Last active
March 26, 2022 01:37
-
-
Save smazzanti/42ac13ec13fb58df656ba51e9d48bccd to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
from sklearn.feature_selection import f_regression | |
# inputs: | |
# X: pandas.DataFrame, features | |
# y: pandas.Series, target variable | |
# K: number of features to select | |
# compute F-statistics and correlations | |
F = pd.Series(f_regression(X, y)[0], index = X.columns) | |
corr = X.corr().abs().clip(.00001) # minimum value of correlation set to .00001 (to avoid division by zero) | |
# initialize list of selected features and list of excluded features | |
selected = [] | |
not_selected = list(X.columns) | |
# repeat K times: | |
# compute FCQ score for all the features that are currently excluded, | |
# then find the best one, add it to selected, and remove it from not_selected | |
for i in range(K): | |
# compute FCQ score for all the (currently) excluded features (this is Formula 2) | |
score = F.loc[not_selected] / corr.loc[not_selected, selected].mean(axis = 1).fillna(.00001) | |
# find best feature, add it to selected and remove it from not_selected | |
best = score.index[score.argmax()] | |
selected.append(best) | |
not_selected.remove(best) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment