python|特征选择

import pandas as pd
import numpy as np
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_regression

df = pd.read_csv('C:/Users/.......csv')
x = df.drop('Accident_Level', axis=1)  # df中删掉某一列，扔掉列axis=1
y = df['Accident_Level']

# select feature by person coefficient
X = np.array(x)
Y = np.array(y)
skb = SelectKBest(score_func=f_regression, k=5)
skb.fit(X, Y.ravel())
print('选择的特征有:', [x.columns[i] for i in skb.get_support(indices=True)])
X_selected = skb.transform(X)
print('X_selected.shape:', X_selected.shape)

输出

选择的特征有: ['WorkingDay', 'Weather', 'Slope', 'Traffic_Volume', 'Truck_Ratio']
X_selected.shape: (968, 5)