《机器学习实战》线性回归

一.最小平方差进行线性回归

　　比较简单，就是进行残差平方和最小来进行，其中这里的差为全局最优，相当于全局梯度下降法。

　　也可以参考之前写的博文：http://www.cnblogs.com/wjy-lulu/p/7759515.html

logist.py 

import numpy as np

def loadData(filename):
    numFeat = len(open(filename).readline().split('\t')) - 1
    dataMat = []
    labelMat = []
    fr = open(filename)

    for line in fr.readlines():
        linArr = []
        curline = line.strip().split('\t')
        for i in range(numFeat):
            linArr.append(float(curline[i]))
        dataMat.append(linArr)
        labelMat.append(float(curline[-1]))
    return dataMat, labelMat
def standRegres(xArr,yArr):
    xMat = np.mat(xArr)
    yMat = np.mat(yArr).T
    xTx = xMat.T * xMat
    if (np.linalg.det(xTx)==0.0):#det求解的值|A|
        print("This matrix is singular: cannot do inverse")
        return
    ws = xTx.I * (xMat.T*yMat)#mat.I求解矩阵的逆
    return ws 

            

main.py

import logist
import numpy as np
import matplotlib.pyplot as plt

if __name__ == '__main__':
    xArr, yArr = logist.loadData("ex0.txt")
    ws = logist.standRegres(xArr,yArr)
    xMat = np.mat(xArr);yMat = np.mat(yArr)
    xCopy = xMat.copy()
    xCopy = np.sort(xCopy,0)#对X进行排序之后再进行画图,列排序
    yHat = xCopy*ws
    fg = plt.figure()
    ax = fg.add_subplot(111)
    ax.scatter(xMat[:,1].flatten().tolist()[0],yMat.T[:,0].flatten().tolist()[0])
    ax.plot(xCopy[:,1],yHat)
    plt.show()



    print("hello deepin")
    print(ws);

二.局部加权线性回归

　　理论部分请看之前笔记：http://www.cnblogs.com/wjy-lulu/p/7759515.html