机器学习第五章代码.docxVIP

5—1． Logistic 回归梯度上升优算法#加载数据，前两列是点所属的 X1, X2 坐标, 最后一列是该点所属分类。fromnumpy import *defloadDataSet(): #加载数据dataMat = []; labelMat = []fr = open(testSet.txt)#打开文本文件testSet.txtfor line in fr.readlines(): #逐行读取lineArr = line.strip().split()dataMat.append([1.0,float(lineArr[0]),float(lineArr[1])])# 因为线性回归化式为 H(x) = W0 + W1*X1 + W2*X2即为 (W0, W1, W2)*(1, X1, X2), 其中 (W0, W1, W2) 即为所求回归系数 W。为了方便计算, 读出 X1, X2 后要在前面补上一个 1.0labelMat.append(int(lineArr[2]))return dataMat,labelMat#计算 sigmoid 函数def sigmoid(inX):????return 1.0/(1+exp(-inX))# 梯度上升算法计算出最佳回归系数defgradAscent(dataMatIn, classLabels):??dataMatrix = mat(dataMatIn)#转换为NumPy矩阵数据类型????labelMat = mat(classLabels).transpose() #转换为NumPy矩阵数据类型??m,n = shape(dataMatrix)????alpha = 0.001?????????????????????????? # 步长????maxCycles = 500????????????????????#循环次数????weights = ones((n,1))???????????????# 回归系数初始化为1#循环maxCycles次, 每次都沿梯度向真实值labelMat靠拢Fork in range(maxCycles):???????????????h = sigmoid(dataMatrix*weights)???? # 矩阵相乘???????error=(labelMat-h)? #向量减法运算????????weights = weights + alpha * dataMatrix.transpose()* error #矩阵相乘，dataMatrix.transpose()* error 就是梯度f(w)?return weights5—2 画出数据集和Logistic回归最佳拟合直线的函数。#画出各个训练点,根据 weights(即回归的各个参数) 画出直线, 以便直观的看到划分是否正确defplotBestFit(weights):????importmatplotlib.pyplot as plt????# 画点????dataMat,labelMat=loadDataSet()????dataArr = array(dataMat)????n = shape(dataArr)[0] ????xcord1 = []; ycord1 = []????xcord2 = []; ycord2 = []????for i in range(n):??????ifint(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)?# 画线?x= arange(-3.0, 3.0, 0.1)?# x取值区间为 [-3.0, 3.0),步长为 0.1?y = (-weights[0]-weights[1]*x1)/weights[2]?ax.plot(x,y)?plt.xlabel(X1); plt.ylabel(X2);# 显示?plt.show()5—3 随机梯度上升算法def stocGradAscent0(dataMatrix, classLabels):m,n = shape(dataMatrix)alp