{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.14"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"},{"sourceId":7453542,"sourceType":"datasetVersion","datasetId":921302}],"dockerImageVersionId":30776,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false},"papermill":{"default_parameters":{},"duration":673.251127,"end_time":"2024-12-12T20:25:29.287784","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-12-12T20:14:16.036657","version":"2.6.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"---\n# Submission 2: Version 7 / Ensemble models 1\n---","metadata":{"papermill":{"duration":0.020535,"end_time":"2024-12-12T20:16:40.222671","exception":false,"start_time":"2024-12-12T20:16:40.202136","status":"completed"},"tags":[]}},{"cell_type":"code","source":"!pip -q install /kaggle/input/pytorchtabnet/pytorch_tabnet-4.1.0-py3-none-any.whl","metadata":{"papermill":{"duration":40.674512,"end_time":"2024-12-12T20:17:20.959469","exception":false,"start_time":"2024-12-12T20:16:40.284957","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:03:58.369229Z","iopub.execute_input":"2025-01-22T10:03:58.369699Z","iopub.status.idle":"2025-01-22T10:04:42.805726Z","shell.execute_reply.started":"2025-01-22T10:03:58.369644Z","shell.execute_reply":"2025-01-22T10:04:42.804118Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from pytorch_tabnet.tab_model import TabNetRegressor\nimport torch","metadata":{"papermill":{"duration":0.039431,"end_time":"2024-12-12T20:17:21.020376","exception":false,"start_time":"2024-12-12T20:17:20.980945","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:04:42.808417Z","iopub.execute_input":"2025-01-22T10:04:42.808822Z","iopub.status.idle":"2025-01-22T10:04:47.584064Z","shell.execute_reply.started":"2025-01-22T10:04:42.808783Z","shell.execute_reply":"2025-01-22T10:04:47.582727Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport re\nfrom sklearn.base import clone\nfrom sklearn.metrics import cohen_kappa_score\nfrom sklearn.model_selection import StratifiedKFold\nfrom scipy.optimize import minimize\nfrom concurrent.futures import ThreadPoolExecutor\nfrom tqdm import tqdm\nimport polars as pl\nimport polars.selectors as cs\nimport matplotlib.pyplot as plt\nfrom matplotlib.ticker import MaxNLocator, FormatStrFormatter, PercentFormatter\nimport seaborn as sns\n\nfrom sklearn.preprocessing import StandardScaler\nimport matplotlib.pyplot as plt\nfrom keras.models import Model\nfrom keras.layers import Input, Dense\nfrom keras.optimizers import Adam\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\n\nfrom colorama import Fore, Style\nfrom IPython.display import clear_output\nimport warnings\nfrom lightgbm import LGBMRegressor\nfrom xgboost import XGBRegressor\nfrom catboost import CatBoostRegressor\nfrom sklearn.ensemble import VotingRegressor, RandomForestRegressor, GradientBoostingRegressor\nfrom sklearn.impute import SimpleImputer, KNNImputer\nfrom sklearn.pipeline import Pipeline\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None","metadata":{"papermill":{"duration":0.029756,"end_time":"2024-12-12T20:17:21.071019","exception":false,"start_time":"2024-12-12T20:17:21.041263","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:04:47.585196Z","iopub.execute_input":"2025-01-22T10:04:47.585824Z","iopub.status.idle":"2025-01-22T10:05:06.240415Z","shell.execute_reply.started":"2025-01-22T10:04:47.585779Z","shell.execute_reply":"2025-01-22T10:05:06.239119Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import random\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(2024)","metadata":{"papermill":{"duration":0.03252,"end_time":"2024-12-12T20:17:21.125269","exception":false,"start_time":"2024-12-12T20:17:21.092749","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:05:06.242938Z","iopub.execute_input":"2025-01-22T10:05:06.243676Z","iopub.status.idle":"2025-01-22T10:05:06.256984Z","shell.execute_reply.started":"2025-01-22T10:05:06.243631Z","shell.execute_reply":"2025-01-22T10:05:06.255696Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"SEED = 42\nn_splits = 5","metadata":{"papermill":{"duration":0.0261,"end_time":"2024-12-12T20:17:21.172107","exception":false,"start_time":"2024-12-12T20:17:21.146007","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:05:06.258880Z","iopub.execute_input":"2025-01-22T10:05:06.259454Z","iopub.status.idle":"2025-01-22T10:05:06.273233Z","shell.execute_reply.started":"2025-01-22T10:05:06.259399Z","shell.execute_reply":"2025-01-22T10:05:06.271990Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def process_file(filename, dirname):\n    df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n    df.drop('step', axis=1, inplace=True)\n    return df.describe().values.reshape(-1), filename.split('=')[1]\n\ndef load_time_series(dirname) -> pd.DataFrame:\n    ids = os.listdir(dirname)\n    \n    with ThreadPoolExecutor() as executor:\n        results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n    \n    stats, indexes = zip(*results)\n    \n    df = pd.DataFrame(stats, columns=[f\"stat_{i}\" for i in range(len(stats[0]))])\n    df['id'] = indexes\n    return df\n\n\nclass AutoEncoder(nn.Module):\n    def __init__(self, input_dim, encoding_dim):\n        super(AutoEncoder, self).__init__()\n        self.encoder = nn.Sequential(\n            nn.Linear(input_dim, encoding_dim*3),\n            nn.ReLU(),\n            nn.Linear(encoding_dim*3, encoding_dim*2),\n            nn.ReLU(),\n            nn.Linear(encoding_dim*2, encoding_dim),\n            nn.ReLU()\n        )\n        self.decoder = nn.Sequential(\n            nn.Linear(encoding_dim, input_dim*2),\n            nn.ReLU(),\n            nn.Linear(input_dim*2, input_dim*3),\n            nn.ReLU(),\n            nn.Linear(input_dim*3, input_dim),\n            nn.Sigmoid()\n        )\n        \n    def forward(self, x):\n        encoded = self.encoder(x)\n        decoded = self.decoder(encoded)\n        return decoded\n\n\ndef perform_autoencoder(df, encoding_dim=50, epochs=50, batch_size=32):\n    scaler = StandardScaler()\n    df_scaled = scaler.fit_transform(df)\n    \n    data_tensor = torch.FloatTensor(df_scaled)\n    \n    input_dim = data_tensor.shape[1]\n    autoencoder = AutoEncoder(input_dim, encoding_dim)\n    \n    criterion = nn.MSELoss()\n    optimizer = optim.Adam(autoencoder.parameters())\n    \n    for epoch in range(epochs):\n        for i in range(0, len(data_tensor), batch_size):\n            batch = data_tensor[i : i + batch_size]\n            optimizer.zero_grad()\n            reconstructed = autoencoder(batch)\n            loss = criterion(reconstructed, batch)\n            loss.backward()\n            optimizer.step()\n            \n        if (epoch + 1) % 10 == 0:\n            print(f'Epoch [{epoch + 1}/{epochs}], Loss: {loss.item():.4f}]')\n                 \n    with torch.no_grad():\n        encoded_data = autoencoder.encoder(data_tensor).numpy()\n        \n    df_encoded = pd.DataFrame(encoded_data, columns=[f'Enc_{i + 1}' for i in range(encoded_data.shape[1])])\n    \n    return df_encoded\n\ndef feature_engineering(df):\n    season_cols = [col for col in df.columns if 'Season' in col]\n    df = df.drop(season_cols, axis=1) \n    df['BMI_Age'] = df['Physical-BMI'] * df['Basic_Demos-Age']\n    df['Internet_Hours_Age'] = df['PreInt_EduHx-computerinternet_hoursday'] * df['Basic_Demos-Age']\n    df['BMI_Internet_Hours'] = df['Physical-BMI'] * df['PreInt_EduHx-computerinternet_hoursday']\n    df['BFP_BMI'] = df['BIA-BIA_Fat'] / df['BIA-BIA_BMI']\n    df['FFMI_BFP'] = df['BIA-BIA_FFMI'] / df['BIA-BIA_Fat']\n    df['FMI_BFP'] = df['BIA-BIA_FMI'] / df['BIA-BIA_Fat']\n    df['LST_TBW'] = df['BIA-BIA_LST'] / df['BIA-BIA_TBW']\n    df['BFP_BMR'] = df['BIA-BIA_Fat'] * df['BIA-BIA_BMR']\n    df['BFP_DEE'] = df['BIA-BIA_Fat'] * df['BIA-BIA_DEE']\n    df['BMR_Weight'] = df['BIA-BIA_BMR'] / df['Physical-Weight']\n    df['DEE_Weight'] = df['BIA-BIA_DEE'] / df['Physical-Weight']\n    df['SMM_Height'] = df['BIA-BIA_SMM'] / df['Physical-Height']\n    df['Muscle_to_Fat'] = df['BIA-BIA_SMM'] / df['BIA-BIA_FMI']\n    df['Hydration_Status'] = df['BIA-BIA_TBW'] / df['Physical-Weight']\n    df['ICW_TBW'] = df['BIA-BIA_ICW'] / df['BIA-BIA_TBW']\n    df['BMI_PHR'] = df['Physical-BMI'] * df['Physical-HeartRate']  \n    return df","metadata":{"papermill":{"duration":0.037195,"end_time":"2024-12-12T20:17:21.271465","exception":false,"start_time":"2024-12-12T20:17:21.23427","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:05:06.275721Z","iopub.execute_input":"2025-01-22T10:05:06.276093Z","iopub.status.idle":"2025-01-22T10:05:06.297390Z","shell.execute_reply.started":"2025-01-22T10:05:06.276059Z","shell.execute_reply":"2025-01-22T10:05:06.296131Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\ndf_train = train_ts.drop('id', axis=1)\ndf_test = test_ts.drop('id', axis=1)\n\ntrain_ts_encoded = perform_autoencoder(df_train, encoding_dim=60, epochs=100, batch_size=32)\ntest_ts_encoded = perform_autoencoder(df_test, encoding_dim=60, epochs=100, batch_size=32)\n\ntime_series_cols = train_ts_encoded.columns.tolist()\ntrain_ts_encoded[\"id\"]=train_ts[\"id\"]\ntest_ts_encoded['id']=test_ts[\"id\"]\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')\ntest = pd.merge(test, test_ts_encoded, how=\"left\", on='id')\n\nimputer = KNNImputer(n_neighbors=5)\nnumeric_cols = train.select_dtypes(include=['float64', 'int64']).columns\nimputed_data = imputer.fit_transform(train[numeric_cols])\ntrain_imputed = pd.DataFrame(imputed_data, columns=numeric_cols)\ntrain_imputed['sii'] = train_imputed['sii'].round().astype(int)\nfor col in train.columns:\n    if col not in numeric_cols:\n        train_imputed[col] = train[col]\n        \ntrain = train_imputed\n\ntrain = feature_engineering(train)\ntrain = train.dropna(thresh=10, axis=0)\ntest = feature_engineering(test)\n\ntrain = train.drop('id', axis=1)\ntest  = test .drop('id', axis=1)   \n\n\nfeaturesCols = ['Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-CGAS_Score', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday', 'sii', 'BMI_Age','Internet_Hours_Age','BMI_Internet_Hours',\n                'BFP_BMI', 'FFMI_BFP', 'FMI_BFP', 'LST_TBW', 'BFP_BMR', 'BFP_DEE', 'BMR_Weight', 'DEE_Weight',\n                'SMM_Height', 'Muscle_to_Fat', 'Hydration_Status', 'ICW_TBW','BMI_PHR']\n\nfeaturesCols += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n\nfeaturesCols = ['Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-CGAS_Score', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday', 'BMI_Age','Internet_Hours_Age','BMI_Internet_Hours',\n                'BFP_BMI', 'FFMI_BFP', 'FMI_BFP', 'LST_TBW', 'BFP_BMR', 'BFP_DEE', 'BMR_Weight', 'DEE_Weight',\n                'SMM_Height', 'Muscle_to_Fat', 'Hydration_Status', 'ICW_TBW','BMI_PHR']\n\nfeaturesCols += time_series_cols\ntest = test[featuresCols]","metadata":{"papermill":{"duration":86.896067,"end_time":"2024-12-12T20:18:48.188603","exception":false,"start_time":"2024-12-12T20:17:21.292536","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:05:06.299322Z","iopub.execute_input":"2025-01-22T10:05:06.300243Z","iopub.status.idle":"2025-01-22T10:07:18.024367Z","shell.execute_reply.started":"2025-01-22T10:05:06.300201Z","shell.execute_reply":"2025-01-22T10:07:18.022932Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"if np.any(np.isinf(train)):\n    train = train.replace([np.inf, -np.inf], np.nan)\n\ndef quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\ndef threshold_Rounder(oof_non_rounded, thresholds):\n    return np.where(oof_non_rounded < thresholds[0], 0,\n                    np.where(oof_non_rounded < thresholds[1], 1,\n                             np.where(oof_non_rounded < thresholds[2], 2, 3)))\n\ndef evaluate_predictions(thresholds, y_true, oof_non_rounded):\n    rounded_p = threshold_Rounder(oof_non_rounded, thresholds)\n    return -quadratic_weighted_kappa(y_true, rounded_p)","metadata":{"papermill":{"duration":0.048881,"end_time":"2024-12-12T20:18:48.276056","exception":false,"start_time":"2024-12-12T20:18:48.227175","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.026322Z","iopub.execute_input":"2025-01-22T10:07:18.027093Z","iopub.status.idle":"2025-01-22T10:07:18.043214Z","shell.execute_reply.started":"2025-01-22T10:07:18.027048Z","shell.execute_reply":"2025-01-22T10:07:18.041671Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"feature_col = train.drop(['sii'], axis=1).columns\nall_importances = pd.DataFrame({'feature': feature_col})","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.045028Z","iopub.execute_input":"2025-01-22T10:07:18.045431Z","iopub.status.idle":"2025-01-22T10:07:18.054048Z","shell.execute_reply.started":"2025-01-22T10:07:18.045395Z","shell.execute_reply":"2025-01-22T10:07:18.052705Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def TrainML(model_class, test_data):\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n    \n    train_S = []\n    test_S = []\n    \n    oof_non_rounded = np.zeros(len(y), dtype=float) \n    oof_rounded = np.zeros(len(y), dtype=int) \n    test_preds = np.zeros((len(test_data), n_splits))\n    feature_names = X.columns\n\n    lgb_importances_list = []\n    xgb_importances_list = []\n    cat_importances_list = []\n    tabnet_importances_list = []\n\n    for fold, (train_idx, test_idx) in enumerate(tqdm(SKF.split(X, y), desc=\"Training Folds\", total=n_splits)):\n        X_train, X_val = X.iloc[train_idx], X.iloc[test_idx]\n        y_train, y_val = y.iloc[train_idx], y.iloc[test_idx]\n\n        model = clone(model_class)\n        model.fit(X_train, y_train)\n\n        y_train_pred = model.predict(X_train)\n        y_val_pred = model.predict(X_val)\n\n        oof_non_rounded[test_idx] = y_val_pred\n        y_val_pred_rounded = y_val_pred.round(0).astype(int)\n        oof_rounded[test_idx] = y_val_pred_rounded\n\n        train_kappa = quadratic_weighted_kappa(y_train, y_train_pred.round(0).astype(int))\n        val_kappa = quadratic_weighted_kappa(y_val, y_val_pred_rounded)\n\n        train_S.append(train_kappa)\n        test_S.append(val_kappa)\n        \n        test_preds[:, fold] = model.predict(test_data)\n        \n        print(f\"Fold {fold+1} - Train QWK: {train_kappa:.4f}, Validation QWK: {val_kappa:.4f}\")\n        clear_output(wait=True)\n        named_estimators = model.named_estimators_\n        \n        # LightGBM\n        if 'lightgbm' in named_estimators and hasattr(named_estimators['lightgbm'], 'feature_importances_'):\n            lgb_importances_list.append(named_estimators['lightgbm'].feature_importances_)\n\n        # XGBoost\n        if 'xgboost' in named_estimators and hasattr(named_estimators['xgboost'], 'feature_importances_'):\n            xgb_importances_list.append(named_estimators['xgboost'].feature_importances_)\n\n        # CatBoost\n        if 'catboost' in named_estimators and hasattr(named_estimators['catboost'], 'get_feature_importance'):\n            cat_importances_list.append(named_estimators['catboost'].get_feature_importance())\n\n        # TabNet\n        if 'tabnet' in named_estimators and hasattr(named_estimators['tabnet'], 'feature_importances_'):\n            tabnet_importances_list.append(named_estimators['tabnet'].feature_importances_)\n\n\n    print(f\"Mean Train QWK --> {np.mean(train_S):.4f}\")\n    print(f\"Mean Validation QWK ---> {np.mean(test_S):.4f}\")\n\n    KappaOPtimizer = minimize(evaluate_predictions,\n                              x0=[0.5, 1.5, 2.5], args=(y, oof_non_rounded), \n                              method='Nelder-Mead')\n    assert KappaOPtimizer.success, \"Optimization did not converge.\"\n    \n    oof_tuned = threshold_Rounder(oof_non_rounded, KappaOPtimizer.x)\n    tKappa = quadratic_weighted_kappa(y, oof_tuned)\n\n    print(f\"----> || Optimized QWK SCORE :: {Fore.CYAN}{Style.BRIGHT} {tKappa:.3f}{Style.RESET_ALL}\")\n\n    tpm = test_preds.mean(axis=1)\n    tpTuned = threshold_Rounder(tpm, KappaOPtimizer.x)\n    \n    submission = pd.DataFrame({\n        'id': sample['id'],\n        'sii': tpTuned\n    })\n\n    def mean_importances(importances_list):\n        if len(importances_list) > 0:\n            return np.mean(importances_list, axis=0)\n        else:\n            return None\n\n    lgb_mean = mean_importances(lgb_importances_list)\n    xgb_mean = mean_importances(xgb_importances_list)\n    cat_mean = mean_importances(cat_importances_list)\n    tab_mean = mean_importances(tabnet_importances_list)\n\n    def normalize_importances(importance_array):\n        if importance_array is not None:\n            return importance_array / importance_array.sum()\n        else:\n            return None\n\n    lgb_mean_normalized = normalize_importances(lgb_mean)\n    xgb_mean_normalized = normalize_importances(xgb_mean)\n    cat_mean_normalized = normalize_importances(cat_mean)\n    tab_mean_normalized = normalize_importances(tab_mean)\n\n\n\n    if lgb_mean_normalized is not None:\n        lgb_df = pd.DataFrame({'feature': feature_names, 'importance': lgb_mean_normalized}).sort_values('importance', ascending=False)\n        plt.figure(figsize=(10,20))\n        plt.barh(lgb_df['feature'], lgb_df['importance'])\n        plt.gca().invert_yaxis()\n        plt.title(\"LightGBM Feature Importance\")\n        plt.show()\n        all_importances['LightGBM'] = lgb_mean_normalized\n\n    # XGBoost\n    if xgb_mean_normalized is not None:\n        xgb_df = pd.DataFrame({'feature': feature_names, 'importance': xgb_mean_normalized}).sort_values('importance', ascending=False)\n        plt.figure(figsize=(10,20))\n        plt.barh(xgb_df['feature'], xgb_df['importance'])\n        plt.gca().invert_yaxis()\n        plt.title(\"XGBoost Feature Importance\")\n        plt.show()\n        all_importances['XGBoost'] = xgb_mean_normalized\n\n    # CatBoost\n    if cat_mean_normalized is not None:\n        cat_df = pd.DataFrame({'feature': feature_names, 'importance': cat_mean_normalized}).sort_values('importance', ascending=False)\n        plt.figure(figsize=(10,20))\n        plt.barh(cat_df['feature'], cat_df['importance'])\n        plt.gca().invert_yaxis()\n        plt.title(\"CatBoost Feature Importance\")\n        plt.show()\n        all_importances['CatBoost'] = cat_mean_normalized\n\n    # TabNet\n    if tab_mean_normalized is not None:\n        tab_df = pd.DataFrame({'feature': feature_names, 'importance': tab_mean_normalized}).sort_values('importance', ascending=False)\n        plt.figure(figsize=(10,20))\n        plt.barh(tab_df['feature'], tab_df['importance'])\n        plt.gca().invert_yaxis()\n        plt.title(\"TabNet Feature Importance\")\n        plt.show()\n        all_importances['TabNet'] = tab_mean_normalized\n\n    return submission","metadata":{"papermill":{"duration":0.047855,"end_time":"2024-12-12T20:18:48.432006","exception":false,"start_time":"2024-12-12T20:18:48.384151","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.058541Z","iopub.execute_input":"2025-01-22T10:07:18.058996Z","iopub.status.idle":"2025-01-22T10:07:18.083367Z","shell.execute_reply.started":"2025-01-22T10:07:18.058948Z","shell.execute_reply":"2025-01-22T10:07:18.082080Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# LightGBM parameters\nParams = {\n    'learning_rate': 0.046,\n    'max_depth': 12,\n    'num_leaves': 478,\n    'min_data_in_leaf': 13,\n    'feature_fraction': 0.893,\n    'bagging_fraction': 0.784,\n    'bagging_freq': 4,\n    'lambda_l1': 10, \n    'lambda_l2': 0.01,\n    'device': 'cpu'\n\n}\n# XGBoost parameters\nXGB_Params = {\n    'learning_rate': 0.05,\n    'max_depth': 6,\n    'n_estimators': 200,\n    'subsample': 0.8,\n    'colsample_bytree': 0.8,\n    'reg_alpha': 1,  \n    'reg_lambda': 5,  \n    'random_state': SEED,\n    'tree_method': 'gpu_hist',\n\n}\n\n# CatBoost parameters\nCatBoost_Params = {\n    'learning_rate': 0.05,\n    'depth': 6,\n    'iterations': 200,\n    'random_seed': SEED,\n    'verbose': 0,\n    'l2_leaf_reg': 10,  # Increase this value\n    'task_type': 'GPU'\n\n}","metadata":{"papermill":{"duration":0.042924,"end_time":"2024-12-12T20:18:48.581996","exception":false,"start_time":"2024-12-12T20:18:48.539072","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.085017Z","iopub.execute_input":"2025-01-22T10:07:18.085469Z","iopub.status.idle":"2025-01-22T10:07:18.103815Z","shell.execute_reply.started":"2025-01-22T10:07:18.085420Z","shell.execute_reply":"2025-01-22T10:07:18.102136Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# TabNet\n\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.model_selection import train_test_split\nfrom pytorch_tabnet.callbacks import Callback\nimport os\nimport torch\nfrom pytorch_tabnet.callbacks import Callback\n\nclass TabNetWrapper(BaseEstimator, RegressorMixin):\n    def __init__(self, **kwargs):\n        self.model = TabNetRegressor(**kwargs)\n        self.kwargs = kwargs\n        self.imputer = SimpleImputer(strategy='median')\n        self.best_model_path = 'best_tabnet_model.pt'\n        \n    def fit(self, X, y):\n        # Handle missing values\n        X_imputed = self.imputer.fit_transform(X)\n        \n        if hasattr(y, 'values'):\n            y = y.values\n            \n        X_train, X_valid, y_train, y_valid = train_test_split(\n            X_imputed, \n            y, \n            test_size=0.2,\n            random_state=42\n        )\n        \n        # Train TabNet model\n        history = self.model.fit(\n            X_train=X_train,\n            y_train=y_train.reshape(-1, 1),\n            eval_set=[(X_valid, y_valid.reshape(-1, 1))],\n            eval_name=['valid'],\n            eval_metric=['mse'],\n            max_epochs=200,\n            patience=20,\n            batch_size=1024,\n            virtual_batch_size=128,\n            num_workers=0,\n            drop_last=False,\n            callbacks=[\n                TabNetPretrainedModelCheckpoint(\n                    filepath=self.best_model_path,\n                    monitor='valid_mse',\n                    mode='min',\n                    save_best_only=True,\n                    verbose=True\n                )\n            ]\n        )\n        \n        # Load the best model\n        if os.path.exists(self.best_model_path):\n            self.model.load_model(self.best_model_path)\n            os.remove(self.best_model_path)  # Remove temporary file\n\n        self.feature_importances_ = self.model.feature_importances_\n        \n        return self\n    \n    def predict(self, X):\n        X_imputed = self.imputer.transform(X)\n        return self.model.predict(X_imputed).flatten()\n    \n    def __deepcopy__(self, memo):\n        # Add deepcopy support for scikit-learn\n        cls = self.__class__\n        result = cls.__new__(cls)\n        memo[id(self)] = result\n        for k, v in self.__dict__.items():\n            setattr(result, k, deepcopy(v, memo))\n        return result\n\n# TabNet hyperparameters\nTabNet_Params = {\n    'n_d': 64,              \n    'n_a': 64,            \n    'n_steps': 5,       \n    'gamma': 1.5,        \n    'n_independent': 2,     \n    'n_shared': 2,         \n    'lambda_sparse': 1e-4,  \n    'optimizer_fn': torch.optim.Adam,\n    'optimizer_params': dict(lr=2e-2, weight_decay=1e-5),\n    'mask_type': 'entmax',\n    'scheduler_params': dict(mode=\"min\", patience=10, min_lr=1e-5, factor=0.5),\n    'scheduler_fn': torch.optim.lr_scheduler.ReduceLROnPlateau,\n    'verbose': 1,\n    'device_name': 'cuda' if torch.cuda.is_available() else 'cpu'\n}\n\nclass TabNetPretrainedModelCheckpoint(Callback):\n    def __init__(self, filepath, monitor='val_loss', mode='min', \n                 save_best_only=True, verbose=1):\n        super().__init__()  # Initialize parent class\n        self.filepath = filepath\n        self.monitor = monitor\n        self.mode = mode\n        self.save_best_only = save_best_only\n        self.verbose = verbose\n        self.best = float('inf') if mode == 'min' else -float('inf')\n        \n    def on_train_begin(self, logs=None):\n        self.model = self.trainer  # Use trainer itself as model\n        \n    def on_epoch_end(self, epoch, logs=None):\n        logs = logs or {}\n        current = logs.get(self.monitor)\n        if current is None:\n            return\n        \n        # Check if current metric is better than best\n        if (self.mode == 'min' and current < self.best) or \\\n           (self.mode == 'max' and current > self.best):\n            if self.verbose:\n                print(f'\\nEpoch {epoch}: {self.monitor} improved from {self.best:.4f} to {current:.4f}')\n            self.best = current\n            if self.save_best_only:\n                self.model.save_model(self.filepath)  # Save the entire model","metadata":{"papermill":{"duration":0.051218,"end_time":"2024-12-12T20:18:48.669191","exception":false,"start_time":"2024-12-12T20:18:48.617973","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.105425Z","iopub.execute_input":"2025-01-22T10:07:18.105812Z","iopub.status.idle":"2025-01-22T10:07:18.126104Z","shell.execute_reply.started":"2025-01-22T10:07:18.105768Z","shell.execute_reply":"2025-01-22T10:07:18.124889Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Create model instances\nLight = LGBMRegressor(**Params, random_state=SEED, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\nTabNet_Model = TabNetWrapper(**TabNet_Params) # New","metadata":{"papermill":{"duration":0.050985,"end_time":"2024-12-12T20:18:48.906901","exception":false,"start_time":"2024-12-12T20:18:48.855916","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.127528Z","iopub.execute_input":"2025-01-22T10:07:18.128014Z","iopub.status.idle":"2025-01-22T10:07:18.153522Z","shell.execute_reply.started":"2025-01-22T10:07:18.127960Z","shell.execute_reply":"2025-01-22T10:07:18.152286Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"imputer = SimpleImputer(strategy='median')\n\nvoting_model = VotingRegressor(estimators=[\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model),\n    ('tabnet', TabNet_Model),\n    ('rf', Pipeline(steps=[('imputer', imputer), ('regressor', RandomForestRegressor(random_state=SEED))])),\n    ('gb', Pipeline(steps=[('imputer', imputer), ('regressor', GradientBoostingRegressor(random_state=SEED))]))\n\n],weights=[6.0,4.0,4.0,4.0,4.0,4.0])\n\nSubmission1 = TrainML(voting_model, test)\n\nmelted = all_importances.melt(id_vars='feature', var_name='model', value_name='importance')\nmelted = melted.dropna().sort_values('importance', ascending=False)\n\nmean_importances = melted.groupby('feature', as_index=False)['importance'].mean()\n\nmean_importances = mean_importances.sort_values('importance', ascending=False)\n\nplt.figure(figsize=(10,20))\nsns.barplot(data=mean_importances, y='feature', x='importance', orient='h')\nplt.gca().invert_yaxis()\nplt.title(\"Average Feature Importances Across Models\")\nplt.show()\n\nSubmission1","metadata":{"papermill":{"duration":74.74773,"end_time":"2024-12-12T20:20:03.763394","exception":false,"start_time":"2024-12-12T20:18:49.015664","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-01-22T10:07:18.155001Z","iopub.execute_input":"2025-01-22T10:07:18.155363Z","iopub.status.idle":"2025-01-22T10:07:22.842262Z","shell.execute_reply.started":"2025-01-22T10:07:18.155309Z","shell.execute_reply":"2025-01-22T10:07:22.840167Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"```\n],weights=[5.0,4.0,4.0,4.0])\nMean Train QWK --> 0.7424\nMean Validation QWK ---> 0.4735\n----> || Optimized QWK SCORE ::  0.533\n\n```","metadata":{"papermill":{"duration":0.037036,"end_time":"2024-12-12T20:20:03.838467","exception":false,"start_time":"2024-12-12T20:20:03.801431","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"---\n# Ensemble models 2\n---","metadata":{"papermill":{"duration":0.036329,"end_time":"2024-12-12T20:20:03.911459","exception":false,"start_time":"2024-12-12T20:20:03.87513","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ndef process_file(filename, dirname):\n    df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n    df.drop('step', axis=1, inplace=True)\n    return df.describe().values.reshape(-1), filename.split('=')[1]\n\ndef load_time_series(dirname) -> pd.DataFrame:\n    ids = os.listdir(dirname)\n    \n    with ThreadPoolExecutor() as executor:\n        results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n    \n    stats, indexes = zip(*results)\n    \n    df = pd.DataFrame(stats, columns=[f\"stat_{i}\" for i in range(len(stats[0]))])\n    df['id'] = indexes\n    return df\n        \ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\ntime_series_cols = train_ts.columns.tolist()\ntime_series_cols.remove(\"id\")\n\ntrain = pd.merge(train, train_ts, how=\"left\", on='id')\ntest = pd.merge(test, test_ts, how=\"left\", on='id')\n\ntrain = train.drop('id', axis=1)\ntest = test.drop('id', axis=1)   \n\nfeaturesCols = ['Basic_Demos-Enroll_Season', 'Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-Season', 'CGAS-CGAS_Score', 'Physical-Season', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Season', 'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-Season', 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone', 'BIA-Season',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-Season', 'PAQ_A-PAQ_A_Total', 'PAQ_C-Season',\n                'PAQ_C-PAQ_C_Total', 'SDS-Season', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T', 'PreInt_EduHx-Season',\n                'PreInt_EduHx-computerinternet_hoursday', 'sii']\n\nfeaturesCols += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"cat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', \n          'Fitness_Endurance-Season', 'FGC-Season', 'BIA-Season', \n          'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\n\ndef update(df):\n    global cat_c\n    for c in cat_c: \n        df[c] = df[c].fillna('Missing')\n        df[c] = df[c].astype('category')\n    return df\n        \ntrain = update(train)\ntest = update(test)\n\ndef create_mapping(column, dataset):\n    unique_values = dataset[column].unique()\n    return {value: idx for idx, value in enumerate(unique_values)}\n\nfor col in cat_c:\n    mapping = create_mapping(col, train)\n    mappingTe = create_mapping(col, test)\n    \n    train[col] = train[col].replace(mapping).astype(int)\n    test[col] = test[col].replace(mappingTe).astype(int)\n\ndef quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\ndef threshold_Rounder(oof_non_rounded, thresholds):\n    return np.where(oof_non_rounded < thresholds[0], 0,\n                    np.where(oof_non_rounded < thresholds[1], 1,\n                             np.where(oof_non_rounded < thresholds[2], 2, 3)))\n\ndef evaluate_predictions(thresholds, y_true, oof_non_rounded):\n    rounded_p = threshold_Rounder(oof_non_rounded, thresholds)\n    return -quadratic_weighted_kappa(y_true, rounded_p)\n\ndef TrainML(model_class, test_data):\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n    \n    train_S = []\n    test_S = []\n    \n    oof_non_rounded = np.zeros(len(y), dtype=float) \n    oof_rounded = np.zeros(len(y), dtype=int) \n    test_preds = np.zeros((len(test_data), n_splits))\n\n    for fold, (train_idx, test_idx) in enumerate(tqdm(SKF.split(X, y), desc=\"Training Folds\", total=n_splits)):\n        X_train, X_val = X.iloc[train_idx], X.iloc[test_idx]\n        y_train, y_val = y.iloc[train_idx], y.iloc[test_idx]\n\n        model = clone(model_class)\n        model.fit(X_train, y_train)\n\n        y_train_pred = model.predict(X_train)\n        y_val_pred = model.predict(X_val)\n\n        oof_non_rounded[test_idx] = y_val_pred\n        y_val_pred_rounded = y_val_pred.round(0).astype(int)\n        oof_rounded[test_idx] = y_val_pred_rounded\n\n        train_kappa = quadratic_weighted_kappa(y_train, y_train_pred.round(0).astype(int))\n        val_kappa = quadratic_weighted_kappa(y_val, y_val_pred_rounded)\n\n        train_S.append(train_kappa)\n        test_S.append(val_kappa)\n        \n        test_preds[:, fold] = model.predict(test_data)\n        \n        print(f\"Fold {fold+1} - Train QWK: {train_kappa:.4f}, Validation QWK: {val_kappa:.4f}\")\n        clear_output(wait=True)\n\n    print(f\"Mean Train QWK --> {np.mean(train_S):.4f}\")\n    print(f\"Mean Validation QWK ---> {np.mean(test_S):.4f}\")\n\n    KappaOPtimizer = minimize(evaluate_predictions,\n                              x0=[0.5, 1.49, 2.5], args=(y, oof_non_rounded), \n                              method='Nelder-Mead')\n    assert KappaOPtimizer.success, \"Optimization did not converge.\"\n    thresholds = KappaOPtimizer.x\n    \n    oof_tuned = threshold_Rounder(oof_non_rounded, thresholds)\n    tKappa = quadratic_weighted_kappa(y, oof_tuned)\n\n    print(f\"----> || Optimized QWK SCORE :: {Fore.CYAN}{Style.BRIGHT} {tKappa:.3f}{Style.RESET_ALL}\")\n\n    fold_weights = [1.25, 1.0, 1.0, 1.0, 1.0]\n    tpm = test_preds.dot(fold_weights) / np.sum(fold_weights)\n    tpTuned = threshold_Rounder(tpm, thresholds)\n    \n    submission = pd.DataFrame({\n        'id': sample['id'],\n        'sii': tpTuned\n    })\n\n    return submission","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# LightGBM parameters \nParams = {\n    'learning_rate': 0.046,\n    'max_depth': 12,\n    'num_leaves': 478,\n    'min_data_in_leaf': 13,\n    'feature_fraction': 0.893,\n    'bagging_fraction': 0.784,\n    'bagging_freq': 4,\n    'lambda_l1': 10,  \n    'lambda_l2': 0.01  \n}\n\n\n# XGBoost parameters\nXGB_Params = {\n    'learning_rate': 0.05,\n    'max_depth': 6,\n    'n_estimators': 200,\n    'subsample': 0.8,\n    'colsample_bytree': 0.8,\n    'reg_alpha': 1,\n    'reg_lambda': 5, \n    'random_state': SEED\n}\n\n\nCatBoost_Params = {\n    'learning_rate': 0.05,\n    'depth': 6,\n    'iterations': 200,\n    'random_seed': SEED,\n    'cat_features': cat_c,\n    'verbose': 0,\n    'l2_leaf_reg': 10  # Increase this value\n}\n\nLight = LGBMRegressor(**Params, random_state=SEED, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\n\nvoting_model = VotingRegressor(estimators=[\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model)\n])\n\nSubmission2 = TrainML(voting_model, test)\n\nSubmission2","metadata":{"papermill":{"duration":125.974049,"end_time":"2024-12-12T20:22:09.922074","exception":false,"start_time":"2024-12-12T20:20:03.948025","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T03:26:59.002286Z","iopub.execute_input":"2024-12-19T03:26:59.002571Z","iopub.status.idle":"2024-12-19T03:29:02.476877Z","shell.execute_reply.started":"2024-12-19T03:26:59.002543Z","shell.execute_reply":"2024-12-19T03:29:02.475965Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"---\n# Submission 1: Verion 6 / Ensemble models 3\n---","metadata":{"papermill":{"duration":0.038492,"end_time":"2024-12-12T20:22:10.005701","exception":false,"start_time":"2024-12-12T20:22:09.967209","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\nfeaturesCols = ['Basic_Demos-Enroll_Season', 'Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-Season', 'CGAS-CGAS_Score', 'Physical-Season', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Season', 'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-Season', 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone', 'BIA-Season',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-Season', 'PAQ_A-PAQ_A_Total', 'PAQ_C-Season',\n                'PAQ_C-PAQ_C_Total', 'SDS-Season', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T', 'PreInt_EduHx-Season',\n                'PreInt_EduHx-computerinternet_hoursday', 'sii']\n\ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\ntime_series_cols = train_ts.columns.tolist()\ntime_series_cols.remove(\"id\")\n\ntrain = pd.merge(train, train_ts, how=\"left\", on='id')\ntest = pd.merge(test, test_ts, how=\"left\", on='id')\n\ntrain = train.drop('id', axis=1)\ntest = test.drop('id', axis=1)\n\nfeaturesCols += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"cat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', \n          'Fitness_Endurance-Season', 'FGC-Season', 'BIA-Season', \n          'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\n\ndef update(df):\n    global cat_c\n    for c in cat_c: \n        df[c] = df[c].fillna('Missing')\n        df[c] = df[c].astype('category')\n    return df\n\ntrain = update(train)\ntest = update(test)\n\ndef create_mapping(column, dataset):\n    unique_values = dataset[column].unique()\n    return {value: idx for idx, value in enumerate(unique_values)}\n\nfor col in cat_c:\n    mapping = create_mapping(col, train)\n    mappingTe = create_mapping(col, test)\n    \n    train[col] = train[col].replace(mapping).astype(int)\n    test[col] = test[col].replace(mappingTe).astype(int)\n\ndef quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\ndef threshold_Rounder(oof_non_rounded, thresholds):\n    return np.where(oof_non_rounded < thresholds[0], 0,\n                    np.where(oof_non_rounded < thresholds[1], 1,\n                             np.where(oof_non_rounded < thresholds[2], 2, 3)))\n\ndef evaluate_predictions(thresholds, y_true, oof_non_rounded):\n    rounded_p = threshold_Rounder(oof_non_rounded, thresholds)\n    return -quadratic_weighted_kappa(y_true, rounded_p)\n\ndef TrainML(model_class, test_data):\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n    \n    train_S = []\n    test_S = []\n    \n    oof_non_rounded = np.zeros(len(y), dtype=float) \n    oof_rounded = np.zeros(len(y), dtype=int) \n    test_preds = np.zeros((len(test_data), n_splits))\n\n    for fold, (train_idx, test_idx) in enumerate(tqdm(SKF.split(X, y), desc=\"Training Folds\", total=n_splits)):\n        X_train, X_val = X.iloc[train_idx], X.iloc[test_idx]\n        y_train, y_val = y.iloc[train_idx], y.iloc[test_idx]\n\n        model = clone(model_class)\n        model.fit(X_train, y_train)\n\n        y_train_pred = model.predict(X_train)\n        y_val_pred = model.predict(X_val)\n\n        oof_non_rounded[test_idx] = y_val_pred\n        y_val_pred_rounded = y_val_pred.round(0).astype(int)\n        oof_rounded[test_idx] = y_val_pred_rounded\n\n        train_kappa = quadratic_weighted_kappa(y_train, y_train_pred.round(0).astype(int))\n        val_kappa = quadratic_weighted_kappa(y_val, y_val_pred_rounded)\n\n        train_S.append(train_kappa)\n        test_S.append(val_kappa)\n        \n        test_preds[:, fold] = model.predict(test_data)\n        \n        print(f\"Fold {fold+1} - Train QWK: {train_kappa:.4f}, Validation QWK: {val_kappa:.4f}\")\n        clear_output(wait=True)\n\n    print(f\"Mean Train QWK --> {np.mean(train_S):.4f}\")\n    print(f\"Mean Validation QWK ---> {np.mean(test_S):.4f}\")\n\n    KappaOPtimizer = minimize(evaluate_predictions,\n                              x0=[0.5, 1.5, 2.5], args=(y, oof_non_rounded), \n                              method='Nelder-Mead')\n    assert KappaOPtimizer.success, \"Optimization did not converge.\"\n    thresholds = KappaOPtimizer.x\n    \n    oof_tuned = threshold_Rounder(oof_non_rounded, thresholds)\n    tKappa = quadratic_weighted_kappa(y, oof_tuned)\n\n    print(f\"----> || Optimized QWK SCORE :: {Fore.CYAN}{Style.BRIGHT} {tKappa:.3f}{Style.RESET_ALL}\")\n\n    tpm = test_preds.mean(axis=1)\n    tp_rounded = threshold_Rounder(tpm, thresholds)\n\n    return tp_rounded","metadata":{"papermill":{"duration":195.852934,"end_time":"2024-12-12T20:25:25.901091","exception":false,"start_time":"2024-12-12T20:22:10.048157","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T03:29:02.478468Z","iopub.execute_input":"2024-12-19T03:29:02.479015Z","iopub.status.idle":"2024-12-19T03:32:18.760136Z","shell.execute_reply.started":"2024-12-19T03:29:02.478964Z","shell.execute_reply":"2024-12-19T03:32:18.759239Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"imputer = SimpleImputer(strategy='median')\n\nensemble = VotingRegressor(estimators=[\n    ('lgb', Pipeline(steps=[('imputer', imputer), ('regressor', LGBMRegressor(random_state=SEED))])),\n    ('xgb', Pipeline(steps=[('imputer', imputer), ('regressor', XGBRegressor(random_state=SEED))])),\n    ('cat', Pipeline(steps=[('imputer', imputer), ('regressor', CatBoostRegressor(random_state=SEED, silent=True))])),\n    ('rf', Pipeline(steps=[('imputer', imputer), ('regressor', RandomForestRegressor(random_state=SEED))])),\n    ('gb', Pipeline(steps=[('imputer', imputer), ('regressor', GradientBoostingRegressor(random_state=SEED))]))\n])\n\nSubmission3 = TrainML(ensemble, test)\nSubmission3 = pd.DataFrame({\n    'id': sample['id'],\n    'sii': Submission3\n})\n\nSubmission3","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Final Ensemble","metadata":{"papermill":{"duration":0.037551,"end_time":"2024-12-12T20:25:25.97673","exception":false,"start_time":"2024-12-12T20:25:25.939179","status":"completed"},"tags":[]}},{"cell_type":"code","source":"sub1 = Submission1\nsub2 = Submission2\nsub3 = Submission3\nsub4 = Submission4\n\nsub1 = sub1.sort_values(by='id').reset_index(drop=True)\nsub2 = sub2.sort_values(by='id').reset_index(drop=True)\nsub3 = sub3.sort_values(by='id').reset_index(drop=True)\nsub4 = sub4.sort_values(by='id').reset_index(drop=True)\n\ncombined = pd.DataFrame({\n    'id': sub1['id'],\n    'sii_1': sub1['sii'],\n    'sii_2': sub2['sii'],\n    'sii_3': sub3['sii'],\n    'sii_4': sub4['sii']\n\n})\n\ndef majority_vote(row):\n    return row.mode()[0]\ndef priority_majority_vote(row):\n    mode_values = row.mode()  # Tìm tất cả các giá trị phổ biến nhất\n    if len(mode_values) > 1:  # Nếu có nhiều giá trị phổ biến\n        return row['sii_3']  # Ưu tiên giá trị từ Sub1\n    return mode_values[0]  # Nếu chỉ có 1 mode, trả về giá trị đó\n\n\n# combined['final_sii'] = combined[['sii_1','sii_2','sii_3','sii_4']].apply(majority_vote, axis=1)\ncombined['final_sii'] = combined[['sii_1', 'sii_2', 'sii_3', 'sii_4']].apply(priority_majority_vote, axis=1)\n\nprint(\"Majority voting with priority for sub3 completed and saved to 'submission.csv'\")\n\nfinal_submission = combined[['id', 'final_sii']].rename(columns={'final_sii': 'sii'})\n# final_submission = Submission1\nfinal_submission.to_csv('submission.csv', index=False)\n\nprint(\"Majority voting completed and saved to 'Final_Submission.csv'\")","metadata":{"papermill":{"duration":0.064111,"end_time":"2024-12-12T20:25:26.078163","exception":false,"start_time":"2024-12-12T20:25:26.014052","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T03:37:32.340624Z","iopub.execute_input":"2024-12-19T03:37:32.341001Z","iopub.status.idle":"2024-12-19T03:37:32.360023Z","shell.execute_reply.started":"2024-12-19T03:37:32.340967Z","shell.execute_reply":"2024-12-19T03:37:32.35922Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"combined","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T03:37:56.383553Z","iopub.execute_input":"2024-12-19T03:37:56.384405Z","iopub.status.idle":"2024-12-19T03:37:56.393973Z","shell.execute_reply.started":"2024-12-19T03:37:56.38437Z","shell.execute_reply":"2024-12-19T03:37:56.39307Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"final_submission","metadata":{"papermill":{"duration":0.049067,"end_time":"2024-12-12T20:25:26.165082","exception":false,"start_time":"2024-12-12T20:25:26.116015","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T03:34:43.463059Z","iopub.execute_input":"2024-12-19T03:34:43.463712Z","iopub.status.idle":"2024-12-19T03:34:43.472106Z","shell.execute_reply.started":"2024-12-19T03:34:43.463681Z","shell.execute_reply":"2024-12-19T03:34:43.471196Z"}},"outputs":[],"execution_count":null}]}