python画logistic拟合曲线_Logistic回归python实现

# -*- coding: utf-8 -*-

'''function: 实现Logistic回归，拟合直线，对数据进行分类；利用梯度上升，随机梯度上升，改进的随机梯度上升，牛顿法分别对损失函数优化；这里没有给出最后测试分类的函数；date: 2017.8.12'''

from numpy import *

#从文件加载处理数据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 function X: w1*x1+w2*x2+...+wn*xndef sigmoid(x):return 1 / (1 + exp(-x))

#梯度上升求函数的最大值时取得的权重def gradAscent(dataMatIn, classLabels):dataMatrix = mat(dataMatIn)labelMat = mat(classLabels).transpose() #将m维行向量转制为m维列向量m,n = shape(dataMatrix)alpha = 0.001 #设置梯度上升的步长maxCycles = 500 #最大迭代次数weights = ones((n,1)) #weights就是theta，n维列向量,二维数组for i in range(maxCycles):h = sigmoid(dataMatrix*weights) #计算所有数据的分类概率，h是m维向量,这里实际上进行了300次乘法运算error = labelMat - h #计算(y-h(x))：误差weights = weights + alpha * dataMatrix.transpose()*error #对所有weights同时更新print('shape of weights', shape(weights))return weights

#随机上升上升def stocGradAscent0(dataMatrix, classLabels):m,n = shape(dataMatrix)alpha = 0.01weights = ones(n, float) #n 维行向量for i in range(m):h = sigmoid(sum(dataMatrix[i] * weights))error = classLabels[i] - hweights = weights + alpha * error * dataMatrix[int(i)]return weights

#改进的随机上升上升def stocGradAscent1(dataMatrix, classLabels, numIter = 550):m,n = shape(dataMatrix)weights = ones(n)dataIndex = []for j in range(numIter):for k in range(m):dataIndex.append(k)for i in range(m):alpha = 4 / (i + j + 1.0) + 0.01 #aloha随着迭代次数增多不断减小但是不为0，为了解决局部波动randIndex = int(random.uniform(0, len(dataIndex))) #随机选取一个数据进行更新参数h = sigmoid(dataMatrix[randIndex] * weights)error = classLabels[randIndex] - hweights = weights + alpha * error * dataMatrix[randIndex]del(dataIndex[randIndex]) #这里会不会对本来的dataMatrix有影响,不会，因为没有操作矩阵return weights

'''functuion: 牛顿法更新theta,计算海森矩阵note: 这里一定要对 XT*X 结果求逆，不然分类效果无法直视'''def computeHessianMatrix(dataMatrix):hessianMatrix = mat(dataMatrix).transpose().dot(mat(dataMatrix))return hessianMatrix.I #矩阵求逆

'''function: 牛顿法更新theta'''def newtonMethod(dataMat, labelMat, numIter = 10):m,n = shape(dataMat)dataMatrix = mat(dataMat)labelMat = mat(labelMat).transpose()weights = ones((n,1)) #参数向量hessianMatrix = computeHessianMatrix(dataMatrix)print('shape of hessian', shape(hessianMatrix))for k in range(numIter):h = sigmoid(dataMatrix * weights)error = (labelMat - h)weights = weights - (dataMatrix*hessianMatrix).transpose() * errorreturn weights

#画出决策边界def plotBestFit(weights):import matplotlib.pyplot as pltdataMat, labelMat = loadDataSet() #或取数据和标签dataArr = array(dataMat) #将二维列表转换为数组n = shape(dataArr)[0] #行数，代表数据的个数

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)print(len(x))print(len(weights))print(shape(weights))y = (-weights[0] - weights[1]*x) / weights[2] #把x2堪称y,x0=1,所以就是x1,x2之间的函数print(len(y))ax.plot(x,y)plt.xlabel('X1'); plt.ylabel('X2')plt.show() #显示图像

'''function: 对测试数据进行测试input: testDate 是一个向量，或者多个向量'''def logisticTest(weights, testData):m,n = shape(testData)typeLabel = []for i in range(m):result = sigmoid(sum(testData[i] * weights)) #得到一个册数数据的概率if result > 0.5:typeLabel.append(1)else:typeLabel.append(0)return typeLabel

'''function: 计算分类的正确率input: calssLables 是测试数据的类别向量'''def getCorrectRate(classLabels, testLabel):correctRate = 0.0numOfRight = 0for i in range(len(testLabel)):if classLabels[i] == testLabel[i]:numOfRight += 1correctRate = numOfRight / float(len(testLabel))return correctRate

#测试算法dataMat, labelMat = loadDataSet()print('shape of datamet, ', shape(dataMat))weights1 = gradAscent(dataMat, labelMat)weights2 = stocGradAscent0(array(dataMat), labelMat)weights3 = stocGradAscent1(dataMat, labelMat)

weights4 = newtonMethod(dataMat, labelMat, 2000) #牛顿法

#测试正确率typeLabel = logisticTest(weights4, [[1,1,0],[1,1,1]])print(typeLabel)correctRate = getCorrectRate([1,0],typeLabel)print('正确率： ' ,str(correctRate))

#画图#plotBestFit(array(weights1)) #这里因为普通梯度上升返回的是一个矩阵，所以要转换为向量#plotBestFit(weights2)#plotBestFit(weights3)plotBestFit(array(weights4))