应用多元统计分析（8）第七章 主成分分析

课堂代码整理及注释

import numpy as np
import pandas as pd

dat = pd.read_excel("F:\\基础数学课\\应用多元统计分析\\exec6.5.xlsx",header = 0)

R = dat.corr().values
lam,T = np.linalg.eig(R)
lam/sum(lam)
(lam/sum(lam)).cumsum()
pd.DataFrame(T)

第八次作业

import numpy as np
import pandas as pd

dat = pd.read_excel("F:\\基础数学课\\应用多元统计分析\\examp6.3.3.xlsx",header=1)

R = dat.corr()

lamda,T = np.linalg.eig(R)
lamda/lamda.sum()
(lamda/lamda.sum()).cumsum()
pd.DataFrame(T)

# 由于前三个的方差贡献率已到达了87% > 85% , 选用前面三个进行主成分分析即可

lam1 = lamda[0]
lam2 = lamda[1]
lam3 = lamda[2]

t1 = T[:,0]
t2 = T[:,1]
t3 = T[:,2]

T = pd.DataFrame(T[:,:3],index=['x1','x2','x3','x4','x5','x6','x7','x8'],columns=['y1','y2','y3'])