Logistic回归 Python实现

本文实现了Logistic回归算法，代码中有梯度下降法和随机下降法供选择，并画图显示了最后的分隔结果。

#!/usr/bin/python
# -*- coding: utf-8 -*-
from numpy import*
import operator
import matplotlib
import matplotlib.pyplot as plt
from os import listdir
def loadDataSet():   #加载数据
    dataMat=[];labelMat=[]
    fr=open('testSet.txt')
    for line in fr.readlines():
        lineArr=line.strip().split()
        dataMat.append([1.0,float(lineArr[0]),float(lineArr[1])])  #1.0是为了方便向量运算
        labelMat.append(int(lineArr[2]))
    return dataMat,labelMat
def sigmoid(inX):
    return 1.0/(1+exp(-inX))
def gradAscent(dataMatIn,classLabels):    #梯度上升
    dataMatrix=mat(dataMatIn)
    labelMat=mat(classLabels).transpose()
    m,n=shape(dataMatrix)
    alpha=0.001
    maxCycles=500
    weights=ones((n,1))
    for k in range(maxCycles):
        h=sigmoid(dataMatrix*weights)
        error=(labelMat-h)
        weights=weights+alpha*dataMatrix.transpose()*error
    return weights
def stocGradAscent1(dataMatrix, classLabels, numIter=150):
    m,n = shape(dataMatrix)
    weights = ones(n)
    for j in range(numIter):
        dataIndex = range(m)
        for i in range(m):
            alpha = 4/(1.0+j+i)+0.0001
            randIndex = int(random.uniform(0,len(dataIndex)))
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights

def plotBestFit(weights):
    import matplotlib.pyplot as plt
    dataMat,labelMat=loadDataSet()
    dataArr = array(dataMat)
    n = shape(dataArr)[0]
    xcord1 = []; ycord1 = []
    xcord2 = []; ycord2 = []
    for i in range(n):
        if int(labelMat[i])== 1:
            xcord1.append(dataArr[i,1]); ycord1.append(dataArr[i,2])
        else:
            xcord2.append(dataArr[i,1]); ycord2.append(dataArr[i,2])
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(xcord1, ycord1, s=30, c='red',marker='s')
    ax.scatter(xcord2, ycord2, s=30, c='green')
    x = arange(-3.0, 3.0, 0.1)
    y = (-weights[0]-weights[1]*x)/weights[2]
    ax.plot(x, y)
    plt.xlabel('X1'); plt.ylabel('X2');
    plt.show()
def classifyVector(inX,weights):
    prob=sigmoid(sum(inX*weights))
    if(prob>0.5):return 1.0
    else:return 0.0
def colicTest():   #病马测试集
    frTrain = open('horseColicTraining.txt'); frTest = open('horseColicTest.txt')
    trainingSet = []; trainingLabels = []
    for line in frTrain.readlines():
        currLine = line.strip().split('\t')
        lineArr =[]
        for i in range(21):
            lineArr.append(float(currLine[i]))
        trainingSet.append(lineArr)
        trainingLabels.append(float(currLine[21]))
    trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 1000)
    errorCount = 0; numTestVec = 0.0
    for line in frTest.readlines():
        numTestVec += 1.0
        currLine = line.strip().split('\t')
        lineArr =[]
        for i in range(21):
            lineArr.append(float(currLine[i]))
        if int(classifyVector(array(lineArr), trainWeights))!= int(currLine[21]):
            errorCount += 1
    errorRate = (float(errorCount)/numTestVec)
    print "the error rate of this test is: %f" % errorRate
    return errorRate
def multiTest():
    numTests = 10; errorSum=0.0
    for k in range(numTests):
        errorSum += colicTest()
    print "after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests))

dataArr,labelMat=loadDataSet()
#
# wei=gradAscent(array(dataArr),labelMat)
wei2=stocGradAscent1(array(dataArr),labelMat)
#plotBestFit(wei.getA())
plotBestFit(wei2)
# colicTest()