python/mllib/gradient_boosting_regression_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 Gradient Boosted Trees Regression Example.
0020 """
0021 from __future__ import print_function
0022
0023 from pyspark import SparkContext
0024 # $example on$
0025 from pyspark.mllib.tree import GradientBoostedTrees, GradientBoostedTreesModel
0026 from pyspark.mllib.util import MLUtils
0027 # $example off$
0028
0029 if __name__ == "__main__":
0030     sc = SparkContext(appName="PythonGradientBoostedTreesRegressionExample")
0031     # $example on$
0032     # Load and parse the data file.
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 GradientBoostedTrees model.
0038     #  Notes: (a) Empty categoricalFeaturesInfo indicates all features are continuous.
0039     #         (b) Use more iterations in practice.
0040     model = GradientBoostedTrees.trainRegressor(trainingData,
0041                                                 categoricalFeaturesInfo={}, numIterations=3)
0042
0043     # Evaluate model on test instances and compute test error
0044     predictions = model.predict(testData.map(lambda x: x.features))
0045     labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
0046     testMSE = labelsAndPredictions.map(lambda lp: (lp[0] - lp[1]) * (lp[0] - lp[1])).sum() /\
0047         float(testData.count())
0048     print('Test Mean Squared Error = ' + str(testMSE))
0049     print('Learned regression GBT model:')
0050     print(model.toDebugString())
0051
0052     # Save and load model
0053     model.save(sc, "target/tmp/myGradientBoostingRegressionModel")
0054     sameModel = GradientBoostedTreesModel.load(sc, "target/tmp/myGradientBoostingRegressionModel")
0055     # $example off$