python/mllib/logistic_regression.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 using MLlib.
0020
0021 This example requires NumPy (http://www.numpy.org/).
0022 """
0023 from __future__ import print_function
0024
0025 import sys
0026
0027 from pyspark import SparkContext
0028 from pyspark.mllib.regression import LabeledPoint
0029 from pyspark.mllib.classification import LogisticRegressionWithSGD
0030
0031
0032 def parsePoint(line):
0033     """
0034     Parse a line of text into an MLlib LabeledPoint object.
0035     """
0036     values = [float(s) for s in line.split(' ')]
0037     if values[0] == -1:   # Convert -1 labels to 0 for MLlib
0038         values[0] = 0
0039     return LabeledPoint(values[0], values[1:])
0040
0041
0042 if __name__ == "__main__":
0043     if len(sys.argv) != 3:
0044         print("Usage: logistic_regression <file> <iterations>", file=sys.stderr)
0045         sys.exit(-1)
0046     sc = SparkContext(appName="PythonLR")
0047     points = sc.textFile(sys.argv[1]).map(parsePoint)
0048     iterations = int(sys.argv[2])
0049     model = LogisticRegressionWithSGD.train(points, iterations)
0050     print("Final weights: " + str(model.weights))
0051     print("Final intercept: " + str(model.intercept))
0052     sc.stop()