python/mllib/logistic_regression_with_lbfgs_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 Logistic Regression With LBFGS Example.
0020 """
0021 from __future__ import print_function
0022
0023 from pyspark import SparkContext
0024 # $example on$
0025 from pyspark.mllib.classification import LogisticRegressionWithLBFGS, LogisticRegressionModel
0026 from pyspark.mllib.regression import LabeledPoint
0027 # $example off$
0028
0029 if __name__ == "__main__":
0030
0031     sc = SparkContext(appName="PythonLogisticRegressionWithLBFGSExample")
0032
0033     # $example on$
0034     # Load and parse the data
0035     def parsePoint(line):
0036         values = [float(x) for x in line.split(' ')]
0037         return LabeledPoint(values[0], values[1:])
0038
0039     data = sc.textFile("data/mllib/sample_svm_data.txt")
0040     parsedData = data.map(parsePoint)
0041
0042     # Build the model
0043     model = LogisticRegressionWithLBFGS.train(parsedData)
0044
0045     # Evaluating the model on training data
0046     labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
0047     trainErr = labelsAndPreds.filter(lambda lp: lp[0] != lp[1]).count() / float(parsedData.count())
0048     print("Training Error = " + str(trainErr))
0049
0050     # Save and load model
0051     model.save(sc, "target/tmp/pythonLogisticRegressionWithLBFGSModel")
0052     sameModel = LogisticRegressionModel.load(sc,
0053                                              "target/tmp/pythonLogisticRegressionWithLBFGSModel")
0054     # $example off$