机器学习各个算法2---逻辑回归

相关函数：

from numpy import *

def loadDataSet():     #读取数据集
    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])])   #前面的一个1是表征常数项
        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    #步长设置
    maxCycles = 500   #最大迭代次数
    weights = ones((n,1))   #拟合系数全部初始化为1
    for k in range(maxCycles):              #heavy on matrix operations
        h = sigmoid(dataMatrix*weights)     #matrix mult  矩阵乘法
        error = (labelMat - h)              #vector subtraction
        weights = weights + alpha * dataMatrix.transpose()* error #matrix mult
    return weights

def plotBestFit(weights):      #画LR最佳拟合直线
    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)        #此处根据拟合系数画拟合直线
    y = (-weights[0]-weights[1]*x)/weights[2]
    ax.plot(x, y)
    plt.xlabel('X1'); plt.ylabel('X2');
    plt.show()

测试代码：

import logRegres
dataArr, labelArr = logRegres.loadDataSet()
print logRegres.gradAscent(dataArr, labelArr)

#画出数据集和LR回归最佳拟合直线
from numpy import *
weights = logRegres.gradAscent(dataArr,labelArr)
logRegres.plotBestFit(weights.getA())   #getA()函数与mat()函数的功能相反，是将一个numpy矩阵转换为数组
#作用可查看http://blog.csdn.net/douya2016/article/details/78161890?locationNum=5&fps=1

结果：

[[ 4.12414349]
 [ 0.48007329]
 [-0.6168482 ]]

随机梯度上升

stocGradAscent0

函数

def stocGradAscent0(dataMatrix, classLabels):
    m,n = shape(dataMatrix)    #m是样本个数
    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

测试代码

import logRegres
from numpy import *
dataArr, labelArr = logRegres.loadDataSet()
weights = logRegres.stocGradAscent0(array(dataArr),labelArr)
logRegres.plotBestFit(weights) 

图

随机梯度算法改进

函数

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
    m,n = shape(dataMatrix)
    weights = ones(n)   #initialize to all ones
    for j in range(numIter):
        dataIndex = range(m)
        for i in range(m):
            alpha = 4/(1.0+j+i)+0.0001    #apha decreases with iteration, does not go to 0 because of the constant
            randIndex = int(random.uniform(0,len(dataIndex)))#随机选取下标
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])   #去掉
    return weights

测试代码

#随机梯度上升
import logRegres
from numpy import *
dataArr, labelArr = logRegres.loadDataSet()
weights = logRegres.stocGradAscent0(array(dataArr),labelArr)
logRegres.plotBestFit(weights)  

#改进的随机梯度上升算法
NEWweights = logRegres.stocGradAscent1(array(dataArr),labelArr)
logRegres.plotBestFit(NEWweights)

结果

效果和基于梯度上升算法的LR差不多，但随机梯度上升算法的计算量更少了

函数

def classifyVector(inX, weights):   #分类器，返回分类结果向量
    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]))
    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():     #10次求平均
    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))

测试代码

import logRegres
logRegres.multiTest()

结果：

the error rate of this test is: 0.328358
the error rate of this test is: 0.268657
the error rate of this test is: 0.432836
the error rate of this test is: 0.283582
the error rate of this test is: 0.343284
the error rate of this test is: 0.283582
the error rate of this test is: 0.283582
the error rate of this test is: 0.313433
the error rate of this test is: 0.402985
the error rate of this test is: 0.417910
after 10 iterations the average error rate is: 0.335821