Repository: spark Updated Branches: refs/heads/branch-1.6 39c1ebcd3 -> 6c1409e0b
[SPARK-11382] Replace example code in mllib-decision-tree.md using include_example https://issues.apache.org/jira/browse/SPARK-11382 B.T.W. I fix an error in naive_bayes_example.py. Author: Xusen Yin <yinxu...@gmail.com> Closes #9596 from yinxusen/SPARK-11382. (cherry picked from commit a81f47ff7498e7063c855ccf75bba81ab101b43e) Signed-off-by: Xiangrui Meng <m...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/6c1409e0 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/6c1409e0 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/6c1409e0 Branch: refs/heads/branch-1.6 Commit: 6c1409e0b57cb0202c434a9f6c2593e5ae241e70 Parents: 39c1ebc Author: Xusen Yin <yinxu...@gmail.com> Authored: Tue Nov 10 10:05:53 2015 -0800 Committer: Xiangrui Meng <m...@databricks.com> Committed: Tue Nov 10 10:06:02 2015 -0800 ---------------------------------------------------------------------- docs/mllib-decision-tree.md | 253 +------------------ .../JavaDecisionTreeClassificationExample.java | 91 +++++++ .../JavaDecisionTreeRegressionExample.java | 96 +++++++ .../decision_tree_classification_example.py | 55 ++++ .../mllib/decision_tree_regression_example.py | 56 ++++ .../main/python/mllib/naive_bayes_example.py | 1 + .../DecisionTreeClassificationExample.scala | 67 +++++ .../mllib/DecisionTreeRegressionExample.scala | 66 +++++ 8 files changed, 438 insertions(+), 247 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/docs/mllib-decision-tree.md ---------------------------------------------------------------------- diff --git a/docs/mllib-decision-tree.md b/docs/mllib-decision-tree.md index b5b454b..77ce34e 100644 --- a/docs/mllib-decision-tree.md +++ b/docs/mllib-decision-tree.md @@ -194,137 +194,19 @@ maximum tree depth of 5. The test error is calculated to measure the algorithm a <div data-lang="scala" markdown="1"> Refer to the [`DecisionTree` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.DecisionTree) and [`DecisionTreeModel` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.model.DecisionTreeModel) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.tree.DecisionTree -import org.apache.spark.mllib.tree.model.DecisionTreeModel -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 DecisionTree model. -// Empty categoricalFeaturesInfo indicates all features are continuous. -val numClasses = 2 -val categoricalFeaturesInfo = Map[Int, Int]() -val impurity = "gini" -val maxDepth = 5 -val maxBins = 32 - -val model = DecisionTree.trainClassifier(trainingData, numClasses, categoricalFeaturesInfo, - 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 tree model:\n" + model.toDebugString) - -// Save and load model -model.save(sc, "myModelPath") -val sameModel = DecisionTreeModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala %} </div> <div data-lang="java" markdown="1"> Refer to the [`DecisionTree` Java docs](api/java/org/apache/spark/mllib/tree/DecisionTree.html) and [`DecisionTreeModel` Java docs](api/java/org/apache/spark/mllib/tree/model/DecisionTreeModel.html) for details on the API. -{% highlight java %} -import java.util.HashMap; -import scala.Tuple2; -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.DecisionTree; -import org.apache.spark.mllib.tree.model.DecisionTreeModel; -import org.apache.spark.mllib.util.MLUtils; -import org.apache.spark.SparkConf; - -SparkConf sparkConf = new SparkConf().setAppName("JavaDecisionTree"); -JavaSparkContext sc = new JavaSparkContext(sparkConf); - -// Load and parse the data file. -String datapath = "data/mllib/sample_libsvm_data.txt"; -JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD(); -// Split the data into training and test sets (30% held out for testing) -JavaRDD<LabeledPoint>[] splits = data.randomSplit(new double[]{0.7, 0.3}); -JavaRDD<LabeledPoint> trainingData = splits[0]; -JavaRDD<LabeledPoint> testData = splits[1]; - -// Set parameters. -// Empty categoricalFeaturesInfo indicates all features are continuous. -Integer numClasses = 2; -Map<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>(); -String impurity = "gini"; -Integer maxDepth = 5; -Integer maxBins = 32; - -// Train a DecisionTree model for classification. -final DecisionTreeModel model = DecisionTree.trainClassifier(trainingData, numClasses, - categoricalFeaturesInfo, impurity, maxDepth, maxBins); - -// Evaluate model on test instances and compute test error -JavaPairRDD<Double, Double> predictionAndLabel = - testData.mapToPair(new PairFunction<LabeledPoint, Double, Double>() { - @Override - public Tuple2<Double, Double> call(LabeledPoint p) { - return new Tuple2<Double, Double>(model.predict(p.features()), p.label()); - } - }); -Double testErr = - 1.0 * predictionAndLabel.filter(new Function<Tuple2<Double, Double>, Boolean>() { - @Override - public Boolean call(Tuple2<Double, Double> pl) { - return !pl._1().equals(pl._2()); - } - }).count() / testData.count(); -System.out.println("Test Error: " + testErr); -System.out.println("Learned classification tree model:\n" + model.toDebugString()); - -// Save and load model -model.save(sc.sc(), "myModelPath"); -DecisionTreeModel sameModel = DecisionTreeModel.load(sc.sc(), "myModelPath"); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java %} </div> <div data-lang="python" markdown="1"> Refer to the [`DecisionTree` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.DecisionTree) and [`DecisionTreeModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.DecisionTreeModel) for more details on the API. -{% highlight python %} -from pyspark.mllib.regression import LabeledPoint -from pyspark.mllib.tree import DecisionTree, DecisionTreeModel -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 DecisionTree model. -# Empty categoricalFeaturesInfo indicates all features are continuous. -model = DecisionTree.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={}, - impurity='gini', maxDepth=5, 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 tree model:') -print(model.toDebugString()) - -# Save and load model -model.save(sc, "myModelPath") -sameModel = DecisionTreeModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example python/mllib/decision_tree_classification_example.py %} </div> </div> @@ -343,142 +225,19 @@ depth of 5. The Mean Squared Error (MSE) is computed at the end to evaluate <div data-lang="scala" markdown="1"> Refer to the [`DecisionTree` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.DecisionTree) and [`DecisionTreeModel` Scala docs](api/scala/index.html#org.apache.spark.mllib.tree.model.DecisionTreeModel) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.tree.DecisionTree -import org.apache.spark.mllib.tree.model.DecisionTreeModel -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 DecisionTree model. -// Empty categoricalFeaturesInfo indicates all features are continuous. -val categoricalFeaturesInfo = Map[Int, Int]() -val impurity = "variance" -val maxDepth = 5 -val maxBins = 32 - -val model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo, 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 tree model:\n" + model.toDebugString) - -// Save and load model -model.save(sc, "myModelPath") -val sameModel = DecisionTreeModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala %} </div> <div data-lang="java" markdown="1"> Refer to the [`DecisionTree` Java docs](api/java/org/apache/spark/mllib/tree/DecisionTree.html) and [`DecisionTreeModel` Java docs](api/java/org/apache/spark/mllib/tree/model/DecisionTreeModel.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.DecisionTree; -import org.apache.spark.mllib.tree.model.DecisionTreeModel; -import org.apache.spark.mllib.util.MLUtils; -import org.apache.spark.SparkConf; - -SparkConf sparkConf = new SparkConf().setAppName("JavaDecisionTree"); -JavaSparkContext sc = new JavaSparkContext(sparkConf); - -// Load and parse the data file. -String datapath = "data/mllib/sample_libsvm_data.txt"; -JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD(); -// Split the data into training and test sets (30% held out for testing) -JavaRDD<LabeledPoint>[] splits = data.randomSplit(new double[]{0.7, 0.3}); -JavaRDD<LabeledPoint> trainingData = splits[0]; -JavaRDD<LabeledPoint> testData = splits[1]; - -// Set parameters. -// Empty categoricalFeaturesInfo indicates all features are continuous. -Map<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>(); -String impurity = "variance"; -Integer maxDepth = 5; -Integer maxBins = 32; - -// Train a DecisionTree model. -final DecisionTreeModel model = DecisionTree.trainRegressor(trainingData, - categoricalFeaturesInfo, impurity, maxDepth, maxBins); - -// Evaluate model on test instances and compute test error -JavaPairRDD<Double, Double> predictionAndLabel = - testData.mapToPair(new PairFunction<LabeledPoint, Double, Double>() { - @Override - public Tuple2<Double, Double> call(LabeledPoint p) { - return new Tuple2<Double, Double>(model.predict(p.features()), p.label()); - } - }); -Double testMSE = - predictionAndLabel.map(new Function<Tuple2<Double, Double>, Double>() { - @Override - public Double call(Tuple2<Double, Double> pl) { - Double diff = pl._1() - pl._2(); - return diff * diff; - } - }).reduce(new Function2<Double, Double, Double>() { - @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 tree model:\n" + model.toDebugString()); - -// Save and load model -model.save(sc.sc(), "myModelPath"); -DecisionTreeModel sameModel = DecisionTreeModel.load(sc.sc(), "myModelPath"); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java %} </div> <div data-lang="python" markdown="1"> Refer to the [`DecisionTree` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.DecisionTree) and [`DecisionTreeModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.tree.DecisionTreeModel) for more details on the API. -{% highlight python %} -from pyspark.mllib.regression import LabeledPoint -from pyspark.mllib.tree import DecisionTree, DecisionTreeModel -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 DecisionTree model. -# Empty categoricalFeaturesInfo indicates all features are continuous. -model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={}, - impurity='variance', maxDepth=5, 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 tree model:') -print(model.toDebugString()) - -# Save and load model -model.save(sc, "myModelPath") -sameModel = DecisionTreeModel.load(sc, "myModelPath") -{% endhighlight %} +{% include_example python/mllib/decision_tree_regression_example.py %} </div> </div> http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java new file mode 100644 index 0000000..5839b0c --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java @@ -0,0 +1,91 @@ +/* + * 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.DecisionTree; +import org.apache.spark.mllib.tree.model.DecisionTreeModel; +import org.apache.spark.mllib.util.MLUtils; +// $example off$ + +class JavaDecisionTreeClassificationExample { + + public static void main(String[] args) { + + // $example on$ + SparkConf sparkConf = new SparkConf().setAppName("JavaDecisionTreeClassificationExample"); + JavaSparkContext jsc = new JavaSparkContext(sparkConf); + + // Load and parse the data file. + String datapath = "data/mllib/sample_libsvm_data.txt"; + JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD(); + // Split the data into training and test sets (30% held out for testing) + JavaRDD<LabeledPoint>[] splits = data.randomSplit(new double[]{0.7, 0.3}); + JavaRDD<LabeledPoint> trainingData = splits[0]; + JavaRDD<LabeledPoint> testData = splits[1]; + + // Set parameters. + // Empty categoricalFeaturesInfo indicates all features are continuous. + Integer numClasses = 2; + Map<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>(); + String impurity = "gini"; + Integer maxDepth = 5; + Integer maxBins = 32; + + // Train a DecisionTree model for classification. + final DecisionTreeModel model = DecisionTree.trainClassifier(trainingData, numClasses, + categoricalFeaturesInfo, impurity, maxDepth, maxBins); + + // Evaluate model on test instances and compute test error + JavaPairRDD<Double, Double> predictionAndLabel = + testData.mapToPair(new PairFunction<LabeledPoint, Double, Double>() { + @Override + public Tuple2<Double, Double> call(LabeledPoint p) { + return new Tuple2<Double, Double>(model.predict(p.features()), p.label()); + } + }); + Double testErr = + 1.0 * predictionAndLabel.filter(new Function<Tuple2<Double, Double>, Boolean>() { + @Override + public Boolean call(Tuple2<Double, Double> pl) { + return !pl._1().equals(pl._2()); + } + }).count() / testData.count(); + + System.out.println("Test Error: " + testErr); + System.out.println("Learned classification tree model:\n" + model.toDebugString()); + + // Save and load model + model.save(jsc.sc(), "target/tmp/myDecisionTreeClassificationModel"); + DecisionTreeModel sameModel = DecisionTreeModel + .load(jsc.sc(), "target/tmp/myDecisionTreeClassificationModel"); + // $example off$ + } +} http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java new file mode 100644 index 0000000..ccde578 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.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.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.Function2; +import org.apache.spark.api.java.function.PairFunction; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.tree.DecisionTree; +import org.apache.spark.mllib.tree.model.DecisionTreeModel; +import org.apache.spark.mllib.util.MLUtils; +// $example off$ + +class JavaDecisionTreeRegressionExample { + + public static void main(String[] args) { + + // $example on$ + SparkConf sparkConf = new SparkConf().setAppName("JavaDecisionTreeRegressionExample"); + JavaSparkContext jsc = new JavaSparkContext(sparkConf); + + // Load and parse the data file. + String datapath = "data/mllib/sample_libsvm_data.txt"; + JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD(); + // Split the data into training and test sets (30% held out for testing) + JavaRDD<LabeledPoint>[] splits = data.randomSplit(new double[]{0.7, 0.3}); + JavaRDD<LabeledPoint> trainingData = splits[0]; + JavaRDD<LabeledPoint> testData = splits[1]; + + // Set parameters. + // Empty categoricalFeaturesInfo indicates all features are continuous. + Map<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>(); + String impurity = "variance"; + Integer maxDepth = 5; + Integer maxBins = 32; + + // Train a DecisionTree model. + final DecisionTreeModel model = DecisionTree.trainRegressor(trainingData, + categoricalFeaturesInfo, impurity, maxDepth, maxBins); + + // Evaluate model on test instances and compute test error + JavaPairRDD<Double, Double> predictionAndLabel = + testData.mapToPair(new PairFunction<LabeledPoint, Double, Double>() { + @Override + public Tuple2<Double, Double> call(LabeledPoint p) { + return new Tuple2<Double, Double>(model.predict(p.features()), p.label()); + } + }); + Double testMSE = + predictionAndLabel.map(new Function<Tuple2<Double, Double>, Double>() { + @Override + public Double call(Tuple2<Double, Double> pl) { + Double diff = pl._1() - pl._2(); + return diff * diff; + } + }).reduce(new Function2<Double, Double, Double>() { + @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 tree model:\n" + model.toDebugString()); + + // Save and load model + model.save(jsc.sc(), "target/tmp/myDecisionTreeRegressionModel"); + DecisionTreeModel sameModel = DecisionTreeModel + .load(jsc.sc(), "target/tmp/myDecisionTreeRegressionModel"); + // $example off$ + } +} http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/python/mllib/decision_tree_classification_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/mllib/decision_tree_classification_example.py b/examples/src/main/python/mllib/decision_tree_classification_example.py new file mode 100644 index 0000000..1b52976 --- /dev/null +++ b/examples/src/main/python/mllib/decision_tree_classification_example.py @@ -0,0 +1,55 @@ +# +# 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. +# + +""" +Decision Tree Classification Example. +""" +from __future__ import print_function + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.tree import DecisionTree, DecisionTreeModel +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + + sc = SparkContext(appName="PythonDecisionTreeClassificationExample") + + # $example on$ + # 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 DecisionTree model. + # Empty categoricalFeaturesInfo indicates all features are continuous. + model = DecisionTree.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={}, + impurity='gini', maxDepth=5, 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 tree model:') + print(model.toDebugString()) + + # Save and load model + model.save(sc, "target/tmp/myDecisionTreeClassificationModel") + sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeClassificationModel") + # $example off$ http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/python/mllib/decision_tree_regression_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/mllib/decision_tree_regression_example.py b/examples/src/main/python/mllib/decision_tree_regression_example.py new file mode 100644 index 0000000..cf518ea --- /dev/null +++ b/examples/src/main/python/mllib/decision_tree_regression_example.py @@ -0,0 +1,56 @@ +# +# 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. +# + +""" +Decision Tree Regression Example. +""" +from __future__ import print_function + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.tree import DecisionTree, DecisionTreeModel +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + + sc = SparkContext(appName="PythonDecisionTreeRegressionExample") + + # $example on$ + # 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 DecisionTree model. + # Empty categoricalFeaturesInfo indicates all features are continuous. + model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={}, + impurity='variance', maxDepth=5, 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 tree model:') + print(model.toDebugString()) + + # Save and load model + model.save(sc, "target/tmp/myDecisionTreeRegressionModel") + sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeRegressionModel") + # $example off$ http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/python/mllib/naive_bayes_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/mllib/naive_bayes_example.py b/examples/src/main/python/mllib/naive_bayes_example.py index a2e7dac..f5e120c 100644 --- a/examples/src/main/python/mllib/naive_bayes_example.py +++ b/examples/src/main/python/mllib/naive_bayes_example.py @@ -20,6 +20,7 @@ NaiveBayes Example. """ from __future__ import print_function +from pyspark import SparkContext # $example on$ from pyspark.mllib.classification import NaiveBayes, NaiveBayesModel from pyspark.mllib.linalg import Vectors http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala new file mode 100644 index 0000000..d427bba --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.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 + +// $example on$ +import org.apache.spark.mllib.tree.DecisionTree +import org.apache.spark.mllib.tree.model.DecisionTreeModel +import org.apache.spark.mllib.util.MLUtils +// $example off$ +import org.apache.spark.{SparkConf, SparkContext} + +object DecisionTreeClassificationExample { + + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("DecisionTreeClassificationExample") + 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 DecisionTree model. + // Empty categoricalFeaturesInfo indicates all features are continuous. + val numClasses = 2 + val categoricalFeaturesInfo = Map[Int, Int]() + val impurity = "gini" + val maxDepth = 5 + val maxBins = 32 + + val model = DecisionTree.trainClassifier(trainingData, numClasses, categoricalFeaturesInfo, + 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 tree model:\n" + model.toDebugString) + + // Save and load model + model.save(sc, "target/tmp/myDecisionTreeClassificationModel") + val sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeClassificationModel") + // $example off$ + } +} +// scalastyle:on println http://git-wip-us.apache.org/repos/asf/spark/blob/6c1409e0/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala new file mode 100644 index 0000000..fb05e7d --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.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 + +// $example on$ +import org.apache.spark.mllib.tree.DecisionTree +import org.apache.spark.mllib.tree.model.DecisionTreeModel +import org.apache.spark.mllib.util.MLUtils +// $example off$ +import org.apache.spark.{SparkConf, SparkContext} + +object DecisionTreeRegressionExample { + + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("DecisionTreeRegressionExample") + 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 DecisionTree model. + // Empty categoricalFeaturesInfo indicates all features are continuous. + val categoricalFeaturesInfo = Map[Int, Int]() + val impurity = "variance" + val maxDepth = 5 + val maxBins = 32 + + val model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo, 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 tree model:\n" + model.toDebugString) + + // Save and load model + model.save(sc, "target/tmp/myDecisionTreeRegressionModel") + val sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeRegressionModel") + // $example off$ + } +} +// scalastyle:on println --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
