Last active
May 19, 2022 16:40
-
-
Save smazzanti/8f5466acb231f54559afcf149c89c172 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 initialize correlation matrix | |
F = pd.Series(f_regression(X, y)[0], index = X.columns) | |
corr = pd.DataFrame(.00001, index = X.columns, columns = X.columns) | |
# initialize list of selected features and list of excluded features | |
selected = [] | |
not_selected = X.columns.to_list() | |
# repeat K times | |
for i in range(K): | |
# compute (absolute) correlations between the last selected feature and all the (currently) excluded features | |
if i > 0: | |
last_selected = selected[-1] | |
corr.loc[not_selected, last_selected] = X[not_selected].corrwith(X[last_selected]).abs().clip(.00001) | |
# 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