Last active
October 9, 2023 12:26
-
-
Save joaopcnogueira/5008cd7e696262a88a4da793219f4982 to your computer and use it in GitHub Desktop.
Feature selection by Backward Elimination using both the p-value and the adjusted r-squared
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 numpy as np | |
import statsmodels.formula.api as sm | |
def backward_elimination2(X, y, sl): | |
""" | |
X: the data matrix with the independent variables (predictors) | |
y: the matrix of the dependent variable (target) | |
sl: statistical level, by default the user should add 0.05 (5%) | |
""" | |
X = np.append(arr=np.ones((len(X),1)).astype(int), values=X, axis=1) | |
while(True): | |
regressor_OLS = sm.OLS(y,X).fit() | |
ind = np.argmax(regressor_OLS.pvalues) | |
max_pvalue = regressor_OLS.pvalues[ind] | |
if max_pvalue > sl: | |
actual_adj_rsquared = regressor_OLS.rsquared_adj | |
X_temp = np.delete(X, ind, axis=1) | |
next_regressor_OLS = sm.OLS(y,X_temp).fit() | |
next_adj_rsquared = next_regressor_OLS.rsquared_adj | |
if(actual_adj_rsquared > next_adj_rsquared): | |
X = np.delete(X, 0, axis=1) | |
print(regressor_OLS.summary()) | |
return X | |
else: | |
X = np.delete(X, ind, axis=1) | |
else: | |
print(regressor_OLS.summary()) | |
X = np.delete(X, 0, axis=1) | |
return X |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment