diff options
Diffstat (limited to 'examples/src/main/python/mllib')
-rwxr-xr-x | examples/src/main/python/mllib/decision_tree_runner.py | 17 | ||||
-rwxr-xr-x | examples/src/main/python/mllib/random_forest_example.py | 89 |
2 files changed, 99 insertions, 7 deletions
diff --git a/examples/src/main/python/mllib/decision_tree_runner.py b/examples/src/main/python/mllib/decision_tree_runner.py index 61ea4e06ec..fccabd841b 100755 --- a/examples/src/main/python/mllib/decision_tree_runner.py +++ b/examples/src/main/python/mllib/decision_tree_runner.py @@ -106,8 +106,7 @@ def reindexClassLabels(data): def usage(): print >> sys.stderr, \ - "Usage: decision_tree_runner [libsvm format data filepath]\n" + \ - " Note: This only supports binary classification." + "Usage: decision_tree_runner [libsvm format data filepath]" exit(1) @@ -127,16 +126,20 @@ if __name__ == "__main__": # Re-index class labels if needed. (reindexedData, origToNewLabels) = reindexClassLabels(points) + numClasses = len(origToNewLabels) # Train a classifier. categoricalFeaturesInfo = {} # no categorical features - model = DecisionTree.trainClassifier(reindexedData, numClasses=2, + model = DecisionTree.trainClassifier(reindexedData, numClasses=numClasses, categoricalFeaturesInfo=categoricalFeaturesInfo) # Print learned tree and stats. print "Trained DecisionTree for classification:" - print " Model numNodes: %d\n" % model.numNodes() - print " Model depth: %d\n" % model.depth() - print " Training accuracy: %g\n" % getAccuracy(model, reindexedData) - print model + print " Model numNodes: %d" % model.numNodes() + print " Model depth: %d" % model.depth() + print " Training accuracy: %g" % getAccuracy(model, reindexedData) + if model.numNodes() < 20: + print model.toDebugString() + else: + print model sc.stop() diff --git a/examples/src/main/python/mllib/random_forest_example.py b/examples/src/main/python/mllib/random_forest_example.py new file mode 100755 index 0000000000..d3c24f7664 --- /dev/null +++ b/examples/src/main/python/mllib/random_forest_example.py @@ -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. +# + +""" +Random Forest classification and regression using MLlib. + +Note: This example illustrates binary classification. + For information on multiclass classification, please refer to the decision_tree_runner.py + example. +""" + +import sys + +from pyspark.context import SparkContext +from pyspark.mllib.tree import RandomForest +from pyspark.mllib.util import MLUtils + + +def testClassification(trainingData, testData): + # 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()) + + +def testRegression(trainingData, testData): + # 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()) + + +if __name__ == "__main__": + if len(sys.argv) > 1: + print >> sys.stderr, "Usage: random_forest_example" + exit(1) + sc = SparkContext(appName="PythonRandomForestExample") + + # 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]) + + print('\nRunning example of classification using RandomForest\n') + testClassification(trainingData, testData) + + print('\nRunning example of regression using RandomForest\n') + testRegression(trainingData, testData) + + sc.stop() |