# # 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. # """ A logistic regression implementation that uses NumPy (http://www.numpy.org) to act on batches of input data using efficient matrix operations. """ from collections import namedtuple from math import exp from os.path import realpath import sys import numpy as np from pyspark import SparkContext D = 10 # Number of dimensions # Read a batch of points from the input file into a NumPy matrix object. We operate on batches to # make further computations faster. # The data file contains lines of the form