%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import random# 加载数据集
def loadDataSet():dataMat = []labelMat = []fr = open('./testSet.txt')for line in fr.readlines():lineData = line.strip().split()dataMat.append([1.0, float(lineData[0]), float(lineData[1])])labelMat.append(int(lineData[2]))return dataMat, labelMat# sigmoid 函数
def sigmoid(inX):return 1.0 / (1 + np.exp(-inX))# 梯度上升
def gradAscent(dataMatIn, classLabels, maxCycles):dataMatrix = np.mat(dataMatIn)labelsMatrix = np.mat(classLabels).transpose() # 转置，将行向量转置为列向量m, n = np.shape(dataMatrix)alpha = 0.001W = np.ones((n, 1))for i in range(maxCycles):h = sigmoid(dataMatrix * W) # (100, 1)error = labelsMatrix - h # (100, 1)W = W + alpha * dataMatrix.transpose() * error # (3, 100) * (100, 1)return W #改进版随机梯度上升
def stocGradAscent1(dataMatrixIn, classLabels, numIter=150):dataMatrix = np.array(dataMatrixIn)m,n = np.shape(dataMatrix)weights = np.ones(n)   #initialize to all onesfor j in range(numIter):dataIndex = list(range(m))for i in range(m):alpha = 4.0/(1.0+j+i)+0.01    #apha decreases with iteration, does not randIndex = int(random.uniform(0,len(dataIndex)))#go to 0 because of the constanth = sigmoid(sum(dataMatrix[randIndex]*weights))error = classLabels[randIndex] - hweights = weights + alpha * error * dataMatrix[randIndex]del(dataIndex[randIndex])return np.mat(weights.reshape(n, 1))def plotBestFit(weights, dataMat, labelMat):dataArr = np.array(dataMat)n = np.shape(dataArr)[0]xcord1 = []; ycord1 = []xcord2 = []; ycord2 = []for i in range(n):if 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(-4.0, 4.0, 0.1)y = ((np.array((-weights[0] - weights[1] * x) / weights[2]))[0]).transpose()ax.plot(x, y)plt.xlabel('X1')plt.ylabel('X2')plt.show()# 预测
def classifyVector(inX, weights):prob = sigmoid(sum(inX * weights))if prob > 0.5:return 1.0else:return 0.0# 对训练集进行训练，并且对测试集进行测试
def colicTest():trainFile = open('horseColicTraining.txt')testFile = open('horseColicTest.txt')trainingSet = []; trainingLabels = []for line in trainFile.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]))# 开始训练weights = stocGradAscent1(trainingSet, trainingLabels, 400)errorCount = 0.0numTestVec = 0.0for line in testFile.readlines():numTestVec += 1.0currLine = line.strip().split('\t')lineArr = []for i in range(21):lineArr.append(float(currLine[i]))if int(classifyVector(np.array(lineArr), weights)) != int(currLine[21]):errorCount += 1.0errorRate = errorCount / float(numTestVec)print("the error rate is:%f" % errorRate)return errorRate# 多次测试求平均值
def multiTest():testTimes = 10errorRateSum = 0.0for i in range(testTimes):errorRateSum += colicTest()print("the average error rate is:%f" % (errorRateSum / float(testTimes)))multiTest()