logistic回归

# coding=gbk
from numpy import *

def loadDataSet():
    dataMat = []; labelMat = []
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()
        #某个点所对应的x、y坐标
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
        #某个点所属的类别class
        labelMat.append(int(lineArr[2]))
    return dataMat,labelMat

#sigmoid函数，近似符号函数
def sigmoid(inX):
    return 1.0/(1+exp(-inX))


#梯度法
#为了以最快的速度到达最高点
#每次寻找梯度最大的方向，朝该方向移动固定长度alpha
#直到到达指定高度或走了多少次为止
def gradAscent(dataMatIn, classLabels):
    #将python的list转成mat格式进行矩阵运算
    #transpose()转置成列向量
    dataMatrix = mat(dataMatIn)             #convert to NumPy matrix
    labelMat = mat(classLabels).transpose() #convert to NumPy matrix

    m,n = shape(dataMatrix)
    print(m,n)
    alpha = 0.001           #步长
    maxCycles = 500
    weights = ones((n,1))   #初始值为1,1,1 代表三个参数权重相等
    for k in range(maxCycles):              #heavy on matrix operations
        #dataMatrix
        #error用于计算真实类别与预测类别的差值，按照该方向调整回归系数
        h = sigmoid(dataMatrix*weights)     #matrix mult
        error = (labelMat - h)              #vector subtraction
        #其中，alpha * dataMatrix.transpose()表示的就是梯度
        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的值域
    y = (-weights[0]-weights[1]*x)/weights[2]
    ax.plot(x, y)
    plt.xlabel('X1'); plt.ylabel('X2');
    plt.show()

#随机梯度算法
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

#改进的随机梯度算法
def stocGradAscent1(dataMatrix, classLabels, numIter=500):
    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 * 1 * dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights


dataArr,labelMat=loadDataSet()
weights=stocGradAscent1(array(dataArr),labelMat,20)
plotBestFit(weights)