问用于特征选择的Sklearn Chi2

EN

from sklearn.datasets import load_iris
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
import pandas as pd
import numpy as np

# Load iris data
iris = load_iris()

# Create features and target
X = iris.data
y = iris.target

# Convert to categorical data by converting data to integers
X = X.astype(int)

# Select two features with highest chi-squared statistics
chi2_selector = SelectKBest(chi2, k=2)
chi2_selector.fit(X, y)

# Look at scores returned from the selector for each feature
chi2_scores = pd.DataFrame(list(zip(iris.feature_names, chi2_selector.scores_, chi2_selector.pvalues_)), columns=['ftr', 'score', 'pval'])
chi2_scores

# you can see that the kbest returned from SelectKBest 
#+ were the two features with the _highest_ score
kbest = np.asarray(iris.feature_names)[chi2_selector.get_support()]
kbest