remaining.remove(response)
selected = []
current_score, best_new_score = 0.0, 0.0
while remaining and current_score == best_new_score:
scores_with_candidates = []
for candidate in remaining:
formula = '{} ~ {} + 1'.format(response, ' + '.join(selected + [candidate]))
score = smf.ols(formula, data).fit().rsquared_adj
scores_with_candidates.append((score, candidate))
scores_with_candidates.sort()
best_new_score, best_candidate = scores_with_candidates.pop()
if current_score > best_new_score:
remaining.remove(best_candidate)
selected.append(best_candidate)
current_score = best_new_score
formula = '{} ~ {} + 1'.format(response, ' + '.join(seleted))
model = smf.ols(formula, data).fit()
return model
model = forward_selected(DataSubset, 'NumberLikes24')
print('Model Selected')
print(model.model.formula)
print('R2=', model.rsquared_adj)
if __name__ == "__main__":
assignment = LinearRegression('somefile.txt')
assignment.clean()
assignment.summarize()
assignment.regression()
