From 61a28486ccbcdd37461419df958aea222c8b9f09 Mon Sep 17 00:00:00 2001 From: Rishabh Bhardwaj Date: Fri, 13 Nov 2015 08:36:46 -0800 Subject: [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. --- .../gradient_boosting_classification_example.py | 57 +++++++++++++++++++++ .../mllib/gradient_boosting_regression_example.py | 57 +++++++++++++++++++++ .../mllib/random_forest_classification_example.py | 58 +++++++++++++++++++++ .../mllib/random_forest_regression_example.py | 59 ++++++++++++++++++++++ 4 files changed, 231 insertions(+) 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 (limited to 'examples/src/main/python') 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 0000000000..a94ea0d582 --- /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 0000000000..86040799dc --- /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 0000000000..324ba50625 --- /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 0000000000..f7aa6114ec --- /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") + # $example off$ -- cgit v1.2.3