机器学习实战 Logistic回归

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from numpy import *

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):#梯度上升法
    dataMatrix = mat(dataMatIn)             #convert to NumPy matrix
    labelMat = mat(classLabels) #convert to NumPy matrix
    labelMat = labelMat.transpose()
    m,n = shape(dataMatrix)
    alpha = 0.001#移动步长
    maxCycles = 500#迭代次数
    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 # W = W + a*ᐁf(W)
    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, numIter=150):#一次仅用一个样本点更新回归系数 随机梯度上升法
    m,n = shape(dataMatrix)
    alpha = 0.01
    weights = ones(n)   #initialize to all ones
    for j in range(numIter):
        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):#改进:alpha随迭代次数减小 随机选取样本
    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)))
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights

if __name__ == '__main__':
    dataArr, labelMat = loadDataSet()

    weights = gradAscent(dataArr,labelMat)
    plotBestFit(weights.getA())

    weights = stocGradAscent0(array(dataArr),labelMat)
    plotBestFit(weights)

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

testSet.txt:

-0.017612    14.053064    0
-1.395634    4.662541    1
-0.752157    6.538620    0
-1.322371    7.152853    0
0.423363    11.054677    0
0.406704    7.067335    1
0.667394    12.741452    0
-2.460150    6.866805    1
0.569411    9.548755    0
-0.026632    10.427743    0
0.850433    6.920334    1
1.347183    13.175500    0
1.176813    3.167020    1
-1.781871    9.097953    0
-0.566606    5.749003    1