逻辑回归的分布式实现 [Logistic Regression / Machine Learning / Spark ]

1- 问题提出

---

2- 逻辑回归

---

3- 理论推导

---

4- Python/Spark实现

 # -*- coding: utf-8 -*-
 from pyspark import SparkContext
 from math import *

 theta = [0, 0, 0]    #初始theta值
 alpha = 0.001    #学习速率

 def inner(x, y):
     return sum([i*j for i,j in zip(x,y)])

 def func(lst):
     h = (1 + exp(-inner(lst, theta)))**(-1)
     return map(lambda x: (h - lst[-1]) * x, lst[:-1])

 sc = SparkContext('local')

 rdd = sc.textFile('/home/freyr/logisticRegression.txt')\
         .map(lambda line: map(float, line.strip().split(',')))\
         .map(lambda lst: [1]+lst)

 for i in range(400):
     partheta = rdd.map(func)\
                    .reduce(lambda x,y: [i+j for i,j in zip(x,y)])

     for j in range(3):
         theta[j] = theta[j] - alpha * partheta[j]

 print 'theta = %s' % theta

PS: logisticRegression.txt