实训1、2 找最小相关系数
import numpy as np
import pandas as pd
data=pd.read_csv(r"G:\大数据实验数据库\data.csv",encoding="GBK")
print("相关系数矩阵为:\n",np.round(data.corr(method="pearson"),6))
实训3 找相关行数
import pandas as pd
import numpy as np
from sklearn.linear_model import Lasso
inputfile="G:\大数据实验数据库\income_tax.csv" #文件位置
data=pd.read_csv(inputfile)
lasso =Lasso(1000,random_state=1234)
lasso.fit(data.iloc[:,0:11],data["y"])
print("相关系数",np.round(lasso.coef_,5))
print("相关系数非零个数为",np.sum(lasso.coef_!=0))