{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":96164,"databundleVersionId":11418275,"sourceType":"competition"},{"sourceId":12411677,"sourceType":"datasetVersion","datasetId":7827653}],"dockerImageVersionId":31040,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-05-29T00:22:11.850191Z","iopub.execute_input":"2025-05-29T00:22:11.850472Z","iopub.status.idle":"2025-05-29T00:22:13.83001Z","shell.execute_reply.started":"2025-05-29T00:22:11.850441Z","shell.execute_reply":"2025-05-29T00:22:13.829184Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"The commented out code below will produce a submission.csv file with a slightly improved score. I am trying to tune this offline and add new features so I've commented out the results and just imported the CSV. Please feel free to comment out the code below and run it for yourself, preferably with GPU acceleration.","metadata":{}},{"cell_type":"code","source":"# import pandas as pd\n\n# # Load the remix submission file\n# input_path = \"/kaggle/input/drw-remix-ii-remix-again-data/DRW Remix II - Remix Again.csv\"\n# output_path = \"submission.csv\"\n\n# # Read the CSV file\n# df = pd.read_csv(input_path)\n\n# # Save it as submission.csv\n# df.to_csv(output_path, index=False)\n\n# print(f\"Successfully loaded file from: {input_path}\")\n# print(f\"Saved as: {output_path}\")\n# print(f\"Shape: {df.shape}\")\n# print(f\"Columns: {list(df.columns)}\")\n# print(f\"\\nFirst few rows:\")\n# print(df.head())","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import sys\nimport pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import KFold\nfrom xgboost import XGBRegressor\nfrom lightgbm import LGBMRegressor\nfrom scipy.stats import pearsonr\n\ndef feature_engineering(df):\n   #10\n    df['exp_856P868P855P289'] = np.exp(df['X856'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_860P868P855P289'] = np.exp(df['X860'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_598P868P855P289'] = np.exp(df['X598'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_612P868P855P289'] = np.exp(df['X612'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_289P855P21'] = np.exp(df['X289'] + df['X855'] + df['X21'])\n    df['868xexp_289M125'] = df['X868'] * np.exp(df['X289'] - df['X125'])\n    #9\n    df['exp_603P868P855P289'] = np.exp(df['X603'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_174P868P855P289'] = np.exp(df['X174'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_465P868P855P289'] = np.exp(df['X465'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_125P862P289M125'] = np.exp(df['X125'] + df['X862'] + df['X289'] - df['X125'])\n    df['exp_168P868P855P289'] = np.exp(df['X168'] + df['X868'] + df['X855'] + df['X289'])\n    df['exp_855P289M125'] = np.exp(df['X855'] + df['X289'] - df['X125'])\n    df['exp_302P289M125'] = np.exp(df['X302'] + df['X289'] - df['X125'])\n    df['289xexp_289M125'] = df['X289'] * np.exp(df['X289'] - df['X125'])\n    #8\n    df['exp_862P868P855P289'] = np.exp(df['X862'] + df['X868'] + df['X855'] + df['X289'])\n    df['868x868x855x289'] = df['X868'] * df['X868'] * df['X855'] * df['X289']\n    df['385xexp_289M125'] = df['X385'] * np.exp(df['X289'] - df['X125'])\n    df['exp_862P289M125'] = np.exp(df['X862'] + df['X289'] - df['X125'])\n    df['exp_786P289M125'] = np.exp(df['X786'] + df['X289'] - df['X125'])\n    df['exp_856P289M125'] = np.exp(df['X856'] + df['X289'] - df['X125'])\n    df['852x868x855x289'] = df['X852'] * df['X868'] * df['X855'] * df['X289']\n    df['465x862x465']=df['X465']*df['X465']*df['X862']\n    df['540x881']=df['X540']*df['X881']\n    \n    df['bid_ask_interaction'] = df['bid_qty'] * df['ask_qty']\n    df['bid_buy_interaction'] = df['bid_qty'] * df['buy_qty']\n    df['bid_sell_interaction'] = df['bid_qty'] * df['sell_qty']\n    df['ask_buy_interaction'] = df['ask_qty'] * df['buy_qty']\n    df['ask_sell_interaction'] = df['ask_qty'] * df['sell_qty']\n\n    df['volume_weighted_sell'] = df['sell_qty'] * df['volume']\n    df['buy_sell_ratio'] = df['buy_qty'] / (df['sell_qty'] + 1e-10)\n    df['selling_pressure'] = df['sell_qty'] / (df['volume'] + 1e-10)\n    df['log_volume'] = np.log1p(df['volume'])\n\n    df['effective_spread_proxy'] = np.abs(df['buy_qty'] - df['sell_qty']) / (df['volume'] + 1e-10)\n    df['bid_ask_imbalance'] = (df['bid_qty'] - df['ask_qty']) / (df['bid_qty'] + df['ask_qty'] + 1e-10)\n    df['order_flow_imbalance'] = (df['buy_qty'] - df['sell_qty']) / (df['buy_qty'] + df['sell_qty'] + 1e-10)\n    df['liquidity_ratio'] = (df['bid_qty'] + df['ask_qty']) / (df['volume'] + 1e-10)\n    \n    df['ask_buy_interaction_x_X293']=df['X293']*df['ask_buy_interaction']\n     # Price Pressure Indicators\n    df['net_order_flow'] = df['buy_qty'] - df['sell_qty']\n    df['normalized_net_flow'] = df['net_order_flow'] / (df['volume'] + 1e-10)\n    df['buying_pressure'] = df['buy_qty'] / (df['volume'] + 1e-10)\n    df['volume_weighted_buy'] = df['buy_qty'] * df['volume']\n    \n    # Liquidity Depth Measures\n    df['total_depth'] = df['bid_qty'] + df['ask_qty']\n    df['depth_imbalance'] = (df['bid_qty'] - df['ask_qty']) / (df['total_depth'] + 1e-10)\n    df['relative_spread'] = np.abs(df['bid_qty'] - df['ask_qty']) / (df['total_depth'] + 1e-10)\n    df['log_depth'] = np.log1p(df['total_depth'])\n    \n    # Order Flow Toxicity Proxies\n    df['kyle_lambda'] = np.abs(df['net_order_flow']) / (df['volume'] + 1e-10)\n    df['flow_toxicity'] = np.abs(df['order_flow_imbalance']) * df['volume']\n    df['aggressive_flow_ratio'] = (df['buy_qty'] + df['sell_qty']) / (df['total_depth'] + 1e-10)\n    \n    # Market Activity Indicators\n    df['volume_depth_ratio'] = df['volume'] / (df['total_depth'] + 1e-10)\n    df['activity_intensity'] = (df['buy_qty'] + df['sell_qty']) / (df['volume'] + 1e-10)\n    df['log_buy_qty'] = np.log1p(df['buy_qty'])\n    df['log_sell_qty'] = np.log1p(df['sell_qty'])\n    df['log_bid_qty'] = np.log1p(df['bid_qty'])\n    df['log_ask_qty'] = np.log1p(df['ask_qty'])\n    \n    # Microstructure Volatility Proxies\n    df['realized_spread_proxy'] = 2 * np.abs(df['net_order_flow']) / (df['volume'] + 1e-10)\n    df['price_impact_proxy'] = df['net_order_flow'] / (df['total_depth'] + 1e-10)\n    df['quote_volatility_proxy'] = np.abs(df['depth_imbalance'])\n    \n    # Complex Interaction Terms\n    df['flow_depth_interaction'] = df['net_order_flow'] * df['total_depth']\n    df['imbalance_volume_interaction'] = df['order_flow_imbalance'] * df['volume']\n    df['depth_volume_interaction'] = df['total_depth'] * df['volume']\n    df['buy_sell_spread'] = np.abs(df['buy_qty'] - df['sell_qty'])\n    df['bid_ask_spread'] = np.abs(df['bid_qty'] - df['ask_qty'])\n    \n    # Information Asymmetry Measures\n    df['trade_informativeness'] = df['net_order_flow'] / (df['bid_qty'] + df['ask_qty'] + 1e-10)\n    df['execution_shortfall_proxy'] = df['buy_sell_spread'] / (df['volume'] + 1e-10)\n    df['adverse_selection_proxy'] = df['net_order_flow'] / (df['total_depth'] + 1e-10) * df['volume']\n    \n    # Market Efficiency Indicators\n    df['fill_probability'] = df['volume'] / (df['buy_qty'] + df['sell_qty'] + 1e-10)\n    df['execution_rate'] = (df['buy_qty'] + df['sell_qty']) / (df['total_depth'] + 1e-10)\n    df['market_efficiency'] = df['volume'] / (df['bid_ask_spread'] + 1e-10)\n    \n    # Non-linear Transformations\n    df['sqrt_volume'] = np.sqrt(df['volume'])\n    df['sqrt_depth'] = np.sqrt(df['total_depth'])\n    df['volume_squared'] = df['volume'] ** 2\n    df['imbalance_squared'] = df['order_flow_imbalance'] ** 2\n    \n    # Relative Measures\n    df['bid_ratio'] = df['bid_qty'] / (df['total_depth'] + 1e-10)\n    df['ask_ratio'] = df['ask_qty'] / (df['total_depth'] + 1e-10)\n    df['buy_ratio'] = df['buy_qty'] / (df['buy_qty'] + df['sell_qty'] + 1e-10)\n    df['sell_ratio'] = df['sell_qty'] / (df['buy_qty'] + df['sell_qty'] + 1e-10)\n    \n    # Market Stress Indicators\n    df['liquidity_consumption'] = (df['buy_qty'] + df['sell_qty']) / (df['total_depth'] + 1e-10)\n    df['market_stress'] = df['volume'] / (df['total_depth'] + 1e-10) * np.abs(df['order_flow_imbalance'])\n    df['depth_depletion'] = df['volume'] / (df['bid_qty'] + df['ask_qty'] + 1e-10)\n    \n    # Directional Indicators\n    df['net_buying_ratio'] = df['net_order_flow'] / (df['volume'] + 1e-10)\n    df['directional_volume'] = df['net_order_flow'] * np.log1p(df['volume'])\n    df['signed_volume'] = np.sign(df['net_order_flow']) * df['volume']\n\n    #etc\n    df['sqrt_volume_div_log_volume'] = df['sqrt_volume'] / (df['log_volume'] + 1e-6)\n    df['sqrt_volume_div_activity_intensity'] = df['sqrt_volume'] / (df['activity_intensity'] + 1e-6)\n    df['sqrt_volume_mul_fill_probability'] = df['sqrt_volume'] * df['fill_probability']\n    df['volume_div_sqrt_volume'] = df['volume'] / (df['sqrt_volume'] + 1e-6)\n    df['sqrt_volume_div_fill_probability'] = df['sqrt_volume'] / (df['fill_probability'] + 1e-6)\n    df['sqrt_volume_mul_activity_intensity'] = df['sqrt_volume'] * df['activity_intensity']\n    df['sqrt_volume_div_log_sell_qty'] = df['sqrt_volume'] / (df['log_sell_qty'] + 1e-6)\n    df['log_buy_qty_mul_sqrt_volume'] = df['log_buy_qty'] * df['sqrt_volume']\n    df['sqrt_volume_mul_log_buy_qty'] = df['sqrt_volume'] * df['log_buy_qty']\n    df['log_volume_mul_sqrt_volume'] = df['log_volume'] * df['sqrt_volume']\n    \n    df['log_sell_qty_mul_X598'] = df['log_sell_qty'] * df['X598']\n    df['log_buy_qty_mul_X598'] = df['log_buy_qty'] * df['X598']\n    df['log_volume_mul_X598'] = df['log_volume'] * df['X598']\n    \n    df['sqrt_volume_mul_X856'] = df['sqrt_volume'] * df['X856']\n    \n    df['log_sell_qty_mul_X302'] = df['log_sell_qty'] * df['X302']\n    df['log_volume_mul_X302'] = df['log_volume'] * df['X302']\n    df['log_buy_qty_mul_X302'] = df['log_buy_qty'] * df['X302']\n    \n    df['log_sell_qty_mul_X292'] = df['log_sell_qty'] * df['X292']\n    \n    \n    df = df.replace([np.inf, -np.inf], np.nan)\n    df = df.fillna(0)\n    return df \n\nclass Config:\n    TRAIN_PATH = \"/kaggle/input/drw-crypto-market-prediction/train.parquet\"\n    TEST_PATH = \"/kaggle/input/drw-crypto-market-prediction/test.parquet\"\n    SUBMISSION_PATH = \"/kaggle/input/drw-crypto-market-prediction/sample_submission.csv\"\n\n    FEATURES = [\n        \"X863\", \"X856\", \"X598\", \"X862\", \"X385\", \"X852\", \"X603\", \"X860\", \"X674\",\n        \"X415\", \"X345\", \"X855\", \"X174\", \"X302\", \"X178\", \"X168\", \"X612\",\n        \"bid_qty\", \"ask_qty\", \"buy_qty\", \"sell_qty\", \"volume\", \"X888\", \"X421\", \"X333\",\n        'X465','X153','X289','X125','X21',\"X868\", \"X786\" ,\"X293\",\"X873\",'X540','X493','X862',\n        'X881','X425','X858',\"X292\",\"X817\", \"X586\"\n        \n        \n    ]\n    SELECTED_FEATURES=[\n\n        \"X863\", \"X856\", \"X598\", \"X862\", \"X385\", \"X603\", \"X860\", \"X674\",\n        \"X415\", \"X345\", \"X855\", \"X174\", \"X302\", \"X178\", \"X168\", \"X612\",\n        \"buy_qty\", \"sell_qty\", \"volume\", \n        \"X888\", \"X421\", \"X333\",\"X292\",\"X817\", \n        \"X586\",\n        'ask_buy_interaction_x_X293',  '868xexp_289M125','exp_786P289M125','exp_856P289M125',\n        'exp_612P868P855P289','exp_598P868P855P289',\n        'exp_855P289M125',\n        '385xexp_289M125','465x862x465','540x881','exp_125P862P289M125','bid_ask_interaction', 'bid_buy_interaction', 'bid_sell_interaction', 'ask_buy_interaction',\n        'ask_sell_interaction', \"log_volume\", 'net_order_flow', 'normalized_net_flow',\n        'buying_pressure', 'volume_weighted_buy', 'total_depth', 'depth_imbalance',\n        'relative_spread', 'log_depth', 'kyle_lambda', 'flow_toxicity', 'aggressive_flow_ratio',\n        'volume_depth_ratio', 'activity_intensity', 'log_buy_qty', 'log_sell_qty',\n        'log_bid_qty', 'log_ask_qty', 'realized_spread_proxy', 'price_impact_proxy',\n        'quote_volatility_proxy', 'flow_depth_interaction', 'imbalance_volume_interaction',\n        'depth_volume_interaction',  'trade_informativeness',\n        'execution_shortfall_proxy', 'adverse_selection_proxy', 'fill_probability',\n        'execution_rate', 'market_efficiency', 'sqrt_volume', 'sqrt_depth', 'volume_squared',\n        'imbalance_squared', 'bid_ratio', 'ask_ratio', 'buy_ratio', 'sell_ratio',\n        'liquidity_consumption', 'market_stress', 'depth_depletion', 'net_buying_ratio',\n        'directional_volume', 'signed_volume',   \n        \n    \n        #\"sqrt_volume_div_activity_intensity\",\n        \"sqrt_volume_mul_fill_probability\",\n        \"volume_div_sqrt_volume\",\n        #\"sqrt_volume_div_fill_probability\",\n        #\"sqrt_volume_mul_activity_intensity\",\n        #\"sqrt_volume_div_log_sell_qty\",\n        \"log_buy_qty_mul_sqrt_volume\",\n        \"sqrt_volume_mul_log_buy_qty\",\n        \"log_volume_mul_sqrt_volume\",\n        \n        #\"log_sell_qty_mul_X598\",\n        #\"log_buy_qty_mul_X598\",\n        #\"log_volume_mul_X598\",\n        \"sqrt_volume_mul_X856\",\n        \"log_sell_qty_mul_X302\",\n        \"log_volume_mul_X302\",\n        \"log_buy_qty_mul_X302\",\n        \"log_sell_qty_mul_X292\"\n\n\n                      \n    \n    ]\n\n    LABEL_COLUMN = \"label\"\n    N_FOLDS = 3\n    RANDOM_STATE = 42\n\nXGB_PARAMS = {\n    \"tree_method\": \"hist\",\n    \"device\": \"gpu\",\n    \"colsample_bylevel\": 0.4778,\n    \"colsample_bynode\": 0.3628,\n    \"colsample_bytree\": 0.7107,\n    \"gamma\": 1.7095,\n    \"learning_rate\": 0.02213,\n    \"max_depth\": 20,\n    \"max_leaves\": 12,\n    \"min_child_weight\": 16,\n    \"n_estimators\": 1667,\n    \"subsample\": 0.06567,\n    \"reg_alpha\": 39.3524,\n    \"reg_lambda\": 75.4484,\n    \"verbosity\": 0,\n    \"random_state\": Config.RANDOM_STATE,\n    \"n_jobs\": -1\n}\n\nLEARNERS = [\n    {\"name\": \"xgb\", \"Estimator\": XGBRegressor, \"params\": XGB_PARAMS},\n]\n\ndef create_time_decay_weights(n: int, decay: float = 0.9) -> np.ndarray:\n    positions = np.arange(n)\n    normalized = positions / (n - 1)\n    weights = decay ** (1.0 - normalized)\n    return weights * n / weights.sum()\n\ndef load_data():\n    train_df = pd.read_parquet(Config.TRAIN_PATH, columns=Config.FEATURES + [Config.LABEL_COLUMN])\n    test_df = pd.read_parquet(Config.TEST_PATH, columns=Config.FEATURES)\n    submission_df = pd.read_csv(Config.SUBMISSION_PATH)\n\n    train_df = feature_engineering(train_df)\n    test_df = feature_engineering(test_df)\n    print(f\"Loaded data - Train: {train_df.shape}, Test: {test_df.shape}, Submission: {submission_df.shape}\")\n    return train_df.reset_index(drop=True), test_df.reset_index(drop=True), submission_df\n\n#Config.FEATURES += [\"bid_qty\", \"ask_qty\", \"buy_qty\", \"sell_qty\", \"volume\"]\nConfig.FEATURES = list(set(Config.FEATURES))  # remove duplicates\n\ndef get_model_slices(n_samples: int):\n    base_slices = [\n        {\"name\": \"full_data\", \"cutoff\": 0, \"is_oldest\": False, \"outlier_adjusted\": False},\n        {\"name\": \"last_90pct\", \"cutoff\": int(0.10 * n_samples), \"is_oldest\": False, \"outlier_adjusted\": False},\n        {\"name\": \"last_85pct\", \"cutoff\": int(0.15 * n_samples), \"is_oldest\": False, \"outlier_adjusted\": False},\n        {\"name\": \"last_80pct\", \"cutoff\": int(0.20 * n_samples), \"is_oldest\": False, \"outlier_adjusted\": False},\n        {\"name\": \"last_50pct\", \"cutoff\": int(0.50 * n_samples), \"is_oldest\": False, \"outlier_adjusted\": False},\n        {\"name\": \"oldest_23pct\", \"cutoff\": int(0.23 * n_samples), \"is_oldest\": True, \"outlier_adjusted\": False},\n    ]\n    \n    # Duplicate slices with outlier adjustment\n    outlier_adjusted_slices = []\n    for slice_info in base_slices:\n        adjusted_slice = slice_info.copy()\n        adjusted_slice[\"name\"] = f\"{slice_info['name']}_outlier_adj\"\n        adjusted_slice[\"outlier_adjusted\"] = True\n        outlier_adjusted_slices.append(adjusted_slice)\n    \n    return base_slices + outlier_adjusted_slices\n\ndef train_and_evaluate(train_df, test_df):\n    n_samples = len(train_df)\n    model_slices = get_model_slices(n_samples)\n\n    oof_preds = {\n        learner[\"name\"]: {s[\"name\"]: np.zeros(n_samples) for s in model_slices}\n        for learner in LEARNERS\n    }\n    test_preds = {\n        learner[\"name\"]: {s[\"name\"]: np.zeros(len(test_df)) for s in model_slices}\n        for learner in LEARNERS\n    }\n\n    # 모델 저장용 딕셔너리 추가 (예: learner_name -> slice_name -> list of models per fold)\n    trained_models = {\n        learner[\"name\"]: {s[\"name\"]: [] for s in model_slices}\n        for learner in LEARNERS\n    }\n\n    full_weights = create_time_decay_weights(n_samples)\n    kf = KFold(n_splits=Config.N_FOLDS, shuffle=False)\n\n    for fold, (train_idx, valid_idx) in enumerate(kf.split(train_df), start=1):\n        print(f\"\\n--- Fold {fold}/{Config.N_FOLDS} ---\")\n        X_valid = train_df.iloc[valid_idx][Config.SELECTED_FEATURES]\n        y_valid = train_df.iloc[valid_idx][Config.LABEL_COLUMN]\n\n        for s in model_slices:\n            cutoff = s[\"cutoff\"]\n            slice_name = s[\"name\"]\n            subset = train_df.iloc[cutoff:].reset_index(drop=True)\n            rel_idx = train_idx[train_idx >= cutoff] - cutoff\n\n            X_train = subset.iloc[rel_idx][Config.SELECTED_FEATURES]\n            y_train = subset.iloc[rel_idx][Config.LABEL_COLUMN]\n            sw = create_time_decay_weights(len(subset))[rel_idx] if cutoff > 0 else full_weights[train_idx]\n\n            print(f\"  Training slice: {slice_name}, samples: {len(X_train)}\")\n\n            for learner in LEARNERS:\n                model = learner[\"Estimator\"](**learner[\"params\"])\n                model.fit(X_train, y_train, sample_weight=sw, eval_set=[(X_valid, y_valid)], verbose=False)\n\n                # 학습된 모델 저장\n                trained_models[learner[\"name\"]][slice_name].append(model)\n\n                mask = valid_idx >= cutoff\n                if mask.any():\n                    idxs = valid_idx[mask]\n                    oof_preds[learner[\"name\"]][slice_name][idxs] = model.predict(train_df.iloc[idxs][Config.SELECTED_FEATURES])\n                if cutoff > 0 and (~mask).any():\n                    oof_preds[learner[\"name\"]][slice_name][valid_idx[~mask]] = oof_preds[learner[\"name\"]][\"full_data\"][valid_idx[~mask]]\n\n                test_preds[learner[\"name\"]][slice_name] += model.predict(test_df[Config.SELECTED_FEATURES])\n\n    # Normalize test predictions\n    for learner_name in test_preds:\n        for slice_name in test_preds[learner_name]:\n            test_preds[learner_name][slice_name] /= Config.N_FOLDS\n\n    return oof_preds, test_preds, model_slices, trained_models\n\nmanual_weights = {\n    \"full_data\": 1,\n    \"last_90pct\": 1,\n    \"last_85pct\": 1,\n    \"last_80pct\": 1,\n    \"last_50pct\": 1,\n    \"oldest_23pct\": 1,\n}\ndef ensemble_and_submit(train_df, oof_preds, test_preds, submission_df, manual_weights=None):\n    learner_ensembles = {}\n\n    # 슬라이스 weight 설정\n    weights = manual_weights if manual_weights is not None else {\n        s: 1.0 for s in next(iter(oof_preds.values())).keys()\n    }\n\n    total_weight = sum(weights.values())\n\n    for learner_name in oof_preds:\n        oof_weighted = sum(\n            weights[s] / total_weight * oof_preds[learner_name][s]\n            for s in weights if s in oof_preds[learner_name]\n        )\n        test_weighted = sum(\n            weights[s] / total_weight * test_preds[learner_name][s]\n            for s in weights if s in test_preds[learner_name]\n        )\n\n        score_weighted = pearsonr(train_df[Config.LABEL_COLUMN], oof_weighted)[0]\n\n        print(f\"{learner_name.upper()} Weighted Ensemble Pearson: {score_weighted:.4f}\")\n\n        learner_ensembles[learner_name] = {\n            \"oof_weighted\": oof_weighted,\n            \"test_weighted\": test_weighted\n        }\n\n    # 여러 learner 평균\n    final_oof = np.mean([le[\"oof_weighted\"] for le in learner_ensembles.values()], axis=0)\n    final_test = np.mean([le[\"test_weighted\"] for le in learner_ensembles.values()], axis=0)\n    final_score = pearsonr(train_df[Config.LABEL_COLUMN], final_oof)[0]\n\n    print(f\"\\nFINAL ensemble across learners (weighted): {final_score:.4f}\")\n\n    submission_df[\"prediction\"] = final_test\n    submission_df.to_csv(\"submission.csv\", index=False)\n    print(\"Saved: submission.csv\")\n\nif __name__ == \"__main__\":\n    train_df, test_df, submission_df = load_data()\n    oof_preds, test_preds, model_slices,trained_models = train_and_evaluate(train_df, test_df)\n    ensemble_and_submit(train_df, oof_preds, test_preds, submission_df,manual_weights)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-29T00:32:52.889663Z","iopub.execute_input":"2025-05-29T00:32:52.889977Z","iopub.status.idle":"2025-05-29T00:32:52.965518Z","shell.execute_reply.started":"2025-05-29T00:32:52.889952Z","shell.execute_reply":"2025-05-29T00:32:52.964296Z"}},"outputs":[],"execution_count":null}]}