#%% evaluate performance with training data
eval_reg = HistGradientBoostingRegressor(random_state=1129)
eval_reg.fit(X_train, y_train)
print("-" * 10, "regression report", "-" * 10)
report = regression_report(y_test, eval_reg.predict(X_test),
X_test.shape[1])
print(report)
print("-" * 10, "evaluation of label", "-" * 10)
label_df = data.get_true_label(
columns=["adr", "revenue", "is_canceled", "label"])
pred_label_df = data.predict_label(eval_reg, X_test_df)
print("[ label evaluation ]")
report_label = evaluate_by_label(pred_label_df, label_df, target="label")
print(report_label)
print("[ revenue_per_day evaluation ]")
report_revenue = evaluate_by_label(pred_label_df,
label_df,
target="revenue")
print(report_revenue)
#%% training with all data
X_df, y_df = data.processing(["revenue"])
reg = HistGradientBoostingRegressor(random_state=1129)
reg.fit(X_df.to_numpy(), y_df["revenue"].to_numpy())
#%% fill predict label to csv
test_X_df = data.processing_test_data("data/test.csv")
predict_df = data.predict_label(reg, test_X_df)
revenue_pred = reg.predict(X_df)
revenue_preds.append(revenue_pred)
revenue_pred = np.sum(revenue_preds, axis=0) / len(revenue_preds)
# print report
report = []
report.append("[ revenue_per_order evaluation ]")
y_test = y_test_df["revenue"].to_numpy()
reg_report = regression_report(y_test, revenue_pred, X_test_df.shape[1])
report.append(reg_report)
pred_df = X_test_df.copy()
pred_df["pred_revenue"] = revenue_pred
pred_label_df = data.to_label(pred_df)
true_label_df = data.get_true_label(
columns=["adr", "revenue", "is_canceled", "label"])
report.append("[ label evaluation ]")
report.append(evaluate_by_label(pred_label_df, true_label_df, "label"))
report.append("[ revenue_per_day evaluation ]")
report.append(evaluate_by_label(pred_label_df, true_label_df, "revenue"))
report = "\n".join(report) + "\n"
print(report)
# training with all data
X_df, y_df = data.processing(["revenue", "is_canceled", "adr"])
regs = split_train(regressor, X_df, y_df, nsplit)
test_X_df = data.processing_test_data()
save_output(regs, test_X_df)