{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":67356,"databundleVersionId":8006601,"sourceType":"competition"}],"dockerImageVersionId":30673,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# [WIP] LightGBM + Voting Model Baseline\nThis is just me combining codes from two great notebooks.\n- Original ecfp code [[Leash Tutorial - ECFPs and Random Forest]](https://www.kaggle.com/code/andrewdblevins/leash-tutorial-ecfps-and-random-forest) by [@andrewdblevins](https://www.kaggle.com/andrewdblevins)\n- Original Voting Model code - [Home Credit Baseline](https://www.kaggle.com/code/greysky/home-credit-baseline) by [@greysky](https://www.kaggle.com/greysky)\n\nGonna take about total 30~40 mins","metadata":{}},{"cell_type":"code","source":"!pip install duckdb","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Import","metadata":{}},{"cell_type":"code","source":"import duckdb\nimport pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.base import BaseEstimator, ClassifierMixin\n# wip\n# import optuna \ntrain_path = '/kaggle/input/leash-BELKA/train.parquet'\ntest_path = '/kaggle/input/leash-BELKA/test.parquet'\n\ncon = duckdb.connect()\n\ndf = con.query(f\"\"\"(SELECT *\n                        FROM parquet_scan('{train_path}')\n                        WHERE binds = 0\n                        ORDER BY random()\n                        LIMIT 30000)\n                        UNION ALL\n                        (SELECT *\n                        FROM parquet_scan('{train_path}')\n                        WHERE binds = 1\n                        ORDER BY random()\n                        LIMIT 30000)\"\"\").df()\n\ncon.close()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Voting Model Define","metadata":{}},{"cell_type":"code","source":"class VotingModel(BaseEstimator, ClassifierMixin):\n    def __init__(self, estimators):\n        super().__init__()\n        self.estimators = estimators\n        \n    def fit(self, X, y=None):\n        return self\n    \n    def predict(self, X):\n        y_preds = [estimator.predict(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)\n    \n    def predict_proba(self, X):\n        y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Generate ECFP","metadata":{}},{"cell_type":"code","source":"from rdkit import Chem\nfrom rdkit.Chem import AllChem\nimport lightgbm as lgb\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import average_precision_score\nfrom sklearn.preprocessing import OneHotEncoder\n\n# Convert SMILES to RDKit molecules\ndf['molecule'] = df['molecule_smiles'].apply(Chem.MolFromSmiles)\n\n# Generate ECFPs\ndef generate_ecfp(molecule, radius=2, bits=1024):\n    if molecule is None:\n        return None\n    return list(AllChem.GetMorganFingerprintAsBitVect(molecule, radius, nBits=bits))\n\ndf['ecfp'] = df['molecule'].apply(generate_ecfp)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Stratified 5 FOLD Voting Model","metadata":{}},{"cell_type":"code","source":"# One-hot encode the protein_name\nonehot_encoder = OneHotEncoder(sparse_output=False)\nprotein_onehot = onehot_encoder.fit_transform(df['protein_name'].values.reshape(-1, 1))\n\n# Combine ECFPs and one-hot encoded protein_name\nX = [ecfp + protein for ecfp, protein in zip(df['ecfp'].tolist(), protein_onehot.tolist())]\nX = pd.DataFrame(X)\ny = df['binds']\n\n# Split the data into train and test sets\n#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\nskf = StratifiedKFold(n_splits=5, shuffle=False)\n\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": 'average_precision',\n    \"max_depth\": 8,\n    \"learning_rate\": 0.05,\n    \"n_estimators\": 1000,\n    \"colsample_bytree\": 0.8, \n    \"colsample_bynode\": 0.8,\n    \"verbose\": -1,\n    \"random_state\": 42,\n    \"device\": \"gpu\",\n}\nfitted_models = []\n\nfor idx_train, idx_valid in skf.split(X, y):\n    X_train, y_train = X.iloc[idx_train], y.iloc[idx_train]\n    X_valid, y_valid = X.iloc[idx_valid], y.iloc[idx_valid]\n\n    model = lgb.LGBMClassifier(**params)\n    model.fit(\n        X_train, y_train,\n        eval_set=[(X_valid, y_valid)],\n        callbacks=[lgb.log_evaluation(100), lgb.early_stopping(100)]\n    )\n\n    fitted_models.append(model)\n\nmodel = VotingModel(fitted_models)\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission ","metadata":{}},{"cell_type":"code","source":"import os\n\n# Process the test.parquet file chunk by chunk\ntest_file = '/kaggle/input/leash-BELKA/test.parquet'\noutput_file = 'submission.csv'  # Specify the path and filename for the output file\n\n# Read the test.parquet file into a pandas DataFrame\nfor df_test in pd.read_csv(test_file, chunksize=100000):\n\n    # Generate ECFPs for the molecule_smiles\n    df_test['molecule'] = df_test['molecule_smiles'].apply(Chem.MolFromSmiles)\n    df_test['ecfp'] = df_test['molecule'].apply(generate_ecfp)\n\n    # One-hot encode the protein_name\n    protein_onehot = onehot_encoder.transform(df_test['protein_name'].values.reshape(-1, 1))\n\n    # Combine ECFPs and one-hot encoded protein_name\n    X_test = [ecfp + protein for ecfp, protein in zip(df_test['ecfp'].tolist(), protein_onehot.tolist())]\n\n    # Predict the probabilities\n    probabilities = model.predict_proba(X_test)[:, 1]\n\n    # Create a DataFrame with 'id' and 'probability' columns\n    output_df = pd.DataFrame({'id': df_test['id'], 'binds': probabilities})\n\n    # Save the output DataFrame to a CSV file\n    output_df.to_csv(output_file, index=False, mode='a', header=not os.path.exists(output_file))","metadata":{},"execution_count":null,"outputs":[]}]}