|
|
|
|
@ -1,5 +1,7 @@
|
|
|
|
|
import pandas as pd
|
|
|
|
|
import numpy as np
|
|
|
|
|
from scipy.stats import zscore
|
|
|
|
|
from sklearn.decomposition import PCA
|
|
|
|
|
import matplotlib.pyplot as plt
|
|
|
|
|
from matplotlib.pyplot import ylabel
|
|
|
|
|
df = pd.read_excel("棉花产量论文作业的数据.xlsx")
|
|
|
|
|
@ -38,5 +40,22 @@ plt.scatter(data2[:,:1],data2[:,1:2],c='g')
|
|
|
|
|
plt.xlabel('压缩到0~1')
|
|
|
|
|
print(data==data1)
|
|
|
|
|
|
|
|
|
|
plt.savefig("shuju.jpg",dpi=2000)
|
|
|
|
|
plt.show()
|
|
|
|
|
# plt.savefig("shuju.jpg",dpi=2000)
|
|
|
|
|
# plt.show()
|
|
|
|
|
md= PCA().fit(data)
|
|
|
|
|
cf = np.cov(data.T)#求协方差矩阵
|
|
|
|
|
print(cf)
|
|
|
|
|
c, d= np.linalg.eig(cf)
|
|
|
|
|
print("特征值：\n",c)
|
|
|
|
|
print(md.explained_variance_)
|
|
|
|
|
e=c/c.sum()
|
|
|
|
|
# for _ in range(len(e)):
|
|
|
|
|
# if(_!=0):
|
|
|
|
|
# e[_]+=e[_-1]
|
|
|
|
|
print('贡献率：')
|
|
|
|
|
print(e)
|
|
|
|
|
print(md.explained_variance_ratio_)
|
|
|
|
|
print('特征向量：')
|
|
|
|
|
print(d.T)
|
|
|
|
|
print(md.components_)
|
|
|
|
|
print(md.components_-d.T<=0.1)
|
