逻辑线性回归

基础

逻辑线性回归(Logistic回归)的原理部分在上篇转载的博文讲解的已经很详细了。直接以示例程序给出

示例代码

from numpy import *

# 文本中加载样本，前两列为特征，最后一列为标签
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

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

# 逻辑线性回归（梯度上升or下降，符号不同而已）
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 = sigmoid(dataMatrix*weights)
        error = (labelMat - h)
        weights = weights + alpha * dataMatrix.transpose()*error # 该步骤是由Logistic回归公式求导得出
    return weights, error

#随机梯度上升法
def stocGradAscent0(dataMatrix, classLabels):
    m, n = shape(dataMatrix)
    alpha = 0.01
    weights = ones(n)
    for i in range(m):
        h = sigmoid(sum(dataMatrix[i]*weights))
        error = classLabels[i] - h
        weights = weights + alpha * error * dataMatrix[i]
    return weights

# 改进的随机梯度上升算法，拟合更加接近
def stocGradAscent1(dataMatrix, classLabels, numIter = 150):
    m, n = shape(dataMatrix)
    weights = ones(n)
    for j in range(numIter):
        dataIndex = list(range(m))
        for i in range(m):
            alpha = 4/(1.0 + i + j) + 0.01
            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

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()

# 逻辑线性回归进行识别
def classifyVector(inX, weights):
    prob = sigmoid(sum(inX*weights))
    if prob > 0.5:
        return 1.0
    else:
        return 0.0

# 病马死亡率预测， 缺失特征用0补齐，对结果影响不大
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
# 实例测试，最后平均错误率在35%左右
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)))

>>>结果
the error rate of this test is : 0.328358
the error rate of this test is : 0.432836
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 : 0.402985
the error rate of this test is : 0.402985
the error rate of this test is : 0.298507
the error rate of this test is : 0.313433
the error rate of this test is : 0.328358
the error rate of this test is : 0.358209
after 10 iterations the average error rate is: 0.358209

算法特点

• 优点：计算代价不高，易于理解和实现
• 缺点：容易欠拟合，分类精度可能不高
• 适用数据类型：数值型和标称型数据