Logistic回归（Python实现）

这篇文章是《机器学习实战》（Machine Learning in Action）第五章 Logistic回归算法的Python实现代码。

---

1 参考链接

机器学习实战

2 实现代码

from numpy import *

def loadDataSet():
    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])])
        labelMat.append(int(lineArr[2]))
    return dataMat, labelMat

def sigmoid(inX):
    return 1.0/(1+exp(-inX))

def gradAscent(dataMatIn, classLabels):
    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 plotBestFit(wei):
    import matplotlib.pyplot as plt
    #weights = wei.getA()
    dataMat, labelMat =loadDataSet()
    dataArr = array(dataMat)
    n = shape(dataArr)[0]
    xcoord1 = []; ycoord1 =[]
    xcoord2 = []; ycoord2 =[]
    for i in range(n):
        if int(labelMat[i]) == 1:
            xcoord1.append(dataArr[i,1]); ycoord1.append(dataArr[i,2])
        else:
            xcoord2.append(dataArr[i,1]); ycoord2.append(dataArr[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 = 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 stocGradAscent0(dataMatrix, labelMat):
    m,n = shape(dataMatrix)
    alpha = 0.01
    weights = ones(n)  
    for i in range(m):
        h = sigmoid(sum(dataMatrix[i]*weights))
        error = labelMat[i] -h
        weights = weights + alpha * error * dataMatrix[i]
    return weights

def stocGradAscent1(dataMatrix, classLabels, numIter=200):
    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) + 0.01
            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 classifyVector(inX, weights):
    prob = sigmoid(sum(inX*weights))
    if prob > 0.5: return 1.0
    else: return 0.0

def colicTest():
    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]))
    trainingWeights = stocGradAscent1(array(trainingSet), trainingLabels, 500);
    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), trainingWeights)) != 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)) 

#TEST
multiTest()

3 运行结果