[机器学习实战] -Logistic回归

根据现有数据对分类边界线建立回归模型，以此进行分类。在练习中会介绍有关梯度上升算法和随机梯度上升算法，最后应用Logistic回归，预测病马的死亡率。参考练习[Exercise 3] Logistic Regression and Newton’s Method。

实验基础

1. sigmod
2. 随机梯度下降（Stochastic gradient descent）和 批量梯度下降（Batch gradient descent ）的公式对比、实现对比

Logistic回归梯度上升算法

#!/usr/bin/env python
# coding=utf-8

from numpy import *

#loadDataSet
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

#sigmod function
def sigmod(inX):
    return  1.0/(1+ exp(-inX))
#梯度上升算法
def gradAscent(dataMatIn, classLabels):
    dataMatrix = mat(dataMatIn)
    labelMat = mat(classLabels).transpose()
    m,n = shape(dataMatrix)
    alpha = 0.001
    maxCycles = 500
    weights = ones((n,1))
    for k in range(maxCycles):
        h = sigmod(dataMatrix*weights)
        error = (labelMat - h)
        weights = weights + alpha*dataMatrix.transpose()*error
    return weights

---

分析数据：画出决策边界

#画出决策边界
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()

---

训练算法

#随机梯度上升算法
def stocGradAscent0(dataMatrix, classLabels):
    m,n = shape(dataMatrix)
    alpha = 0.01
    weights = ones(n)
    for i in range(m):
        h = sigmod(sum(dataMatrix[i]*weights))
        error = classLabels[i] - h
        weights = weights + alpha*error*dataMatrix[i]
    return weights
#改进随机梯度上升算法 1 alpha每次迭代都会调整 2. 随机选择样本
def stocGradAscent1( dataMatrix, classLabels, numIter = 150):
    m,n = shape(dataMatrix)
    weights = ones(n)
    for j in range(numIter):
        dataIndex = range(m)
        for i in range(m):
            alpha = 4/(1.0 + j + i) + 0.01
            randIndex = int(random.uniform(0, len(dataIndex)))
            h = sigmod(sum(dataMatrix[i]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha*error*dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights

def classifyVector(inX, weights):
    prob = sigmod(sum(inX*weights))
    if prob > 0.5:
        return 1.0
    else:
        return 0.0

病马死亡率预测

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, 500)
    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():
    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))

小结

Logistic回归的目的是寻找一个非线性函数sigmod的最佳拟合参数。在优化算法中，最常用的就是梯度上升算法，而梯度上升算法又可以简化为随机梯度上升算法。

机器学习的一个重要问题是如何处理缺少数据。
一些可选的做法：

1. 使用刊用特征的均值来填补缺失值
2. 使用特殊值来填补，如-1
3. 忽略有缺失的样本
4. 使用相似样本的均值填补缺失值
5. 使用另外的算法来预测缺失值