吴裕雄 python 机器学习-Logistic（1）

import numpy as np

def loadDataSet():
    dataMat = []
    labelMat = []
    fr = open('D:\\LearningResource\\machinelearninginaction\\Ch05\\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

dataMat,labelMat = loadDataSet()
print(dataMat)
print(labelMat)

def sigmoid(z):
    sigmoid = 1.0/(1+np.exp(-z)) 
    return sigmoid

def gradAscent(dataMatIn, classLabels):
    dataMatrix = np.mat(dataMatIn)             
    labelMat = np.mat(classLabels).transpose()
    m,n = np.shape(dataMatrix)
    alpha = 0.001
    maxCycles = 500
    weights = np.ones((n,1))
    for k in range(maxCycles):             
        h = sigmoid(dataMatrix*weights)     
        error = (labelMat - h)              
        weights = weights + alpha * dataMatrix.transpose()* error
    return weights

weights = gradAscent(dataMat,labelMat)
print(weights)

def stocGradAscent0(dataMatrix, classLabels):
    m,n = np.shape(dataMatrix)
    alpha = 0.01
    weights = np.ones(n)   
    for i in range(m):
        h = sigmoid(sum(np.array(dataMatrix[i])*weights))
        error = classLabels[i] - h
        weights = weights + alpha * error * np.array(dataMatrix[i])
    return weights

weights = stocGradAscent0(dataMat,labelMat)
print(weights)

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
    m,n = np.shape(dataMatrix)
    weights = np.ones(n)   
    for j in range(numIter):
        dataIndex = list(range(m))
        for i in range(m):
            alpha = 4/(1.0+j+i)+0.0001    
            randIndex = int(np.random.uniform(0,len(dataIndex)))
            h = sigmoid(sum(np.array(dataMatrix[randIndex])*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * np.array(dataMatrix[randIndex])
            del(dataIndex[randIndex])
    return weights

weights = stocGradAscent1(dataMat,labelMat)
print(weights)

import matplotlib.pyplot as plt

def plotBestFit():
    dataMat,labelMat=loadDataSet()
    weights = gradAscent(dataMat,labelMat)
    dataArr = np.array(dataMat)
    n = np.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 = np.arange(-3.0, 3.0, 0.1)
    y = (-weights[0]-weights[1]*x)/weights[2]
    y = np.array(y).reshape(len(x))
    ax.plot(x, y)
    plt.xlabel('X1')
    plt.ylabel('X2');
    plt.show()
    
plotBestFit()

def classifyVector(z, weights):
    prob = sigmoid(sum(z*weights))
    if(prob > 0.5):
        return 1.0
    else: 
        return 0.0
    
def colicTest():
    frTrain = open('D:\\LearningResource\\machinelearninginaction\\Ch05\\horseColicTraining.txt')
    frTest = open('D:\\LearningResource\\machinelearninginaction\\Ch05\\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(np.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(np.array(lineArr), trainWeights))!= int(currLine[21])):
            errorCount += 1
    errorRate = (float(errorCount)/numTestVec)
    print("the error rate of this test is: %f" % errorRate)
    return errorRate

errorRate = colicTest()
print(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)))
    
multiTest()