score_avg = np.sqrt(pp.score_model(averaged_models, train_X_reduced, train_y))
print(" Averaged base models score: {:.6f} ({:.6f})\n".format(
score_avg.mean(), score_avg.std()))
averaged_models.fit(train_X_reduced, train_y)
predicted_prices_averaged = np.expm1(averaged_models.predict(test_X_reduced))
print(predicted_prices_averaged)
my_submission = pd.DataFrame({
'Id': test.Id,
'SalePrice': predicted_prices_averaged
})
my_submission.to_csv('submission_avg.csv', index=False)
stacked_averaged_models = em.StackingAveragedModels(
base_models=[model_svr, model_ENet, model_KRR, model_xgb],
meta_model=model_byr)
score_stacked_averaged = np.sqrt(
pp.score_model(stacked_averaged_models, train_X_reduced, train_y))
print(" Stacked Averaged base models score: {:.6f} ({:.6f})\n".format(
score_stacked_averaged.mean(), score_stacked_averaged.std()))
stacked_averaged_models.fit(train_X_reduced, train_y)
predicted_prices_stacked_averaged = np.expm1(
stacked_averaged_models.predict(test_X_reduced))
print(predicted_prices_stacked_averaged)
model_xgb.fit(train_X_reduced, train_y)
predicted_prices_xgboost = np.expm1(model_xgb.predict(test_X_reduced))
print(predicted_prices_xgboost)
cross_val_table = get_validation_scores(tree_models, X_train, y_train, 5,
X_test, y_test)
print(cross_val_table)
cross_val_table = get_validation_scores(tree_models, train_X_reduced, train_y,
5)
print(cross_val_table)
cross_val_table_linear = get_validation_scores(linear_models, train_X_reduced,
train_y, 5)
print(cross_val_table_linear)
averaged_models = em.AveragingModels(
models=[model_lgb, model_byr, model_svr, model_ridge])
stacked_averaged_models = em.StackingAveragedModels(
base_models=[model_svr, model_lgb], meta_model=model_KRR)
averaged_plus = em.AveragingModels(
models=[averaged_models, model_GBoost, model_xgb], weights=[0.7, 0.2, 0.1])
averaged_plus_plus = em.AveragingModels(
models=[stacked_averaged_models, model_GBoost, model_xgb],
weights=[0.7, 0.2, 0.1])
ensemble_models = []
ensemble_models.append(("averaged", averaged_models))
ensemble_models.append(("stacked", stacked_averaged_models))
ensemble_models.append(("averaged_plus", averaged_plus))
ensemble_models.append(("averaged_plus_plus", averaged_plus_plus))
cross_val_table_ensemble = get_validation_scores(ensemble_models, X_train,
y_train, X_test, y_test)
print(cross_val_table_ensemble)
