python/mllib/decision_tree_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 Decision Tree Classification Example.
0020 """
0021 from __future__ import print_function
0022
0023 from pyspark import SparkContext
0024 # $example on$
0025 from pyspark.mllib.tree import DecisionTree, DecisionTreeModel
0026 from pyspark.mllib.util import MLUtils
0027 # $example off$
0028
0029 if __name__ == "__main__":
0030
0031     sc = SparkContext(appName="PythonDecisionTreeClassificationExample")
0032
0033     # $example on$
0034     # Load and parse the data file into an RDD of LabeledPoint.
0035     data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt')
0036     # Split the data into training and test sets (30% held out for testing)
0037     (trainingData, testData) = data.randomSplit([0.7, 0.3])
0038
0039     # Train a DecisionTree model.
0040     #  Empty categoricalFeaturesInfo indicates all features are continuous.
0041     model = DecisionTree.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
0042                                          impurity='gini', maxDepth=5, maxBins=32)
0043
0044     # Evaluate model on test instances and compute test error
0045     predictions = model.predict(testData.map(lambda x: x.features))
0046     labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
0047     testErr = labelsAndPredictions.filter(
0048         lambda lp: lp[0] != lp[1]).count() / float(testData.count())
0049     print('Test Error = ' + str(testErr))
0050     print('Learned classification tree model:')
0051     print(model.toDebugString())
0052
0053     # Save and load model
0054     model.save(sc, "target/tmp/myDecisionTreeClassificationModel")
0055     sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeClassificationModel")
0056     # $example off$