python/mllib/random_forest_classification_example.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 """
0019 Random Forest Classification Example.
0020 """
0021 from __future__ import print_function
0022
0023 from pyspark import SparkContext
0024 # $example on$
0025 from pyspark.mllib.tree import RandomForest, RandomForestModel
0026 from pyspark.mllib.util import MLUtils
0027 # $example off$
0028
0029 if __name__ == "__main__":
0030     sc = SparkContext(appName="PythonRandomForestClassificationExample")
0031     # $example on$
0032     # Load and parse the data file into an RDD of LabeledPoint.
0033     data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt')
0034     # Split the data into training and test sets (30% held out for testing)
0035     (trainingData, testData) = data.randomSplit([0.7, 0.3])
0036
0037     # Train a RandomForest model.
0038     #  Empty categoricalFeaturesInfo indicates all features are continuous.
0039     #  Note: Use larger numTrees in practice.
0040     #  Setting featureSubsetStrategy="auto" lets the algorithm choose.
0041     model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
0042                                          numTrees=3, featureSubsetStrategy="auto",
0043                                          impurity='gini', maxDepth=4, maxBins=32)
0044
0045     # Evaluate model on test instances and compute test error
0046     predictions = model.predict(testData.map(lambda x: x.features))
0047     labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
0048     testErr = labelsAndPredictions.filter(
0049         lambda lp: lp[0] != lp[1]).count() / float(testData.count())
0050     print('Test Error = ' + str(testErr))
0051     print('Learned classification forest model:')
0052     print(model.toDebugString())
0053
0054     # Save and load model
0055     model.save(sc, "target/tmp/myRandomForestClassificationModel")
0056     sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestClassificationModel")
0057     # $example off$