{"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":"nvidiaTeslaT4","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"},{"sourceId":7453542,"sourceType":"datasetVersion","datasetId":921302}],"dockerImageVersionId":30787,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip -q install /kaggle/input/pytorchtabnet/pytorch_tabnet-4.1.0-py3-none-any.whl","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:21:55.471597Z","iopub.execute_input":"2024-12-18T13:21:55.471943Z","iopub.status.idle":"2024-12-18T13:22:03.758730Z","shell.execute_reply.started":"2024-12-18T13:21:55.471911Z","shell.execute_reply":"2024-12-18T13:22:03.757670Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport re\nimport random\nfrom sklearn.base import clone, BaseEstimator, RegressorMixin\nfrom sklearn.metrics import cohen_kappa_score, accuracy_score, mean_squared_error\nfrom sklearn.model_selection import StratifiedKFold, train_test_split\nfrom sklearn.decomposition import PCA\nfrom sklearn.datasets import make_classification\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\nfrom pytorch_tabnet.tab_model import TabNetRegressor\nfrom pytorch_tabnet.callbacks import Callback\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\n\nSEED = 42\nn_splits = 5","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:22:03.760893Z","iopub.execute_input":"2024-12-18T13:22:03.761198Z","iopub.status.idle":"2024-12-18T13:22:03.769850Z","shell.execute_reply.started":"2024-12-18T13:22:03.761171Z","shell.execute_reply":"2024-12-18T13:22:03.768978Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def 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":"2024-12-18T13:22:03.770928Z","iopub.execute_input":"2024-12-18T13:22:03.771151Z","iopub.status.idle":"2024-12-18T13:22:03.788398Z","shell.execute_reply.started":"2024-12-18T13:22:03.771129Z","shell.execute_reply":"2024-12-18T13:22:03.787713Z"}},"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]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:22:03.790640Z","iopub.execute_input":"2024-12-18T13:22:03.791072Z","iopub.status.idle":"2024-12-18T13:22:03.799502Z","shell.execute_reply.started":"2024-12-18T13:22:03.791034Z","shell.execute_reply":"2024-12-18T13:22:03.798831Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def 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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:22:03.800413Z","iopub.execute_input":"2024-12-18T13:22:03.800664Z","iopub.status.idle":"2024-12-18T13:22:03.810655Z","shell.execute_reply.started":"2024-12-18T13:22:03.800641Z","shell.execute_reply":"2024-12-18T13:22:03.810000Z"}},"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":"2024-12-18T13:22:03.811696Z","iopub.execute_input":"2024-12-18T13:22:03.812019Z","iopub.status.idle":"2024-12-18T13:22:03.822690Z","shell.execute_reply.started":"2024-12-18T13:22:03.811983Z","shell.execute_reply":"2024-12-18T13:22:03.821976Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"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    \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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:22:03.823637Z","iopub.execute_input":"2024-12-18T13:22:03.823881Z","iopub.status.idle":"2024-12-18T13:22:03.834463Z","shell.execute_reply.started":"2024-12-18T13:22:03.823857Z","shell.execute_reply":"2024-12-18T13:22:03.833636Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def 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    df['SDS_InternetHours'] = df['SDS-SDS_Total_T'] * df['PreInt_EduHx-computerinternet_hoursday']\n    \n    return df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:22:03.835590Z","iopub.execute_input":"2024-12-18T13:22:03.835922Z","iopub.status.idle":"2024-12-18T13:22:03.847696Z","shell.execute_reply.started":"2024-12-18T13:22:03.835886Z","shell.execute_reply":"2024-12-18T13:22:03.847026Z"}},"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\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:22:03.848808Z","iopub.execute_input":"2024-12-18T13:22:03.849060Z","iopub.status.idle":"2024-12-18T13:23:14.128179Z","shell.execute_reply.started":"2024-12-18T13:22:03.849035Z","shell.execute_reply":"2024-12-18T13:23:14.127276Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df_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')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:14.132205Z","iopub.execute_input":"2024-12-18T13:23:14.132503Z","iopub.status.idle":"2024-12-18T13:23:24.566613Z","shell.execute_reply.started":"2024-12-18T13:23:14.132453Z","shell.execute_reply":"2024-12-18T13:23:24.565675Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:24.567737Z","iopub.execute_input":"2024-12-18T13:23:24.568009Z","iopub.status.idle":"2024-12-18T13:23:24.684082Z","shell.execute_reply.started":"2024-12-18T13:23:24.567982Z","shell.execute_reply":"2024-12-18T13:23:24.683130Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:24.685340Z","iopub.execute_input":"2024-12-18T13:23:24.685649Z","iopub.status.idle":"2024-12-18T13:23:24.820696Z","shell.execute_reply.started":"2024-12-18T13:23:24.685619Z","shell.execute_reply":"2024-12-18T13:23:24.819911Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"imputer = KNNImputer(n_neighbors=5)\nnumeric_cols = train.select_dtypes(include=['int32', 'int64', '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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:24.821872Z","iopub.execute_input":"2024-12-18T13:23:24.822172Z","iopub.status.idle":"2024-12-18T13:23:31.304766Z","shell.execute_reply.started":"2024-12-18T13:23:24.822139Z","shell.execute_reply":"2024-12-18T13:23:31.304033Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.drop('id', axis=1)\ntrain","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:31.305955Z","iopub.execute_input":"2024-12-18T13:23:31.306316Z","iopub.status.idle":"2024-12-18T13:23:31.790023Z","shell.execute_reply.started":"2024-12-18T13:23:31.306279Z","shell.execute_reply":"2024-12-18T13:23:31.789167Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pciat_columns = [col for col in train.columns if 'PCIAT' in col]\n\n# Tính tỷ lệ giá trị bằng 0 trong các cột 'PCIAT' cho mỗi hàng\nzero_proportion_pciat_train = (train[pciat_columns] == 0).mean(axis=1)\n\n# Xóa các hàng có tỷ lệ giá trị bằng 0 trong các cột 'PCIAT' vượt quá 80%\ntrain.drop(train[zero_proportion_pciat_train >= 0.8].index, axis=0, inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:31.791240Z","iopub.execute_input":"2024-12-18T13:23:31.791651Z","iopub.status.idle":"2024-12-18T13:23:31.802234Z","shell.execute_reply.started":"2024-12-18T13:23:31.791607Z","shell.execute_reply":"2024-12-18T13:23:31.801545Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:31.803199Z","iopub.execute_input":"2024-12-18T13:23:31.803449Z","iopub.status.idle":"2024-12-18T13:23:31.917629Z","shell.execute_reply.started":"2024-12-18T13:23:31.803420Z","shell.execute_reply":"2024-12-18T13:23:31.916845Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test.drop('id', axis=1, inplace=True)\ntest","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:31.918748Z","iopub.execute_input":"2024-12-18T13:23:31.919355Z","iopub.status.idle":"2024-12-18T13:23:32.055435Z","shell.execute_reply.started":"2024-12-18T13:23:31.919314Z","shell.execute_reply":"2024-12-18T13:23:32.054654Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"featuresCols = ['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', 'SDS_InternetHours']\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', 'SDS_InternetHours']\n\nfeaturesCols += time_series_cols\ntest = test[featuresCols]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.056916Z","iopub.execute_input":"2024-12-18T13:23:32.057315Z","iopub.status.idle":"2024-12-18T13:23:32.071551Z","shell.execute_reply.started":"2024-12-18T13:23:32.057279Z","shell.execute_reply":"2024-12-18T13:23:32.070632Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.072665Z","iopub.execute_input":"2024-12-18T13:23:32.072908Z","iopub.status.idle":"2024-12-18T13:23:32.164987Z","shell.execute_reply.started":"2024-12-18T13:23:32.072884Z","shell.execute_reply":"2024-12-18T13:23:32.164094Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.165961Z","iopub.execute_input":"2024-12-18T13:23:32.166200Z","iopub.status.idle":"2024-12-18T13:23:32.291099Z","shell.execute_reply.started":"2024-12-18T13:23:32.166177Z","shell.execute_reply":"2024-12-18T13:23:32.290305Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"simpleImputer = SimpleImputer(strategy='median')\n\nphysical_columns = [col for col in test.columns if 'Physical' in col]\ntest[physical_columns] = test[physical_columns].fillna(0.0)\ntest = pd.DataFrame(simpleImputer.fit_transform(test), columns=test.columns)\ntest","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.292092Z","iopub.execute_input":"2024-12-18T13:23:32.292322Z","iopub.status.idle":"2024-12-18T13:23:32.437227Z","shell.execute_reply.started":"2024-12-18T13:23:32.292298Z","shell.execute_reply":"2024-12-18T13:23:32.436486Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"if np.any(np.isinf(train)):\n    train = train.replace([np.inf, -np.inf], np.nan)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.438353Z","iopub.execute_input":"2024-12-18T13:23:32.438715Z","iopub.status.idle":"2024-12-18T13:23:32.447598Z","shell.execute_reply.started":"2024-12-18T13:23:32.438675Z","shell.execute_reply":"2024-12-18T13:23:32.446831Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def 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=[0.5373, 1.13, 2.775], args=(y, oof_non_rounded), \n                              method='Nelder-Mead')\n    assert KappaOPtimizer.success, \"Optimization did not converge.\"\n    \n    print(\"KappaOPtimizer Results:\")\n    print(KappaOPtimizer)\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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.449200Z","iopub.execute_input":"2024-12-18T13:23:32.449582Z","iopub.status.idle":"2024-12-18T13:23:32.463758Z","shell.execute_reply.started":"2024-12-18T13:23:32.449543Z","shell.execute_reply":"2024-12-18T13:23:32.462851Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class 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        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(X_imputed, y, test_size=0.2, random_state=SEED)\n\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        if os.path.exists(self.best_model_path):\n            self.model.load_model(self.best_model_path)\n            os.remove(self.best_model_path)\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        cls = self.__class__\n        result = self.__new__(cls)\n        memo[id(self)] = result\n        for k, v in self.__dict__.items():\n            setattr(result, k, deepcopy(v, memo))\n\n        return result\n\nTabNet_Params = {\n    'n_d': 64,              # Width of the decision prediction layer\n    'n_a': 64,              # Width of the attention embedding for each step\n    'n_steps': 5,           # Number of steps in the architecture\n    'gamma': 1.5,           # Coefficient for feature selection regularization\n    'n_independent': 2,     # Number of independent GLU layer in each GLU block\n    'n_shared': 2,          # Number of shared GLU layer in each GLU block\n    'lambda_sparse': 1e-4,  # Sparsity regularization\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', save_best_only=True, verbose=1):\n        super().__init__()\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\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        if (self.mode == 'min' and current < self.best) or (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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.465050Z","iopub.execute_input":"2024-12-18T13:23:32.465457Z","iopub.status.idle":"2024-12-18T13:23:32.479226Z","shell.execute_reply.started":"2024-12-18T13:23:32.465420Z","shell.execute_reply":"2024-12-18T13:23:32.478383Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Params = {\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    'device': 'cpu',\n}\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': 'gpu_hist'\n}\n\n\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\n# 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)\n#ODT_Model = ObliqueDecisionTreeRegressor(**ODT_Params)\n\n# Combine models using Voting Regressor\nvoting_model = VotingRegressor(estimators=[\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model),\n    ('tabnet', TabNet_Model),\n    #('odt', ODT_Model),\n], weights=[4.0,4.0,5.0,4.0])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.480383Z","iopub.execute_input":"2024-12-18T13:23:32.480859Z","iopub.status.idle":"2024-12-18T13:23:32.494539Z","shell.execute_reply.started":"2024-12-18T13:23:32.480832Z","shell.execute_reply":"2024-12-18T13:23:32.493922Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission1 = TrainML(voting_model, test)\n\n# Save submission\n# Submission1.to_csv('submission.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:23:32.495468Z","iopub.execute_input":"2024-12-18T13:23:32.495864Z","iopub.status.idle":"2024-12-18T13:24:51.928408Z","shell.execute_reply.started":"2024-12-18T13:23:32.495838Z","shell.execute_reply":"2024-12-18T13:24:51.927466Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:24:51.929763Z","iopub.execute_input":"2024-12-18T13:24:51.930036Z","iopub.status.idle":"2024-12-18T13:24:51.937962Z","shell.execute_reply.started":"2024-12-18T13:24:51.930010Z","shell.execute_reply":"2024-12-18T13:24:51.936959Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\nimport matplotlib.pyplot as plt\n\ndef plot_confusion_matrix(y_true, y_pred):\n    cm = confusion_matrix(y_true, y_pred)\n    cm_display = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=[0, 1, 2, 3])  # Adjust labels according to your task\n    cm_display.plot(cmap='Blues')\n    plt.title(\"Confusion Matrix\")\n    plt.show()\n\ndef plot_accuracy_curve(train_acc, val_acc):\n    epochs = range(1, len(train_acc) + 1)\n    \n    plt.plot(epochs, train_acc, label='Training Accuracy')\n    plt.plot(epochs, val_acc, label='Validation Accuracy')\n    \n    plt.title('Accuracy vs Epochs')\n    plt.xlabel('Epochs')\n    plt.ylabel('Accuracy')\n    plt.legend()\n    plt.show()\n\ndef TrainMLWithMetrics(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    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    train_acc_history = []\n    val_acc_history = []\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_acc = accuracy_score(y_train, y_train_pred.round(0).astype(int))\n        val_acc = accuracy_score(y_val, y_val_pred_rounded)\n\n        train_acc_history.append(train_acc)\n        val_acc_history.append(val_acc)\n        \n        test_preds[:, fold] = model.predict(test_data)\n        \n        print(f\"Fold {fold+1} - Train Accuracy: {train_acc:.4f}, Validation Accuracy: {val_acc:.4f}\")\n        clear_output(wait=True)\n\n    print(f\"Mean Train Accuracy --> {np.mean(train_acc_history):.4f}\")\n    print(f\"Mean Validation Accuracy --> {np.mean(val_acc_history):.4f}\")\n    \n    # Plot Accuracy curves\n    plot_accuracy_curve(train_acc_history, val_acc_history)\n    \n    # Optimize thresholds\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    print(\"KappaOPtimizer Results:\")\n    print(KappaOPtimizer)\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    # Confusion Matrix for the last fold (you can adjust to display other folds or aggregated)\n    plot_confusion_matrix(y, oof_rounded)\n\n    submission = pd.DataFrame({\n        'id': sample['id'],\n        'sii': tpTuned\n    })\n\n    return submission\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:24:51.944290Z","iopub.execute_input":"2024-12-18T13:24:51.944589Z","iopub.status.idle":"2024-12-18T13:24:51.961006Z","shell.execute_reply.started":"2024-12-18T13:24:51.944559Z","shell.execute_reply":"2024-12-18T13:24:51.960259Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"SubmissionX = TrainMLWithMetrics(voting_model, test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:24:51.961951Z","iopub.execute_input":"2024-12-18T13:24:51.962220Z","iopub.status.idle":"2024-12-18T13:26:13.109278Z","shell.execute_reply.started":"2024-12-18T13:24:51.962192Z","shell.execute_reply":"2024-12-18T13:26:13.108235Z"}},"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\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')\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\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=[0.5882, 0.9617, 2.673], args=(y, oof_non_rounded), \n                              method='Nelder-Mead')\n    assert KappaOPtimizer.success, \"Optimization did not converge.\"\n    \n    print(\"KappaOPtimizer Results:\")\n    print(KappaOPtimizer)\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\n# Model parameters for LightGBM\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\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,  # Increased from 0.1\n    'reg_lambda': 5,  # Increased from 1\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\n# 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)\n#ODT_Model = ObliqueDecisionTreeRegressor(**ODT_Params)\n\n# Combine models using Voting Regressor\nvoting_model = VotingRegressor(estimators=[\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model),\n    #('tabnet', TabNet_Model),\n    #('odt', ODT_Model),\n])\n\n# Train the ensemble model\nSubmission2 = TrainML(voting_model, test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:26:13.110639Z","iopub.execute_input":"2024-12-18T13:26:13.110916Z","iopub.status.idle":"2024-12-18T13:28:12.867421Z","shell.execute_reply.started":"2024-12-18T13:26:13.110889Z","shell.execute_reply":"2024-12-18T13:28:12.866529Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission2","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:28:12.868943Z","iopub.execute_input":"2024-12-18T13:28:12.869636Z","iopub.status.idle":"2024-12-18T13:28:12.878806Z","shell.execute_reply.started":"2024-12-18T13:28:12.869588Z","shell.execute_reply":"2024-12-18T13:28:12.877796Z"}},"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\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\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 += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\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=[0.6174, 0.9321, 2.710], args=(y, oof_non_rounded), \n                              method='Nelder-Mead')\n    assert KappaOPtimizer.success, \"Optimization did not converge.\"\n\n    print(\"KappaOPtimizer Results:\")\n    print(KappaOPtimizer)\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    tp_rounded = threshold_Rounder(tpm, KappaOPtimizer.x)\n\n    return tp_rounded\n\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    #('tabnet', Pipeline(steps=[('imputer', imputer), ('regressor', TabNetWrapper(**TabNet_Params))])),\n    #('odt',    Pipeline(steps=[('imputer', imputer), ('regressor', ObliqueDecisionTreeRegressor(**ODT_Params))])),\n])\n\nSubmission3 = TrainML(ensemble, test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:28:12.880162Z","iopub.execute_input":"2024-12-18T13:28:12.880496Z","iopub.status.idle":"2024-12-18T13:31:21.273860Z","shell.execute_reply.started":"2024-12-18T13:28:12.880453Z","shell.execute_reply":"2024-12-18T13:31:21.272990Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission3 = pd.DataFrame({\n    'id': sample['id'],\n    'sii': Submission3\n})\n\nSubmission3","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:31:21.275248Z","iopub.execute_input":"2024-12-18T13:31:21.275741Z","iopub.status.idle":"2024-12-18T13:31:21.285634Z","shell.execute_reply.started":"2024-12-18T13:31:21.275693Z","shell.execute_reply":"2024-12-18T13:31:21.284679Z"}},"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\ncombined = pd.DataFrame({\n    'id': sub1['id'],\n    'sii_1': sub1['sii'],\n    'sii_2': sub2['sii'],\n    'sii_3': sub3['sii']\n})\n\ndef majority_vote(row):\n    return row.mode()[0]\n\ncombined['final_sii'] = combined[['sii_1', 'sii_2', 'sii_3']].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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:31:21.286795Z","iopub.execute_input":"2024-12-18T13:31:21.287045Z","iopub.status.idle":"2024-12-18T13:31:21.306668Z","shell.execute_reply.started":"2024-12-18T13:31:21.287021Z","shell.execute_reply":"2024-12-18T13:31:21.305948Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"final_submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-18T13:31:21.307500Z","iopub.execute_input":"2024-12-18T13:31:21.307718Z","iopub.status.idle":"2024-12-18T13:31:21.320352Z","shell.execute_reply.started":"2024-12-18T13:31:21.307695Z","shell.execute_reply":"2024-12-18T13:31:21.319537Z"}},"outputs":[],"execution_count":null}]}