boostingStrategy.numIterations = 3 // Note: Use more iterations in practice. + boostingStrategy.treeStrategy.maxDepth = 5 + // Empty categoricalFeaturesInfo indicates all features are continuous. + boostingStrategy.treeStrategy.categoricalFeaturesInfo = Map[Int, Int]() + + val model = GradientBoostedTrees.train(trainingData, boostingStrategy) + + // Evaluate model on test instances and compute test error + val labelsAndPredictions = testData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) + } + val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean() + println("Test Mean Squared Error = " + testMSE) + println("Learned regression GBT model:\n" + model.toDebugString) + + // Save and load model + model.save(sc, "target/tmp/myGradientBoostingRegressionModel") + val sameModel = GradientBoostedTreesModel.load(sc, + "target/tmp/myGradientBoostingRegressionModel") + // $example off$ + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala new file mode 100644 index 0000000000000..5e55abd5121c4 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala @@ -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. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkContext, SparkConf} +// $example on$ +import org.apache.spark.mllib.tree.RandomForest +import org.apache.spark.mllib.tree.model.RandomForestModel +import org.apache.spark.mllib.util.MLUtils +// $example off$ + +object RandomForestClassificationExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("RandomForestClassificationExample") + val sc = new SparkContext(conf) + // $example on$ + // Load and parse the data file. + val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") + // Split the data into training and test sets (30% held out for testing) + val splits = data.randomSplit(Array(0.7, 0.3)) + val (trainingData, testData) = (splits(0), splits(1)) + + // Train a RandomForest model. + // Empty categoricalFeaturesInfo indicates all features are continuous. + val numClasses = 2 + val categoricalFeaturesInfo = Map[Int, Int]() + val numTrees = 3 // Use more in practice. + val featureSubsetStrategy = "auto" // Let the algorithm choose. + val impurity = "gini" + val maxDepth = 4 + val maxBins = 32 + + val model = RandomForest.trainClassifier(trainingData, numClasses, categoricalFeaturesInfo, + numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins) + + // Evaluate model on test instances and compute test error + val labelAndPreds = testData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) + } + val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count() + println("Test Error = " + testErr) + println("Learned classification forest model:\n" + model.toDebugString) + + // Save and load model + model.save(sc, "target/tmp/myRandomForestClassificationModel") + val sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestClassificationModel") + // $example off$ + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala new file mode 100644 index 0000000000000..a54fb3ab7e37a --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala @@ -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. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkContext, SparkConf} +// $example on$ +import org.apache.spark.mllib.tree.RandomForest +import org.apache.spark.mllib.tree.model.RandomForestModel +import org.apache.spark.mllib.util.MLUtils +// $example off$ + +object RandomForestRegressionExample { + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("RandomForestRegressionExample") + val sc = new SparkContext(conf) + // $example on$ + // Load and parse the data file. + val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") + // Split the data into training and test sets (30% held out for testing) + val splits = data.randomSplit(Array(0.7, 0.3)) + val (trainingData, testData) = (splits(0), splits(1)) + + // Train a RandomForest model. + // Empty categoricalFeaturesInfo indicates all features are continuous. + val numClasses = 2 + val categoricalFeaturesInfo = Map[Int, Int]() + val numTrees = 3 // Use more in practice. + val featureSubsetStrategy = "auto" // Let the algorithm choose. + val impurity = "variance" + val maxDepth = 4 + val maxBins = 32 + + val model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo, + numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins) + + // Evaluate model on test instances and compute test error + val labelsAndPredictions = testData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) + } + val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean() + println("Test Mean Squared Error = " + testMSE) + println("Learned regression forest model:\n" + model.toDebugString) + + // Save and load model + model.save(sc, "target/tmp/myRandomForestRegressionModel") + val sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestRegressionModel") + // $example off$ + } +} +// scalastyle:on println +