{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30804,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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\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\nfrom sklearn.pipeline import Pipeline\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None\n\nSEED = 42\nn_splits = 5","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:27:00.410543Z","iopub.execute_input":"2024-12-14T14:27:00.410953Z","iopub.status.idle":"2024-12-14T14:27:19.298509Z","shell.execute_reply.started":"2024-12-14T14:27:00.410903Z","shell.execute_reply":"2024-12-14T14:27:19.297352Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import random\nimport torch\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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:27:19.300467Z","iopub.execute_input":"2024-12-14T14:27:19.301131Z","iopub.status.idle":"2024-12-14T14:27:19.311410Z","shell.execute_reply.started":"2024-12-14T14:27:19.301097Z","shell.execute_reply":"2024-12-14T14:27:19.310393Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"featuresCols_1 = ['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\n# ---------------------------------------------------------------------------------\n\nfeaturesCols_2 = ['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\n# ---------------------------------------------------------------------------------\n\nfeaturesCols_3 = [\n    'Basic_Demos-Enroll_Season',\n    'Basic_Demos-Age', \n    'Basic_Demos-Sex',\n    \n    'CGAS-Season',\n    'CGAS-CGAS_Score',\n    \n    'Physical-Season',\n    'Physical-BMI',\n    'Physical-Height',\n    'Physical-Weight',\n    'Physical-Waist_Circumference',\n    'Physical-Diastolic_BP',\n    'Physical-HeartRate',\n    'Physical-Systolic_BP',\n    \n    'Fitness_Endurance-Season', \n    'Fitness_Endurance-Max_Stage',\n    'Fitness_Endurance-Time_Mins',\n    'Fitness_Endurance-Time_Sec',\n    \n    'FGC-Season',\n    \n    'FGC-FGC_CU', \n    'FGC-FGC_CU_Zone',\n    \n    'FGC-FGC_GSND',\n    'FGC-FGC_GSND_Zone',\n    \n    'FGC-FGC_GSD', \n    'FGC-FGC_GSD_Zone', \n    \n    'FGC-FGC_PU',\n    'FGC-FGC_PU_Zone',\n    \n    'FGC-FGC_SRL',\n    'FGC-FGC_SRL_Zone',\n    'FGC-FGC_SRR',\n    'FGC-FGC_SRR_Zone',\n    \n    'FGC-FGC_TL',\n    'FGC-FGC_TL_Zone',\n    \n    'BIA-Season',\n    'BIA-BIA_Activity_Level_num',\n    'BIA-BIA_BMC',\n    'BIA-BIA_BMI',\n    'BIA-BIA_BMR',\n    'BIA-BIA_DEE',\n    'BIA-BIA_ECW', \n    'BIA-BIA_FFM',\n    'BIA-BIA_FFMI',\n    'BIA-BIA_FMI',\n    'BIA-BIA_Fat',\n    'BIA-BIA_Frame_num',    \n    'BIA-BIA_ICW',\n    'BIA-BIA_LDM',\n    'BIA-BIA_LST',\n    'BIA-BIA_SMM',\n    'BIA-BIA_TBW',\n    \n    'PAQ_A-Season',\n    'PAQ_A-PAQ_A_Total',\n    \n    'PAQ_C-Season',\n    'PAQ_C-PAQ_C_Total',\n    \n    'SDS-Season',\n    'SDS-SDS_Total_Raw',\n    'SDS-SDS_Total_T',\n    \n    'PreInt_EduHx-Season',\n    'PreInt_EduHx-computerinternet_hoursday',\n    \n    'sii'\n]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:27:19.312765Z","iopub.execute_input":"2024-12-14T14:27:19.313194Z","iopub.status.idle":"2024-12-14T14:27:19.397986Z","shell.execute_reply.started":"2024-12-14T14:27:19.313132Z","shell.execute_reply":"2024-12-14T14:27:19.396505Z"},"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class 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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:27:19.400560Z","iopub.execute_input":"2024-12-14T14:27:19.400949Z","iopub.status.idle":"2024-12-14T14:27:19.414394Z","shell.execute_reply.started":"2024-12-14T14:27:19.400915Z","shell.execute_reply":"2024-12-14T14:27:19.413350Z"}},"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\n\ndef load_time_series(dirname) -> pd.DataFrame:\n    ids = os.listdir(dirname)\n    with ThreadPoolExecutor() as executor:\n        results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n    stats, indexes = zip(*results)\n    df = pd.DataFrame(stats, columns=[f\"stat_{i}\" for i in range(len(stats[0]))])\n    df['id'] = indexes\n    return df\n\ndef build_autoencoder(input_dim, encoding_dim):\n    input_layer = Input(shape=(input_dim,))\n    encoded = Dense(encoding_dim, activation='relu')(input_layer)\n    decoded = Dense(input_dim, activation='sigmoid')(encoded)\n    autoencoder = Model(inputs=input_layer, outputs=decoded)\n    encoder     = Model(inputs=input_layer, outputs=encoded)\n    autoencoder.compile(optimizer=Adam(), loss='mse')   \n    #legacy_h5_format.save_model_to_hdf5(autoencoder, 'autoencoder_model', overwrite, include_optimizer)\n    return autoencoder, encoder\n\n\n# def 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#     autoencoder = AutoEncoder(input_dim, encoding_dim)\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 perform_autoencoder(df, encoding_dim=50, epochs=50, batch_size=32):\n    scaler = StandardScaler()\n    df_scaled = scaler.fit_transform(df)\n    input_dim = df_scaled.shape[1]\n    autoencoder, encoder = build_autoencoder(input_dim, encoding_dim)\n    autoencoder.fit(df_scaled, df_scaled, epochs=epochs, batch_size=batch_size, shuffle=True, verbose=1)\n    encoded_data = encoder.predict(df_scaled)\n    df_encoded = pd.DataFrame(encoded_data, columns=[f'Enc_{i+1}' for i in range(encoded_data.shape[1])])\n    return df_encoded\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\ndef create_mapping(column, dataset):\n    unique_values = dataset[column].unique()\n    return {value: idx for idx, value in enumerate(unique_values)}\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        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    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    return submission\n\ncat_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']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:27:19.416181Z","iopub.execute_input":"2024-12-14T14:27:19.416540Z","iopub.status.idle":"2024-12-14T14:27:19.441659Z","shell.execute_reply.started":"2024-12-14T14:27:19.416507Z","shell.execute_reply":"2024-12-14T14:27:19.440740Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission 1 with auto encoder","metadata":{}},{"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\ndisplay(train_ts.head(5))\n\n# import keras as kr\n# import tensorflow as tf\n\n# tf.random.set_seed(SEED)\n# kr.utils.set_random_seed(SEED) \n\ntrain_ts_encoded = perform_autoencoder(df_train, encoding_dim=96, epochs=100, batch_size=32)\ntest_ts_encoded  = perform_autoencoder(df_test,  encoding_dim=96, epochs=100, batch_size=32)\n\ndisplay(train_ts_encoded.head(5))\n\ntime_series_cols = train_ts_encoded.columns.tolist()\ntrain_ts_encoded['id'] = train_ts['id']\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')\ntest  = pd.merge(test,  train_ts_encoded, 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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:27:19.443275Z","iopub.execute_input":"2024-12-14T14:27:19.444313Z","iopub.status.idle":"2024-12-14T14:28:55.585374Z","shell.execute_reply.started":"2024-12-14T14:27:19.444268Z","shell.execute_reply":"2024-12-14T14:28:55.584376Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# len(featuresCols)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:29:40.782349Z","iopub.execute_input":"2024-12-14T14:29:40.782795Z","iopub.status.idle":"2024-12-14T14:29:40.787554Z","shell.execute_reply.started":"2024-12-14T14:29:40.782760Z","shell.execute_reply":"2024-12-14T14:29:40.786410Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:29:41.368833Z","iopub.execute_input":"2024-12-14T14:29:41.369803Z","iopub.status.idle":"2024-12-14T14:29:41.373903Z","shell.execute_reply.started":"2024-12-14T14:29:41.369764Z","shell.execute_reply":"2024-12-14T14:29:41.372698Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\nfeaturesCols = featuresCols_1 + time_series_cols + list(train_ts_encoded.columns)\nfeaturesCols = sorted(list(set(featuresCols) - set(['id'])))\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\nfeaturesCols = sorted(list(set(featuresCols) - set(['sii'])))\ntest = test[featuresCols]\ncat_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']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:29:41.905789Z","iopub.execute_input":"2024-12-14T14:29:41.906294Z","iopub.status.idle":"2024-12-14T14:29:41.920687Z","shell.execute_reply.started":"2024-12-14T14:29:41.906258Z","shell.execute_reply":"2024-12-14T14:29:41.919596Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = update(train)\ntest = update(test)\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)\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,  # Increased from 6.59\n    'lambda_l2': 0.01  # Increased from 2.68e-06\n}\n\n\nXGB_Params = {\n    'learning_rate': 0.05,\n    'max_depth': 6,\n    'n_estimators': 400,\n    'subsample': 0.8,\n    'colsample_bytree': 0.8,\n    'reg_alpha': 1,  # Increased from 0.1\n    'reg_lambda': 5,  # Increased from 1\n    'random_state': SEED,\n    'tree_method': 'exact'\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}\nLight = LGBMRegressor(**Params, random_state=SEED, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\n\n# Combine models using Voting Regressor\nvoting_model = VotingRegressor(estimators=[\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model)],\n    weights=[0.3, 0.5, 0.2])\nSubmission1 = TrainML(voting_model, test)\n\nSubmission1 ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:29:42.262931Z","iopub.execute_input":"2024-12-14T14:29:42.263759Z","iopub.status.idle":"2024-12-14T14:31:04.782141Z","shell.execute_reply.started":"2024-12-14T14:29:42.263724Z","shell.execute_reply":"2024-12-14T14:31:04.781053Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission 2 with time series","metadata":{}},{"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\ncat_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\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 = featuresCols_2 + time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n        \ntrain = update(train)\ntest = update(test)\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\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,  # Increased from 6.59\n    'lambda_l2': 0.01  # Increased from 2.68e-06\n}\n\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,  # Increased from 0.1\n    'reg_lambda': 5,  # Increased from 1\n    'random_state': SEED,\n    'tree_method': 'exact'\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    weights=[0.3, 0.5, 0.2])\n\nSubmission2 = TrainML(voting_model, test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:31:04.783819Z","iopub.execute_input":"2024-12-14T14:31:04.784181Z","iopub.status.idle":"2024-12-14T14:33:22.820332Z","shell.execute_reply.started":"2024-12-14T14:31:04.784150Z","shell.execute_reply":"2024-12-14T14:33:22.818945Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission2","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:33:22.822456Z","iopub.execute_input":"2024-12-14T14:33:22.822959Z","iopub.status.idle":"2024-12-14T14:33:22.836438Z","shell.execute_reply.started":"2024-12-14T14:33:22.822910Z","shell.execute_reply":"2024-12-14T14:33:22.835146Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission 3 with imputer median","metadata":{}},{"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\ncat_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\n#train_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\n#test_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 = featuresCols_3 + time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n\ntrain = update(train)\ntest = update(test)\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)\nimputer = 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    weights=[0.15, 0.25, 0.2, 0.25, 0.15])\n\nSubmission3 = TrainML(ensemble, test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:33:22.839682Z","iopub.execute_input":"2024-12-14T14:33:22.840604Z","iopub.status.idle":"2024-12-14T14:35:45.811629Z","shell.execute_reply.started":"2024-12-14T14:33:22.840565Z","shell.execute_reply":"2024-12-14T14:35:45.810715Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission3 ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:35:45.812947Z","iopub.execute_input":"2024-12-14T14:35:45.813244Z","iopub.status.idle":"2024-12-14T14:35:45.822857Z","shell.execute_reply.started":"2024-12-14T14:35:45.813217Z","shell.execute_reply":"2024-12-14T14:35:45.821736Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sub1 = Submission1\nsub2 = Submission2\nsub3 = Submission3\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)\n\nsub1 = sub1.rename(columns={'sii': 'sii_1'})\nsub2 = sub2.rename(columns={'sii': 'sii_2'})\nsub3 = sub3.rename(columns={'sii': 'sii_3'})\nsubs = pd.merge(sub1,sub2,on=['id'])\nsubs = pd.merge(subs,sub3,on=['id'])\n\n#subs['sii_s'] = subs['sii_1'] *0.555 + 0.001* subs['sii_2'] + 0.444* subs['sii_3']\n#subs['sii_s'] = subs['sii_1'] *0.450 + 0.450* subs['sii_2'] + 0.100* subs['sii_3']\n#subs['sii_s'] = subs['sii_1'] *0.525 + 0.050* subs['sii_2'] + 0.425* subs['sii_3']\n#subs['sii_s'] = subs['sii_1'] *0.500 + 0.100* subs['sii_2'] + 0.400* subs['sii_3']\n\nsubs['sii_s'] = np.round(subs['sii_1'] *0.85 + 0.10* subs['sii_2'] + 0.05* subs['sii_3'])\n\nsubs['sii_s'] = subs['sii_s'].astype(int)\n\ncombined = pd.DataFrame({\n    \n    'id'   : sub1['id'],\n    \n    'sii_1': sub1['sii_1'],\n    'sii_2': sub2['sii_2'],\n    'sii_3': sub3['sii_3'],\n    \n    'sii_s': subs['sii_s'],\n})\n\ndisplay(combined)\n\ndef majority_vote(row):\n    return row.mode()[0]\n                                                         \ncombined['final_sii'] = combined[['sii_1', 'sii_2', 'sii_3', 'sii_s']].apply(majority_vote, axis=1)\n\nfinal_submission = combined[['id', 'final_sii']].rename(columns={'final_sii': 'sii'})\n\nfinal_submission.to_csv('submission.csv', index=False)\n\nprint(\"Majority voting completed and saved to 'Final_Submission.csv'\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:35:45.824225Z","iopub.execute_input":"2024-12-14T14:35:45.824526Z","iopub.status.idle":"2024-12-14T14:35:45.866246Z","shell.execute_reply.started":"2024-12-14T14:35:45.824496Z","shell.execute_reply":"2024-12-14T14:35:45.865324Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"final_submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-14T14:35:45.867309Z","iopub.execute_input":"2024-12-14T14:35:45.867589Z","iopub.status.idle":"2024-12-14T14:35:45.876156Z","shell.execute_reply.started":"2024-12-14T14:35:45.867563Z","shell.execute_reply":"2024-12-14T14:35:45.875163Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}