logistic回归

#!/usr/bin/env python
# encoding:utf-8

import math
import numpy
import time
import matplotlib.pyplot as plt


def sigmoid(x):
    return 1.0 / (1 + numpy.exp(-x))


def loadData():
    dataMat = []
    laberMat = []
    with open("test.txt", ‘r‘) as f:
        for line in f.readlines():
            arry = line.strip().split()
            dataMat.append([1.0, float(arry[0]), float(arry[1])])
            laberMat.append(float(arry[2]))
    return numpy.mat(dataMat), numpy.mat(laberMat).transpose()


def gradAscent(dataMat, laberMat, alpha=0.001, maxCycle=500):
    """general gradscent"""
    start_time = time.time()
    m, n = numpy.shape(dataMat)
    weights = numpy.ones((n, 1)) 
    for i in range(maxCycle):
        h = sigmoid(dataMat * weights)
        error = laberMat - h 
        weights += alpha * dataMat.transpose() * error
    duration = time.time() - start_time
    print "duration of time:", duration
    return weights


def stocGradAscent(dataMat, laberMat, alpha=0.01):
    start_time = time.time()
    m, n = numpy.shape(dataMat)
    weights = numpy.ones((n, 1)) 
    for i in range(m):
        h = sigmoid(dataMat[i] * weights)
        error = laberMat[i] - h 
        weights += alpha * dataMat[i].transpose() * error
    duration = time.time() - start_time
    print "duration of time:", duration
    return weights


def betterStocGradAscent(dataMat, laberMat, alpha=0.01, numIter=150):
    """better one, use a dynamic alpha"""
    start_time = time.time()
    m, n = numpy.shape(dataMat)
    weights = numpy.ones((n, 1)) 
    for j in range(numIter):
        for i in range(m):
            alpha = 4 / (1 + j + i) + 0.01
            h = sigmoid(dataMat[i] * weights)
            error = laberMat[i] - h 
            weights += alpha * dataMat[i].transpose() * error
    duration = time.time() - start_time
    print "duration of time:", duration
    return weights
    start_time = time.time()


def show(dataMat, laberMat, weights):
    m, n = numpy.shape(dataMat) 
    min_x = min(dataMat[:, 1])[0, 0]
    max_x = max(dataMat[:, 1])[0, 0]
    xcoord1 = []; ycoord1 = []
    xcoord2 = []; ycoord2 = []
    for i in range(m):
        if int(laberMat[i, 0]) == 0:
            xcoord1.append(dataMat[i, 1]); ycoord1.append(dataMat[i, 2]) 
        elif int(laberMat[i, 0]) == 1:
            xcoord2.append(dataMat[i, 1]); ycoord2.append(dataMat[i, 2]) 
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(xcoord1, ycoord1, s=30, c="red", marker="s")
    ax.scatter(xcoord2, ycoord2, s=30, c="green")
    x = numpy.arange(min_x, max_x, 0.1)
    y = (-weights[0] - weights[1]*x) / weights[2]
    ax.plot(x, y)
    plt.xlabel("x1"); plt.ylabel("x2")
    plt.show()

    
if __name__ == "__main__":
    dataMat, laberMat = loadData()
    #weights = gradAscent(dataMat, laberMat, maxCycle=500)
    #weights = stocGradAscent(dataMat, laberMat)
    weights = betterStocGradAscent(dataMat, laberMat, numIter=80)
    show(dataMat, laberMat, weights)