python实现normal equation进行一元多元线性回归

Posted 2021-03-05 梦小冷

python实现normal equation进行一元、多元线性回归

一元线性回归

数据

代码

import numpy as np
import matplotlib.pyplot as plt 
import matplotlib
from sklearn.linear_model import SGDRegressor
from sklearn.preprocessing import StandardScaler



# 梯度下降
def gradientDecent(xmat,ymat):
    sgd=SGDRegressor(max_iter=1000000, tol=1e-7)
    sgd.fit(xmat,ymat)
    return sgd.coef_,sgd.intercept_

# 导入数据
def loadDataSet(filename):
    x=[[],[]]
    y=[]
    with open(filename,\'r\') as f:
        for line in f.readlines():
            lineDataList=line.split(\'\\t\')
            lineDataList=[float(x) for x in lineDataList]
            x[0].append(lineDataList[0])
            x[1].append(lineDataList[1])
            y.append(lineDataList[2])
    return x,y 

# 转化为矩阵
def mat(x):
    return np.matrix(np.array(x)).T

# 可视化
def dataVisual(xmat,ymat,k,g,intercept):
    k1,k2=k[0],k[1]
    g1,g2=g[0],g[1]
    matplotlib.rcParams[\'font.sans-serif\'] = [\'SimHei\']
    plt.title(\'拟合可视化\')
    plt.scatter(xmat[:,1].flatten().A[0],ymat[:,0].flatten().A[0])
    x = np.linspace(0, 1, 50)
    y=x*k2+k1
    g=x*g2+g1+intercept
    plt.plot(x,g,c=\'yellow\')
    plt.plot(x,y,c=\'r\')
    plt.show()

   

# 求解回归的参数
def normalEquation(xmat,ymat):
    temp=xmat.T.dot(xmat)
    isInverse=np.linalg.det(xmat.T.dot(xmat))
    if isInverse==0.0:
        print(\'不可逆矩阵\')
    else:
        inv=temp.I
        return inv.dot(xmat.T).dot(ymat)
    

# 主函数
def main():
    xAll,y=loadDataSet(\'linearRegression/ex0.txt\')
    xlines=[]# 用于梯度下降算钱调用
    for i in range(len(xAll[0])):
        temp=[]
        temp.append(xAll[0][i])
        temp.append(xAll[1][i])
        xlines.append(temp)
    ylines=np.array(y).reshape(len(y),1)
    # xlines=StandardScaler().fit_transform(xlines)
    # ylines=StandardScaler().fit_transform(ylines)
    # print(xlines)
    # print(ylines)
    
    gradPara,intercept=gradientDecent(xlines,y)
    print(\'梯度下降参数\')
    print(gradPara)
    print(\'梯度下降截距\')
    print(intercept)
    xmat=mat(xAll)
    ymat=mat(y)
    print(\'normequation的参数:\')
    res=normalEquation(xmat,ymat)
    print(res)
    k1,k2=res[0,0],res[1,0]
    dataVisual(xmat,ymat,[k1,k2],gradPara,intercept)

 

if __name__ == "__main__":
    main()

结果

注意这里我踩了一个小小的坑，就是用SGDRegressor的时候，总是和预期结果相差一个截距，通过修改g从g=xg2+g1到g=xg2+g1+intercept，加上截距就好了
图中红色表示normalequation方法，而黄线表示梯度下降，由于我通过调参拟合的非常好，所以重合的很厉害，不好看出来

多元线性回归

数据

代码

import numpy as np 
import matplotlib.pyplot as plt 
import re
from sklearn.linear_model import SGDRegressor


# 将数据转化成为矩阵
def matrix(x):
    return np.matrix(np.array(x)).T

# 线性函数
def linerfunc(xList,thList,*intercept):
    res=0.0
    for i in range(len(xList)):
        res+=xList[i]*thList[i]
    if len(intercept)==0:
        return res
    else:
        return res+intercept[0][0]



# 加载数据
def loadData(fileName):
    x=[]
    y=[]
    regex = re.compile(\'\\s+\')
    with open(fileName,\'r\') as f:
        readlines=f.readlines()
        for line in readlines:
            dataLine=regex.split(line)
            dataList=[float(x) for x in dataLine[0:-1]]
            xList=dataList[0:8]
            x.append(xList)
            y.append(dataList[-1])
    return x,y


# 求解回归的参数
def normalEquation(xmat,ymat):
    temp=xmat.T.dot(xmat)
    isInverse=np.linalg.det(xmat.T.dot(xmat))
    if isInverse==0.0:
        print(\'不可逆矩阵\')
        return None
    else:
        inv=temp.I
        return inv.dot(xmat.T).dot(ymat)


# 梯度下降求参数
def gradientDecent(xmat,ymat):
    sgd=SGDRegressor(max_iter=1000000, tol=1e-7)
    sgd.fit(xmat,ymat)
    return sgd.coef_,sgd.intercept_



# 测试代码

def testTrainResult(normPara,gradPara,Interc,xTest,yTest):
    nright=0
    for i in range(len(xTest)):
        if round(linerfunc(xTest[i],normPara)) ==yTest[i]:
            nright+=1
    print(\'关于normequation的预测方法正确率为 {}\'.format(nright/len(xTest)))

    gright=0
    for i in range(len(xTest)):
        if round(linerfunc(xTest[i],gradPara,Interc))==yTest[i]:
            gright+=1
    print(\'关于梯度下降法预测的正确率为 {}\'.format(gright/len(xTest)))


    
# 运行程序
def main():
    x,y=loadData(\'linearRegression/abalone1.txt\')
    # 划分训练集合和测试集
    lr=0.8
    xTrain=x[:int(len(x)*lr)]
    yTrain=y[:int(len(y)*lr)]
    xTest=x[int(len(x)*lr):]
    yTest=y[int(len(y)*lr):]

    xmat=matrix(xTrain).T
    ymat=matrix(yTrain)
    # 通过equation来计算模型的参数
    theta=normalEquation(xmat,ymat)
    print(\'通过equation来计算模型的参数\')
    theta=theta.reshape(1,len(theta)).tolist()[0]
    print(theta)
    # 掉包sklearn的梯度下降的算法求参数
    print(\'掉包sklearn的梯度下降的算法求参数\')
    gtheta,Interc=gradientDecent(xTrain,yTrain)
    print(\'参数\')
    print(gtheta)
    print(\'截距\')
    print(Interc)
    testTrainResult(theta,gtheta,Interc,xTest,yTest)

if __name__ == "__main__":
    main()

结果

目录结构

数据下载

链接：https://pan.baidu.com/s/1JXrE4kbYsdVSSWjTUSDT3g
提取码：obxh
链接：https://pan.baidu.com/s/13wXq52wpKHbIlf3v21Qcgg
提取码：w4m5