def stepwise_selection(data, target, SL_in=0.05, SL_out=0.05):
initial_features = data.columns.tolist()
best_features = []
while (len(initial_features) > 0):
remaining_features = list(set(initial_features) - set(best_features))
new_pval = pd.Series(index=remaining_features)
for new_column in remaining_features:
model = OLS(target,
sm.add_constant(data[best_features +
[new_column]])).fit()
new_pval[new_column] = model.pvalues[new_column]
min_p_value = new_pval.min()
if (min_p_value < SL_in):
best_features.append(new_pval.idxmin())
while (len(best_features) > 0):
best_features_with_constant = sm.add_constant(
data[best_features])
p_values = OLS(target,
best_features_with_constant).fit().pvalues[1:]
max_p_value = p_values.max()
if (max_p_value >= SL_out):
excluded_feature = p_values.idxmax()
best_features.remove(excluded_feature)
else:
break
else:
break
return best_features
