from sklearn.datasets import load_iris
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
#加载数据集
iris = load_iris()
x,y = iris.data,iris.target
print('原始特征:')
print(x.shape)
print(x[:5,:])
print()
#使用卡方分布选择2个维度的变量
x_new = SelectKBest(chi2,k=2).fit_transform(x,y)
#问题:为什么要有y,因为是考量每个特征与标签的关系,所以要有y
print('选取的特征')
print(x_new.shape)
print(x_new[:5,:])