机器学习之逻辑回归--使用虚拟成绩进行模拟

1. 成绩通过情况的分类错误率

import logRegres
logRegres.multiTest(3)
#the error rate of this test is: 0.128770
#the error rate of this test is: 0.201532
#the error rate of this test is: 0.113930
#the error rate of this test is: 0.018669
#the error rate of this test is: 0.166108
#the error rate of this test is: 0.127334
#the error rate of this test is: 0.127812
#the error rate of this test is: 0.034466
#the error rate of this test is: 0.136908
#the error rate of this test is: 0.020584
#after 10 iterations the average error rate is: 0.107611

2.分类预测

# 输入数据
frTrain = open('horseColicTraining.txt');
trainingSet = []; trainingLabels = []
for line in frTrain.readlines():
    currLine = line.strip().split('\t')
    lineArr =[]
    for i in range(3):
        lineArr.append(float(currLine[i]))
    trainingSet.append(lineArr)
    trainingLabels.append(float(currLine[3]))

trainingSet[:5]
#[[3.0, 3.0, 575.0],
# [1.0, 3.0, 640.0],
# [1.0, 4.0, 450.0],
# [1.0, 2.0, 370.0],
# [1.0, 2.0, 460.0]]

trainingLabels[:5]
#[1.0, 1.0, 0.0, 1.0, 1.0]

# 得出回归系数，迭代1000次
trainWeights = logRegres.stocGradAscent1(trainingSet, trainingLabels, numIter=1000)

# 预测结果
logRegres.classifyVector(array([3,3,410]), trainWeights)
#0.0

logRegres.py

from numpy import *
import numpy as np

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)             #convert to NumPy matrix
    labelMat = mat(classLabels).transpose() #convert to NumPy matrix
    m,n = shape(dataMatrix)
    alpha = 0.001
    maxCycles = 500
    weights = ones((n,1))
    for k in range(maxCycles):              #heavy on matrix operations
        h = sigmoid(dataMatrix*weights)     #matrix mult
        error = (labelMat - h)              #vector subtraction
        weights = weights + alpha * dataMatrix.transpose()* error #matrix mult
    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 stocGradAscent0(dataMatrix, classLabels):
    m,n = shape(dataMatrix)
    alpha = 0.01
    weights = ones(n)   #initialize to all ones
    for i in range(m):
        h = sigmoid(sum(dataMatrix[i]*weights))
        error = classLabels[i] - h
        weights = weights + alpha * error * dataMatrix[i]
    return weights

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
    dataMatrix = np.array(dataMatrix)
    classLabels = np.array(classLabels)
    m,n = shape(dataMatrix)
    weights = ones(n)   #initialize to all ones
    for j in range(numIter):
        dataIndex = list(range(m))
        for i in range(m):
            alpha = 4/(1.0+j+i)+0.0001    #apha decreases with iteration, does not 
            randIndex = int(random.uniform(0,len(dataIndex)))#go to 0 because of the constant
            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(m):
    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(m):
            lineArr.append(float(currLine[i]))
        trainingSet.append(lineArr)
        trainingLabels.append(float(currLine[m]))
    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(m):
            lineArr.append(float(currLine[i]))
        if int(classifyVector(array(lineArr), trainWeights))!= int(currLine[m]):
            errorCount += 1
    errorRate = (float(errorCount)/numTestVec)
    print ("the error rate of this test is: %f" % errorRate)
    return errorRate

def multiTest(m):
    numTests = 10; errorSum=0.0
    for k in range(numTests):
        errorSum += colicTest(m)
    print ("after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests)))