feat: add a new competition (#474)

* add tabular-playground-series-dec-2021

* finished

* fix a mistake

* fix a bug

* fix a bug

rdagent/scenarios/kaggle/docker/Dockerfile

@@ -25,4 +25,5 @@ RUN pip install xgboost
 RUN pip install sparse
 RUN pip install lightgbm 
 RUN pip install pyarrow
-RUN pip install fastparquet
+RUN pip install fastparquet
+RUN pip install optuna

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/fea_share_preprocess.py

@@ -0,0 +1,72 @@
+import os
+
+import numpy as np
+import pandas as pd
+from sklearn.impute import SimpleImputer
+from sklearn.model_selection import train_test_split
+
+
+def prepreprocess():
+    """
+    This method loads the data, drops the unnecessary columns, and splits it into train and validation sets.
+    """
+    # Load and preprocess the data
+    data_df = pd.read_csv("/kaggle/input/train.csv")
+    data_df = data_df.drop(["Id"], axis=1)
+
+    X = data_df.drop(["Cover_Type"], axis=1)
+    y = data_df["Cover_Type"] - 1
+
+    # Split the data into training and validation sets
+    X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.20, random_state=42)
+
+    return X_train, X_valid, y_train, y_valid
+
+
+def preprocess_script():
+    """
+    This method applies the preprocessing steps to the training, validation, and test datasets.
+    """
+    if os.path.exists("/kaggle/input/X_train.pkl"):
+        X_train = pd.read_pickle("/kaggle/input/X_train.pkl")
+        X_valid = pd.read_pickle("/kaggle/input/X_valid.pkl")
+        y_train = pd.read_pickle("/kaggle/input/y_train.pkl")
+        y_valid = pd.read_pickle("/kaggle/input/y_valid.pkl")
+        X_test = pd.read_pickle("/kaggle/input/X_test.pkl")
+        others = pd.read_pickle("/kaggle/input/others.pkl")
+
+        return X_train, X_valid, y_train, y_valid, X_test, *others
+
+    X_train, X_valid, y_train, y_valid = prepreprocess()
+
+    # Load and preprocess the test data
+    submission_df = pd.read_csv("/kaggle/input/test.csv")
+    ids = submission_df["Id"]
+    X_test = submission_df.drop(["Id"], axis=1)
+
+    return X_train, X_valid, y_train, y_valid, X_test, ids
+
+
+def clean_and_impute_data(X_train, X_valid, X_test):
+    """
+    Handles inf and -inf values by replacing them with NaN,
+    then imputes missing values using the mean strategy.
+    Also removes duplicate columns.
+    """
+    # Replace inf and -inf with NaN
+    X_train.replace([np.inf, -np.inf], np.nan, inplace=True)
+    X_valid.replace([np.inf, -np.inf], np.nan, inplace=True)
+    X_test.replace([np.inf, -np.inf], np.nan, inplace=True)
+
+    # Impute missing values
+    imputer = SimpleImputer(strategy="mean")
+    X_train = pd.DataFrame(imputer.fit_transform(X_train), columns=X_train.columns)
+    X_valid = pd.DataFrame(imputer.transform(X_valid), columns=X_valid.columns)
+    X_test = pd.DataFrame(imputer.transform(X_test), columns=X_test.columns)
+
+    # Remove duplicate columns
+    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()]
+
+    return X_train, X_valid, X_test

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/feature/feature.py

@@ -0,0 +1,23 @@
+import pandas as pd
+
+"""
+Here is the feature engineering code for each task, with a class that has a fit and transform method.
+Remember
+"""
+
+
+class IdentityFeature:
+    def fit(self, train_df: pd.DataFrame):
+        """
+        Fit the feature engineering model to the training data.
+        """
+        pass
+
+    def transform(self, X: pd.DataFrame):
+        """
+        Transform the input data.
+        """
+        return X
+
+
+feature_engineering_cls = IdentityFeature

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/model/model_randomforest.py

@@ -0,0 +1,38 @@
+"""
+Motivation of the model:
+The Random Forest model is chosen for its robustness and ability to handle large datasets with higher dimensionality.
+It reduces overfitting by averaging multiple decision trees and typically performs well out of the box, making it a good
+baseline model for many classification tasks.
+"""
+
+import pandas as pd
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score
+
+
+def fit(X_train: pd.DataFrame, y_train: pd.Series, X_valid: pd.DataFrame, y_valid: pd.Series):
+    """
+    Define and train the Random Forest model. Merge feature selection into the pipeline.
+    """
+    # Initialize the Random Forest model
+    model = RandomForestClassifier(n_estimators=200, random_state=32, n_jobs=-1)
+
+    # Fit the model
+    model.fit(X_train, y_train)
+
+    # Validate the model
+    y_valid_pred = model.predict(X_valid)
+    accuracy = accuracy_score(y_valid, y_valid_pred)
+    print(f"Validation Accuracy: {accuracy:.4f}")
+
+    return model
+
+
+def predict(model, X):
+    """
+    Keep feature selection's consistency and make predictions.
+    """
+    # Predict using the trained model
+    y_pred = model.predict(X)
+
+    return y_pred.reshape(-1, 1)

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/model/model_xgboost.py

@@ -0,0 +1,35 @@
+"""
+motivation  of the model
+"""
+
+import pandas as pd
+import xgboost as xgb
+
+
+def fit(X_train: pd.DataFrame, y_train: pd.DataFrame, X_valid: pd.DataFrame, y_valid: pd.DataFrame):
+    """Define and train the model. Merge feature_select"""
+    dtrain = xgb.DMatrix(X_train, label=y_train)
+    dvalid = xgb.DMatrix(X_valid, label=y_valid)
+
+    params = {
+        "objective": "multi:softmax",  # Use softmax for multi-class classification
+        "num_class": len(set(y_train)),  # Number of classes
+        "nthread": -1,
+        "tree_method": "gpu_hist",
+        "device": "cuda",
+    }
+    num_round = 100
+
+    evallist = [(dtrain, "train"), (dvalid, "eval")]
+    bst = xgb.train(params, dtrain, num_round, evallist)
+
+    return bst
+
+
+def predict(model, X):
+    """
+    Keep feature select's consistency.
+    """
+    dtest = xgb.DMatrix(X)
+    y_pred = model.predict(dtest)
+    return y_pred.astype(int).reshape(-1, 1)

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/model/select_lightgbm.py

@@ -0,0 +1,12 @@
+import pandas as pd
+
+
+def select(X: pd.DataFrame) -> pd.DataFrame:
+    """
+    Select relevant features. To be used in fit & predict function.
+    """
+    # For now, we assume all features are relevant. This can be expanded to feature selection logic.
+    if X.columns.nlevels == 1:
+        return X
+    X.columns = ["_".join(str(i) for i in col).strip() for col in X.columns.values]
+    return X

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/model/select_nn.py

@@ -0,0 +1,12 @@
+import pandas as pd
+
+
+def select(X: pd.DataFrame) -> pd.DataFrame:
+    """
+    Select relevant features. To be used in fit & predict function.
+    """
+    # For now, we assume all features are relevant. This can be expanded to feature selection logic.
+    if X.columns.nlevels == 1:
+        return X
+    X.columns = ["_".join(str(i) for i in col).strip() for col in X.columns.values]
+    return X

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/model/select_randomforest.py

@@ -0,0 +1,12 @@
+import pandas as pd
+
+
+def select(X: pd.DataFrame) -> pd.DataFrame:
+    """
+    Select relevant features. To be used in fit & predict function.
+    """
+    # For now, we assume all features are relevant. This can be expanded to feature selection logic.
+    if X.columns.nlevels == 1:
+        return X
+    X.columns = ["_".join(str(i) for i in col).strip() for col in X.columns.values]
+    return X

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/model/select_xgboost.py

@@ -0,0 +1,12 @@
+import pandas as pd
+
+
+def select(X: pd.DataFrame) -> pd.DataFrame:
+    """
+    Select relevant features. To be used in fit & predict function.
+    """
+    # For now, we assume all features are relevant. This can be expanded to feature selection logic.
+    if X.columns.nlevels == 1:
+        return X
+    X.columns = ["_".join(str(i) for i in col).strip() for col in X.columns.values]
+    return X

rdagent/scenarios/kaggle/experiment/tabular-playground-series-dec-2021_template/train.py

@@ -0,0 +1,91 @@
+import importlib.util
+import random
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+from fea_share_preprocess import clean_and_impute_data, preprocess_script
+from sklearn.metrics import accuracy_score, matthews_corrcoef
+
+# Set random seed for reproducibility
+SEED = 42
+random.seed(SEED)
+np.random.seed(SEED)
+DIRNAME = Path(__file__).absolute().resolve().parent
+
+
+def compute_metrics_for_classification(y_true, y_pred):
+    """Compute MCC for classification."""
+    mcc = matthews_corrcoef(y_true, y_pred)
+    return mcc
+
+
+def import_module_from_path(module_name, module_path):
+    spec = importlib.util.spec_from_file_location(module_name, module_path)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+# 1) Preprocess the data
+X_train, X_valid, y_train, y_valid, X_test, ids = preprocess_script()
+
+# 2) Auto feature engineering
+X_train_l, X_valid_l = [], []
+X_test_l = []
+
+for f in DIRNAME.glob("feature/feat*.py"):
+    cls = import_module_from_path(f.stem, f).feature_engineering_cls()
+    cls.fit(X_train)
+    X_train_f = cls.transform(X_train)
+    X_valid_f = cls.transform(X_valid)
+    X_test_f = cls.transform(X_test)
+
+    if X_train_f.shape[-1] == X_valid_f.shape[-1] and X_train_f.shape[-1] == X_test_f.shape[-1]:
+        X_train_l.append(X_train_f)
+        X_valid_l.append(X_valid_f)
+        X_test_l.append(X_test_f)
+
+X_train = pd.concat(X_train_l, axis=1, keys=[f"feature_{i}" for i in range(len(X_train_l))])
+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))])
+
+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)
+
+
+model_l = []  # list[tuple[model, predict_func]]
+for f in DIRNAME.glob("model/model*.py"):
+    select_python_path = f.with_name(f.stem.replace("model", "select") + f.suffix)
+    select_m = import_module_from_path(select_python_path.stem, select_python_path)
+    X_train_selected = select_m.select(X_train.copy())
+    X_valid_selected = select_m.select(X_valid.copy())
+
+    m = import_module_from_path(f.stem, f)
+    model_l.append((m.fit(X_train_selected, y_train, X_valid_selected, y_valid), m.predict, select_m))
+
+# 4) Evaluate the model on the validation set
+metrics_all = []
+for model, predict_func, select_m in model_l:
+    X_valid_selected = select_m.select(X_valid.copy())
+    y_valid_pred = predict_func(model, X_valid_selected)
+    accuracy = accuracy_score(y_valid, y_valid_pred)
+    print(f"final accuracy on valid set: {accuracy}")
+    metrics_all.append(accuracy)
+
+# 5) Save the validation accuracy
+max_index = np.argmax(metrics_all)
+pd.Series(data=[metrics_all[max_index]], index=["multi-class accuracy"]).to_csv("submission_score.csv")
+
+# 6) Make predictions on the test set and save them
+X_test_selected = model_l[max_index][2].select(X_test.copy())
+y_test_pred = model_l[max_index][1](model_l[max_index][0], X_test_selected).flatten() + 1
+
+
+# 7) Submit predictions for the test set
+submission_result = pd.DataFrame(y_test_pred, columns=["Cover_Type"])
+submission_result.insert(0, "Id", ids)
+
+submission_result.to_csv("submission.csv", index=False)

rdagent/scenarios/kaggle/kaggle_crawler.py

@@ -100,33 +100,27 @@ def kaggle_description_css_selectors() -> tuple[str, str]:
 def download_data(competition: str, local_path: str = KAGGLE_IMPLEMENT_SETTING.local_data_path) -> None:
     if KAGGLE_IMPLEMENT_SETTING.if_using_mle_data:
         zipfile_path = f"{local_path}/zip_files"
-        if not Path(zipfile_path).exists():
+        zip_competition_path = Path(zipfile_path) / competition
+        if not zip_competition_path.exists():
             try:
                 subprocess.run(
-                    ["mlebench", "prepare", "-c", competition, "-p", zipfile_path],
+                    ["mlebench", "prepare", "-c", competition, "--data-dir", zipfile_path],
                     check=True,
                     stderr=subprocess.PIPE,
                     stdout=subprocess.PIPE,
                 )
             except subprocess.CalledProcessError as e:
                 logger.error(f"Download failed: {e}, stderr: {e.stderr}, stdout: {e.stdout}")
                 raise KaggleError(f"Download failed: {e}, stderr: {e.stderr}, stdout: {e.stdout}")
-        # unzip data
-        unzip_path = Path(local_path) / f"{competition}_test"
-        if not unzip_path.exists():
-            unzip_data(unzip_file_path=f"{zipfile_path}/{competition}.zip", unzip_target_path=unzip_path)
-            for sub_zip_file in unzip_path.rglob("*.zip"):
-                unzip_data(sub_zip_file, unzip_target_path=unzip_path)
-
-        competition_path = Path(local_path) / competition
-        competition_path.mkdir(parents=True, exist_ok=True)
-        processed_data_folder_path = unzip_path / "prepared/public"
-        subprocess.run(f"cp -r {processed_data_folder_path}/* {competition_path}", shell=True)
-        subprocess.run(f"rm -rf {unzip_path}", shell=True)
+
+            competition_path = Path(local_path) / competition
+            competition_path.mkdir(parents=True, exist_ok=True)
+            processed_data_folder_path = zip_competition_path / "prepared/public"
+            subprocess.run(f"cp -r {processed_data_folder_path}/* {competition_path}", shell=True)
 
     else:
         zipfile_path = f"{local_path}/zip_files"
-        if not Path(zipfile_path).exists():
+        if not Path(f"{zipfile_path}/{competition}.zip").exists():
             try:
                 subprocess.run(
                     ["kaggle", "competitions", "download", "-c", competition, "-p", zipfile_path],
@@ -138,12 +132,12 @@ def download_data(competition: str, local_path: str = KAGGLE_IMPLEMENT_SETTING.l
                 logger.error(f"Download failed: {e}, stderr: {e.stderr}, stdout: {e.stdout}")
                 raise KaggleError(f"Download failed: {e}, stderr: {e.stderr}, stdout: {e.stdout}")
 
-        # unzip data
-        unzip_path = f"{local_path}/{competition}"
-        if not Path(unzip_path).exists():
-            unzip_data(unzip_file_path=f"{zipfile_path}/{competition}.zip", unzip_target_path=unzip_path)
-            for sub_zip_file in Path(unzip_path).rglob("*.zip"):
-                unzip_data(sub_zip_file, unzip_target_path=unzip_path)
+            # unzip data
+            unzip_path = f"{local_path}/{competition}"
+            if not Path(unzip_path).exists():
+                unzip_data(unzip_file_path=f"{zipfile_path}/{competition}.zip", unzip_target_path=unzip_path)
+                for sub_zip_file in Path(unzip_path).rglob("*.zip"):
+                    unzip_data(sub_zip_file, unzip_target_path=unzip_path)
 
 
 def unzip_data(unzip_file_path: str, unzip_target_path: str) -> None: