https://bioinformaticsonline.com/snippets/view/38544/backward-elimination-with-python? https://bioinformaticsonline.com/snippets/view/38544/backward-elimination-with-python Fri, 28 Dec 2018 07:16:48 -0600 https://bioinformaticsonline.com/snippets/view/38544/backward-elimination-with-python #Backward Elimination with p-values only: import statsmodels.formula.api as sm def backwardElimination(x, sl): numVars = len(x[0]) for i in range(0, numVars): regressor_OLS = sm.OLS(y, x).fit() maxVar = max(regressor_OLS.pvalues).astype(float) if maxVar > sl: for j in range(0, numVars - i): if (regressor_OLS.pvalues[j].astype(float) == maxVar): x = np.delete(x, j, 1) regressor_OLS.summary() return x SL = 0.05 X_opt = X[:, [0, 1, 2, 3, 4, 5]] X_Modeled = backwardElimination(X_opt, SL) #Backward Elimination with p-values and Adjusted R Squared: import statsmodels.formula.api as sm def backwardElimination(x, SL): numVars = len(x[0]) temp = np.zeros((50,6)).astype(int) for i in range(0, numVars): regressor_OLS = sm.OLS(y, x).fit() maxVar = max(regressor_OLS.pvalues).astype(float) adjR_before = regressor_OLS.rsquared_adj.astype(float) if maxVar > SL: for j in range(0, numVars - i): if (regressor_OLS.pvalues[j].astype(float) == maxVar): temp[:,j] = x[:, j] x = np.delete(x, j, 1) tmp_regressor = sm.OLS(y, x).fit() adjR_after = tmp_regressor.rsquared_adj.astype(float) if (adjR_before >= adjR_after): x_rollback = np.hstack((x, temp[:,[0,j]])) x_rollback = np.delete(x_rollback, j, 1) print (regressor_OLS.summary()) return x_rollback else: continue regressor_OLS.summary() return x SL = 0.05 X_opt = X[:, [0, 1, 2, 3, 4, 5]] X_Modeled = backwardElimination(X_opt, SL)]]> BioStar