def run():
data_loader = DataLoader(data_dir_root, data_train_file, data_test_file)
raw_train_df, raw_test_df = data_loader.load_csv_data()
data_loader.print_statistics()
pre_processor = PreProcessor(
raw_train_df,
raw_test_df,
cols_to_consider=cols_to_consider,
# cols_to_consider=raw_train_df.columns[0:-1],
target_feature='SalePrice')
pre_processor.pre_process_data()
print_features_info(pre_processor.raw_train_df,
pre_processor.clean_train_df)
plot_target_feature(pre_processor.raw_train_df,
pre_processor.target_feature)
plot_features_hist(pre_processor.raw_train_df)
plot_correlation_numeric_features(pre_processor.clean_train_df)
train_X, train_y = prepare_data(
pre_processor.clean_train_df,
class_col=pre_processor.target_feature,
reg_encoding_features=[],
one_hot_encoding_features=one_hot_encod_features,
ordinal_encoding_features=features_ordinal_mappings,
no_enc_features=no_enc_features)
test_X, test_y = prepare_data(
pre_processor.clean_test_df,
class_col=pre_processor.target_feature,
reg_encoding_features=[],
one_hot_encoding_features=one_hot_encod_features,
ordinal_encoding_features=features_ordinal_mappings,
no_enc_features=no_enc_features)
evaluator = Predictor(train_X, train_y, test_X, test_y, eval_classifiers,
eval_classifiers_params_grid)
all_predictions, final_prediction = evaluator.build_models(
grid_search=False)
evaluation_df = evaluator.save_predictions_to_df(all_predictions,
final_prediction)
submission_df = evaluator.save_predictions_for_submission(
evaluation_df, id_col=pre_processor.raw_test_df['Id'])
evaluation_df.to_csv("test_evaluation_results.csv", index=False)
submission_df.to_csv("test_submission.csv", index=False)
