fix ensemble bug in train.py (#283)

rdagent/scenarios/kaggle/experiment/meta_tpl/model/model_xgb.py

@@ -22,7 +22,7 @@ def fit(X_train: pd.DataFrame, y_train: pd.DataFrame, X_valid: pd.DataFrame, y_v
     params = {
         "nthred": -1,
     }
-    num_round = 200
+    num_round = 100
 
     evallist = [(dtrain, "train"), (dvalid, "eval")]
     bst = xgb.train(params, dtrain, num_round, evallist)

rdagent/scenarios/kaggle/experiment/meta_tpl/train.py

@@ -102,18 +102,14 @@ print("Final on validation set: ", mcc)
 pd.Series(data=[mcc], index=["MCC"]).to_csv("submission_score.csv")
 
 # 7) Make predictions on the test set and save them
-label_encoder = LabelEncoder()
-label_encoder.fit(y_train)
-y_test_pred_bool_l = []
+y_test_pred_l = []
 for m, m_pred in model_l:
-    y_test_pred_bool_l.append(
-        m_pred(m, X_test).astype(int)
-    )  # TODO Make this an ensemble. Currently it uses the last prediction
+    y_test_pred_l.append(m_pred(m, X_test))  # TODO Make this an ensemble. Currently it uses the last prediction
 
-y_test_pred = np.mean(y_test_pred_bool_l, axis=0)
+y_test_pred = np.mean(y_test_pred_l, axis=0)
 y_test_pred = (y_test_pred > 0.5).astype(int)
 
-y_test_pred_labels = label_encoder.inverse_transform(y_test_pred)  # 将整数转换回 'e' 或 'p'
+y_test_pred_labels = np.where(y_test_pred == 1, "p", "e")  # 将整数转换回 'e' 或 'p'
 
 submission_result = pd.DataFrame({"id": passenger_ids, "class": y_test_pred_labels})