机器学习实战笔记(四)：Logist线性回归算法的Python实现

from numpy import *

def loadDataSet():                          #遍历函数，打开文本文件testSet.txt并进行逐行读取
    dataMat = []
    labelMat = []
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()        #去掉文件中换行符且划分文件为行
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) #将X0的值设为1，因为公式w0+w1x1+w2x2
        labelMat.append(int(lineArr[2]))
    return dataMat,labelMat

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

def gradAscent(dataMatIn, classLabels):    #梯度上升算法计算最佳回归系数
    dataMatrix = mat(dataMatIn)                   #获得输入数据并将样本数组转换为矩阵
    labelMat = mat(classLabels).transpose()    #将类标签数组转换为项链并将其转置
    m,n = shape(dataMatrix)                     #得到矩阵的大小
    alpha = 0.001                        #步长
    maxCycles = 500                      #迭代次数
    weights = ones((n,1))                #回归系数初始化为1,n*1的向量
    for k in range(maxCycles):                  #遍历数组
        h = sigmoid(dataMatrix*weights)     #h是一个列向量，元素个数等于样本个数，矩阵相乘
        error = (labelMat - h)                     #误差计算，向量减法运算
        weights = weights + alpha * dataMatrix.transpose()* error    #矩阵相乘，dataMatrix.transpose()*error就是梯度f(w)
    return weights

def plotBestFit(weights):                    #画出训练点
    import matplotlib.pyplot as plt
    dataMat,labelMat=loadDataSet()      #画点
    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)                          #画线，x取值区间为[-3.0,3.0],步长为0.1
    y = (-weights[0]-weights[1]*x)/weights[2]
    ax.plot(x, y)
    plt.xlabel('X1’)
    plt.ylabel('X2')
    plt.show()      #显示

def stocGradAscent0(dataMatrix, classLabels):    #随机梯度上升算法
    m,n = shape(dataMatrix)
    alpha =