Logistic回归实战篇之预测病马死亡率

利用sklearn.linear_model.LogisticRegression训练和测试算法。

示例代码：

import numpy as np

import matplotlib.pyplot as plt

import random

from sklearn.linear_model import LogisticRegression

def stocGradAscent1(dataMatrix, classLabels, numIter=150):  #随机梯度上升算法

    m,n = np.shape(dataMatrix) #返回dataMatrix的大小。m为行数,n为列数。

    weights = np.ones(n) #参数初始化

    for j in range(numIter):

        dataIndex = list(range(m))

        for i in range(m):

            alpha = 4/(1.0+j+i)+0.01 #降低alpha的大小，每次减小1/(j+i)。

            randIndex = int(random.uniform(0,len(dataIndex))) #随机选取样本

            h = sigmoid(sum(dataMatrix[randIndex]*weights)) #选择随机选取的一个样本，计算h

            error = classLabels[randIndex] - h #计算误差

            weights = weights + np.dot(alpha * error ,dataMatrix[randIndex])  #更新回归系数

            del(dataIndex[randIndex]) #删除已经使用的样本

        return weights

def loadDataSet():  #数据处理，得到向量

    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]))

    fr.close()

    return dataMat,labelMat

def sigmoid(intX):  #计算sigmoid

    return 1.0/(1+np.exp(-intX))

def gradAscent(dataMatIn,classLabels):  #梯度上升算法，得到个特征值的权重

    dataMatrix = np.mat(dataMatIn)

    labelMat = np.mat(classLabels).transpose()

    m,n = np.shape(dataMatrix)

    alpha = 0.01

    maxCycles = 500

    weights = np.ones((n,1))

    for k in range(maxCycles):

        h = sigmoid(dataMatrix*weights)

        error = labelMat - h

        weights += alpha * dataMatrix.transpose() * error

    return weights

def plotBestFit(weights):   #绘制数据集和数据划分线w0x0+w1x1+w2x2=0

    dataMat,labelMat = loadDataSet()

    dataArr = np.array(dataMat)

    n = np.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 = np.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 classifyVector(intX,weights):   #将数据分类

    weights = weights.reshape(-1,)  #将（n,1）数组转换成（n,）

    prob = sigmoid(sum(intX*weights))

    if prob > 0.5:

        return 1.0

    else:

        return 0.0

def colicTest():    #测试算法

    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(len(currLine)-1):

            lineArr.append(float(currLine[i]))

        trainingSet.append(lineArr)

        trainingLabels.append(float(currLine[-1]))

    trainWeights = stocGradAscent1(np.array(trainingSet),trainingLabels,500)

    #trainWeights = gradAscent(np.array(trainingSet), trainingLabels)

    errorCount = 0;numTestVec = 0.0

    for line in frTest.readlines():

        numTestVec += 1.0

        currLine = line.strip().split('\t')

        lineArr = []

        for i in range(len(currLine)-1):

            lineArr.append(float(currLine[i]))

        if int(classifyVector(np.array(lineArr), trainWeights))!= int(currLine[-1]):

            errorCount += 1

    errorRate = (float(errorCount)/numTestVec)*100

    print("测试集错误率为: %.2f%%" % errorRate)

def colicSklearn(): #运用SKLEARN中的LogisticRegression测试算法准确率

    frTrain = open('horseColicTraining.txt')

    frTest = open('horseColicTest.txt')  # 打开测试集

    trainingSet = [];trainingLabels = []

    testSet = [];testLabels = []

    for line in frTrain.readlines():

        currLine = line.strip().split('\t')

        lineArr = []

        for i in range(len(currLine) - 1):

            lineArr.append(float(currLine[i]))

        trainingSet.append(lineArr)

        trainingLabels.append(float(currLine[-1]))

    for line in frTest.readlines():

        currLine = line.strip().split('\t')

        lineArr = []

        for i in range(len(currLine) - 1):

            lineArr.append(float(currLine[i]))

        testSet.append(lineArr)

        testLabels.append(float(currLine[-1]))

    classifier = LogisticRegression(solver='liblinear', max_iter=20).fit(trainingSet, trainingLabels)

    test_accurcy = classifier.score(testSet, testLabels) * 100

    print('正确率:%f%%' % test_accurcy)

if __name__ == '__main__':

    #colicTest()

    colicSklearn()