使用Python实现LR算法_ RuntimeWarning: overflow encountered in exp问题解决方案

import numpy as np
filepath = r'C:\Users\Administrator\Desktop\ML\machinelearninginaction-master\machinelearninginaction-master\Ch05'

def load_dataset():
    data_mat = []
    label_mat = []
    fr = open(filepath + '/testSet.txt')
    for line in fr.readlines():
        line = line.strip().split()
        data_mat.append([1.0, float(line[0]), float(line[1])])  # 第一个是常数项
        label_mat.append(int(line[2]))
    return data_mat, label_mat


def sigmoid(in_x):  #  RuntimeWarning: overflow encountered in exp
    # return 1.0/(1 + np.exp(-in_x))
    # 优化方法
    if in_x >= 0:
        return 1.0/(1+np.exp(-in_x))
    else:
        return np.exp(in_x)/(1+np.exp(in_x))


# # 梯度上升算法
# def grad_ascent(datamat_in, class_labels):
#     datamat = np.mat(datamat_in)
#     label_mat = np.mat(class_labels).transpose()
#     m, n = np.shape(datamat)
#     alpha = 0.001
#     max_cycle = 500
#     weights = np.ones((n, 1))
#     for k in range(max_cycle):
#         h = sigmoid(datamat*weights)
#         error = label_mat - h
#         weights = weights + alpha * datamat.transpose() * error
#     return weights


def plotBestFit(wei):
    import matplotlib.pyplot as plt
    # plt.scatter(x=np.array(data)[:, 1], y=np.array(data)[:, 2], s=30, c=label)
    # weights = wei.getA()
    weights = wei
    dataMat, labelMAt = load_dataset()
    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(1, 1, 1)
    ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
    ax.scatter(xcord2, ycord2, s=30, c='green')
    x = dataArr[:, 1]
    # 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()


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


# 改进的随机梯度上升算法
def stocGradAscent1(dataMatrix, classLabels, numIter=150):
    m,n = np.shape(dataMatrix)
    weights = np.ones(n)   # initialize to all ones
    for j in range(numIter):
        dataIndex = list(range(m))  # ###修改的地方.原文是range(m)
        for i in range(m):
            alpha = 4/(1.0+j+i)+0.0001    # alpha decreases with iteration, does not
            randIndex = int(np.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 * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights


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


def colicTest():
    frTrain = open(filepath + '/horseColicTraining.txt')
    frTest = open(filepath + '/horseColicTest.txt')
    trainingSet = []; trainingLabels = []
    for line in frTrain.readlines():
        currentline = line.strip().split('\t')
        lineArr = []
        for i in range(21):
            lineArr.append(float(currentline[i]))
        trainingSet.append(lineArr)
        trainingLabels.append(float(currentline[21]))
    trainingWeights = stocGradAscent1(np.array(trainingSet), trainingLabels, 500)
    errorCount = 0; numTestVec = 0.0
    for line in frTest.readlines():
        numTestVec += 1.0
        currentline = line.strip().split('\t')
        lineArr = []
        for i in range(21):
            lineArr.append(float(currentline[i]))
        if int(classifyVector(np.array(lineArr), trainingWeights)) != int(currentline[21]):
            errorCount += 1
    errorRate = (float(errorCount)/numTestVec)
    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)))

最终的error rate 为33.3%