blob: 6e0f7a4ee5a81efa8780267aee378fa086927925 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
"""
Logistic regression using MLlib.
This example requires NumPy (http://www.numpy.org/).
"""
from math import exp
import sys
import numpy as np
from pyspark import SparkContext
from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.classification import LogisticRegressionWithSGD
# Parse a line of text into an MLlib LabeledPoint object
def parsePoint(line):
values = [float(s) for s in line.split(' ')]
if values[0] == -1: # Convert -1 labels to 0 for MLlib
values[0] = 0
return LabeledPoint(values[0], values[1:])
if __name__ == "__main__":
if len(sys.argv) != 3:
print >> sys.stderr, "Usage: logistic_regression <file> <iterations>"
exit(-1)
sc = SparkContext(appName="PythonLR")
points = sc.textFile(sys.argv[1]).map(parsePoint)
iterations = int(sys.argv[2])
model = LogisticRegressionWithSGD.train(points, iterations)
print "Final weights: " + str(model.weights)
print "Final intercept: " + str(model.intercept)
|