fix: fix a bug in the format of the model input (#327)

* fix a bug

* fix a bug

* fix a ci bug

rdagent/scenarios/kaggle/experiment/forest-cover-type-prediction_template/train.py

@@ -62,7 +62,23 @@ print(X_train.shape, X_valid.shape, X_test.shape)
 # Handle inf and -inf values
 X_train, X_valid, X_test = clean_and_impute_data(X_train, X_valid, X_test)
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)

rdagent/scenarios/kaggle/experiment/playground-series-s3e11_template/train.py

@@ -38,7 +38,23 @@ X_train = pd.concat(X_train_l, axis=1, keys=[f"feature_{i}" for i in range(len(X
 X_valid = pd.concat(X_valid_l, axis=1, keys=[f"feature_{i}" for i in range(len(X_valid_l))])
 X_test = pd.concat(X_test_l, axis=1, keys=[f"feature_{i}" for i in range(len(X_test_l))])
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)

rdagent/scenarios/kaggle/experiment/playground-series-s3e26_template/train.py

@@ -74,7 +74,23 @@ X_test = X_test.loc[:, ~X_test.columns.duplicated()]
 
 print(X_train.shape, X_valid.shape, X_test.shape)
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)

rdagent/scenarios/kaggle/experiment/playground-series-s4e8_template/train.py

@@ -72,7 +72,23 @@ X_train = X_train.loc[:, ~X_train.columns.duplicated()]
 X_valid = X_valid.loc[:, ~X_valid.columns.duplicated()]
 X_test = X_test.loc[:, ~X_test.columns.duplicated()]
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func,]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)

rdagent/scenarios/kaggle/experiment/playground-series-s4e9_template/train.py

@@ -71,7 +71,23 @@ X_train = X_train.loc[:, ~X_train.columns.duplicated()]
 X_valid = X_valid.loc[:, ~X_valid.columns.duplicated()]
 X_test = X_test.loc[:, ~X_test.columns.duplicated()]
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func,]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)

rdagent/scenarios/kaggle/experiment/sf-crime_template/train.py

@@ -74,7 +74,23 @@ X_test = X_test.loc[:, ~X_test.columns.duplicated()]
 
 print(X_train.shape, X_valid.shape, X_test.shape)
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)

rdagent/scenarios/kaggle/experiment/spaceship-titanic_template/train.py

@@ -72,7 +72,23 @@ X_train = X_train.loc[:, ~X_train.columns.duplicated()]
 X_valid = X_valid.loc[:, ~X_valid.columns.duplicated()]
 X_test = X_test.loc[:, ~X_test.columns.duplicated()]
 
+
 # 3) Train the model
+def flatten_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Flatten the columns of a DataFrame with MultiIndex columns,
+    for (feature_0, a), (feature_0, b) -> feature_0_a, feature_0_b
+    """
+    if df.columns.nlevels == 1:
+        return df
+    df.columns = ["_".join(col).strip() for col in df.columns.values]
+    return df
+
+
+X_train = flatten_columns(X_train)
+X_valid = flatten_columns(X_valid)
+X_test = flatten_columns(X_test)
+
 model_l = []  # list[tuple[model, predict_func,]]
 for f in DIRNAME.glob("model/model*.py"):
     m = import_module_from_path(f.stem, f)