{"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":30805,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"pip install xgboost lightgbm catboost scikit-learn\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:40:03.182770Z","iopub.execute_input":"2025-01-23T04:40:03.183073Z","iopub.status.idle":"2025-01-23T04:40:46.932058Z","shell.execute_reply.started":"2025-01-23T04:40:03.183041Z","shell.execute_reply":"2025-01-23T04:40:46.930869Z"}},"outputs":[],"execution_count":null},{"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":"2025-01-23T04:40:46.933827Z","iopub.execute_input":"2025-01-23T04:40:46.934289Z","iopub.status.idle":"2025-01-23T04:41:28.767737Z","shell.execute_reply.started":"2025-01-23T04:40:46.934241Z","shell.execute_reply":"2025-01-23T04:41:28.766015Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from pytorch_tabnet.tab_model import TabNetRegressor\nimport torch","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:41:28.770474Z","iopub.execute_input":"2025-01-23T04:41:28.770845Z","iopub.status.idle":"2025-01-23T04:41:34.416765Z","shell.execute_reply.started":"2025-01-23T04:41:28.770811Z","shell.execute_reply":"2025-01-23T04:41:34.415937Z"}},"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.model_selection import train_test_split\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\nfrom sklearn.preprocessing import OneHotEncoder\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:41:34.421177Z","iopub.execute_input":"2025-01-23T04:41:34.421470Z","iopub.status.idle":"2025-01-23T04:41:53.725239Z","shell.execute_reply.started":"2025-01-23T04:41:34.421440Z","shell.execute_reply":"2025-01-23T04:41:53.724383Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Loading data","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_submission = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:41:53.726538Z","iopub.execute_input":"2025-01-23T04:41:53.727519Z","iopub.status.idle":"2025-01-23T04:41:53.814730Z","shell.execute_reply.started":"2025-01-23T04:41:53.727472Z","shell.execute_reply":"2025-01-23T04:41:53.813944Z"}},"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\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":"2025-01-23T04:41:53.816165Z","iopub.execute_input":"2025-01-23T04:41:53.816528Z","iopub.status.idle":"2025-01-23T04:43:24.583016Z","shell.execute_reply.started":"2025-01-23T04:41:53.816495Z","shell.execute_reply":"2025-01-23T04:43:24.581835Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Data preprocessing","metadata":{}},{"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\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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:24.584656Z","iopub.execute_input":"2025-01-23T04:43:24.585109Z","iopub.status.idle":"2025-01-23T04:43:24.598947Z","shell.execute_reply.started":"2025-01-23T04:43:24.585064Z","shell.execute_reply":"2025-01-23T04:43:24.597812Z"}},"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\"]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:24.603406Z","iopub.execute_input":"2025-01-23T04:43:24.603717Z","iopub.status.idle":"2025-01-23T04:43:38.523094Z","shell.execute_reply.started":"2025-01-23T04:43:24.603687Z","shell.execute_reply":"2025-01-23T04:43:38.521936Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# time_series_cols = train_ts.columns.tolist()\n# time_series_cols.remove(\"id\")\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":"2025-01-23T04:43:38.524517Z","iopub.execute_input":"2025-01-23T04:43:38.525572Z","iopub.status.idle":"2025-01-23T04:43:38.553751Z","shell.execute_reply.started":"2025-01-23T04:43:38.525523Z","shell.execute_reply":"2025-01-23T04:43:38.552602Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"PCIATCols = [col for col in train.columns if 'PCIAT' in col]\ntrain = train.drop(columns=PCIATCols)\n# test = test.dopr(columns = PCIATCols)\n\n# imputer = SimpleImputer(strategy='mean')\nimputer = KNNImputer(n_neighbors=5)\nnumeric_cols = train.select_dtypes(include=['float64', 'float32','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)\n\nseasonCols = [col for col in test.columns if 'Season' in col]\n\ndef update(df):\n    global seasonCols\n    for c in seasonCols: \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 seasonCols:\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\n\nfor col in train.columns:\n    if col in numeric_cols:\n        train[col] = train_imputed[col]\n        \n# train = train_imputed\n\ntrain = train.dropna(subset='sii')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:38.555479Z","iopub.execute_input":"2025-01-23T04:43:38.555930Z","iopub.status.idle":"2025-01-23T04:43:51.358091Z","shell.execute_reply.started":"2025-01-23T04:43:38.555864Z","shell.execute_reply":"2025-01-23T04:43:51.356917Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"imputer = KNNImputer(n_neighbors=5)\nnumeric_cols = test.select_dtypes(include=['float64', 'float32','int64']).columns\nimputed_data = imputer.fit_transform(test[numeric_cols])\ntest_imputed = pd.DataFrame(imputed_data, columns=numeric_cols)\n# test_imputed['sii'] = test_imputed['sii'].round().astype(int)\n\nfor col in train.columns:\n    if col in numeric_cols:\n        test[col] = test_imputed[col]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.359332Z","iopub.execute_input":"2025-01-23T04:43:51.359640Z","iopub.status.idle":"2025-01-23T04:43:51.430797Z","shell.execute_reply.started":"2025-01-23T04:43:51.359611Z","shell.execute_reply":"2025-01-23T04:43:51.429619Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.head","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.432220Z","iopub.execute_input":"2025-01-23T04:43:51.432596Z","iopub.status.idle":"2025-01-23T04:43:51.500399Z","shell.execute_reply.started":"2025-01-23T04:43:51.432562Z","shell.execute_reply":"2025-01-23T04:43:51.499276Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = train.drop('id', axis=1)\ntest  = test.drop('id', axis=1) ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.501548Z","iopub.execute_input":"2025-01-23T04:43:51.501867Z","iopub.status.idle":"2025-01-23T04:43:51.513503Z","shell.execute_reply.started":"2025-01-23T04:43:51.501835Z","shell.execute_reply":"2025-01-23T04:43:51.512663Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Feature engineering","metadata":{}},{"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    \n    return df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.514831Z","iopub.execute_input":"2025-01-23T04:43:51.515185Z","iopub.status.idle":"2025-01-23T04:43:51.530182Z","shell.execute_reply.started":"2025-01-23T04:43:51.515154Z","shell.execute_reply":"2025-01-23T04:43:51.529137Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = feature_engineering(train)\ntest = feature_engineering(test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.531537Z","iopub.execute_input":"2025-01-23T04:43:51.531961Z","iopub.status.idle":"2025-01-23T04:43:51.562943Z","shell.execute_reply.started":"2025-01-23T04:43:51.531912Z","shell.execute_reply":"2025-01-23T04:43:51.561862Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = train.dropna(thresh=10, axis=0)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.564239Z","iopub.execute_input":"2025-01-23T04:43:51.564588Z","iopub.status.idle":"2025-01-23T04:43:51.578096Z","shell.execute_reply.started":"2025-01-23T04:43:51.564557Z","shell.execute_reply":"2025-01-23T04:43:51.576969Z"}},"outputs":[],"execution_count":null},{"cell_type":"raw","source":"","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"correlation_with_label = train.corr()['sii']\ncorr_threshold = 0.2\nhigh_corr_columns = correlation_with_label[abs(correlation_with_label) >= corr_threshold].index\nprint(\"Columns with high correlation:\")\nhigh_corr_name = []\nfor col_name in high_corr_columns:\n    print(col_name)\n    if 'PCIAT' not in col_name:\n        high_corr_name.append(col_name)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.579334Z","iopub.execute_input":"2025-01-23T04:43:51.579732Z","iopub.status.idle":"2025-01-23T04:43:51.781014Z","shell.execute_reply.started":"2025-01-23T04:43:51.579701Z","shell.execute_reply":"2025-01-23T04:43:51.779793Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"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},{"cell_type":"code","source":"high_corr_name += time_series_cols + seasonCols","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.782469Z","iopub.execute_input":"2025-01-23T04:43:51.782809Z","iopub.status.idle":"2025-01-23T04:43:51.787476Z","shell.execute_reply.started":"2025-01-23T04:43:51.782777Z","shell.execute_reply":"2025-01-23T04:43:51.786431Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = train[high_corr_name]\ntrain = train.dropna(subset='sii')\ncommon_columns = train.columns.intersection(test.columns)\ntest = test[common_columns]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.788827Z","iopub.execute_input":"2025-01-23T04:43:51.789261Z","iopub.status.idle":"2025-01-23T04:43:51.809530Z","shell.execute_reply.started":"2025-01-23T04:43:51.789211Z","shell.execute_reply":"2025-01-23T04:43:51.808615Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.810981Z","iopub.execute_input":"2025-01-23T04:43:51.811339Z","iopub.status.idle":"2025-01-23T04:43:51.818023Z","shell.execute_reply.started":"2025-01-23T04:43:51.811304Z","shell.execute_reply":"2025-01-23T04:43:51.816955Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.819520Z","iopub.execute_input":"2025-01-23T04:43:51.819938Z","iopub.status.idle":"2025-01-23T04:43:51.833444Z","shell.execute_reply.started":"2025-01-23T04:43:51.819861Z","shell.execute_reply":"2025-01-23T04:43:51.832403Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.834506Z","iopub.execute_input":"2025-01-23T04:43:51.834814Z","iopub.status.idle":"2025-01-23T04:43:51.933421Z","shell.execute_reply.started":"2025-01-23T04:43:51.834784Z","shell.execute_reply":"2025-01-23T04:43:51.932299Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:51.934725Z","iopub.execute_input":"2025-01-23T04:43:51.935061Z","iopub.status.idle":"2025-01-23T04:43:52.067200Z","shell.execute_reply.started":"2025-01-23T04:43:51.935030Z","shell.execute_reply":"2025-01-23T04:43:52.065848Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# duplicate_columns = train.columns[train.columns.duplicated()].tolist()\n# print(\"Duplicate columns:\", duplicate_columns)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.068626Z","iopub.execute_input":"2025-01-23T04:43:52.068973Z","iopub.status.idle":"2025-01-23T04:43:52.073598Z","shell.execute_reply.started":"2025-01-23T04:43:52.068935Z","shell.execute_reply":"2025-01-23T04:43:52.072508Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = train.loc[:, ~train.columns.duplicated()]\ntest = test.loc[:, ~test.columns.duplicated()]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.074825Z","iopub.execute_input":"2025-01-23T04:43:52.075168Z","iopub.status.idle":"2025-01-23T04:43:52.091531Z","shell.execute_reply.started":"2025-01-23T04:43:52.075137Z","shell.execute_reply":"2025-01-23T04:43:52.090457Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.097274Z","iopub.execute_input":"2025-01-23T04:43:52.097613Z","iopub.status.idle":"2025-01-23T04:43:52.226682Z","shell.execute_reply.started":"2025-01-23T04:43:52.097582Z","shell.execute_reply":"2025-01-23T04:43:52.225559Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Metric","metadata":{}},{"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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.227840Z","iopub.execute_input":"2025-01-23T04:43:52.228182Z","iopub.status.idle":"2025-01-23T04:43:52.234256Z","shell.execute_reply.started":"2025-01-23T04:43:52.228151Z","shell.execute_reply":"2025-01-23T04:43:52.233097Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"code","source":"def TrainML_TrainTestSplit(model_class, test_data, test_size=0.2, random_state=42):\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n    \n    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=test_size, random_state=random_state, stratify=y)\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    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.round(0).astype(int))\n\n    print(f\"Train QWK: {train_kappa:.4f}\")\n    print(f\"Validation QWK: {val_kappa:.4f}\")\n\n    test_preds = model.predict(test_data)\n\n    oof_non_rounded = y_val_pred\n    KappaOptimizer = minimize(evaluate_predictions,\n                              x0=[0.5, 1.5, 2.5], args=(y_val, 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_val, oof_tuned)\n    print(f\"----> || Optimized QWK SCORE :: {tKappa:.3f}\")\n\n    test_preds_tuned = threshold_Rounder(test_preds, KappaOptimizer.x)\n    \n    submission = pd.DataFrame({\n        'id': sample_submission['id'],\n        'sii': test_preds_tuned\n    })\n\n    return submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.235658Z","iopub.execute_input":"2025-01-23T04:43:52.236035Z","iopub.status.idle":"2025-01-23T04:43:52.247146Z","shell.execute_reply.started":"2025-01-23T04:43:52.235985Z","shell.execute_reply":"2025-01-23T04:43:52.246060Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"n_splits = 5\ndef TrainML_StratifiedKFold(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=42)\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    \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_submission['id'],\n        'sii': tpTuned\n    })\n\n    return submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.248470Z","iopub.execute_input":"2025-01-23T04:43:52.248770Z","iopub.status.idle":"2025-01-23T04:43:52.264577Z","shell.execute_reply.started":"2025-01-23T04:43:52.248741Z","shell.execute_reply":"2025-01-23T04:43:52.263504Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Hyperparameter Tuning","metadata":{}},{"cell_type":"code","source":"# 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    'device': 'gpu'\n\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': 42,\n    'tree_method': 'gpu_hist',\n\n}\n\n\nCatBoost_Params = {\n    'learning_rate': 0.05,\n    'depth': 6,\n    'iterations': 200,\n    'random_seed': 42,\n    'verbose': 0,\n    'l2_leaf_reg': 10,  # Increase this value\n    'task_type': 'GPU'\n\n}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.265820Z","iopub.execute_input":"2025-01-23T04:43:52.266195Z","iopub.status.idle":"2025-01-23T04:43:52.281549Z","shell.execute_reply.started":"2025-01-23T04:43:52.266164Z","shell.execute_reply":"2025-01-23T04:43:52.280577Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from 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        # Create internal validation set\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=500,\n            patience=50,\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        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,              # 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', \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":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.282911Z","iopub.execute_input":"2025-01-23T04:43:52.283238Z","iopub.status.idle":"2025-01-23T04:43:52.307807Z","shell.execute_reply.started":"2025-01-23T04:43:52.283208Z","shell.execute_reply":"2025-01-23T04:43:52.306907Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Ensemble","metadata":{}},{"cell_type":"markdown","source":"## Submission 1","metadata":{}},{"cell_type":"code","source":"Light = LGBMRegressor(**Params, random_state=42, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\nTabNet_Model = TabNetWrapper(**TabNet_Params)\nGB = GradientBoostingRegressor(random_state=42)\nRF = RandomForestRegressor(random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.309198Z","iopub.execute_input":"2025-01-23T04:43:52.309632Z","iopub.status.idle":"2025-01-23T04:43:52.341839Z","shell.execute_reply.started":"2025-01-23T04:43:52.309586Z","shell.execute_reply":"2025-01-23T04:43:52.340936Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"voting_model = VotingRegressor(estimators=[\n    ('rf', RF),\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model),\n    ('tabnet', TabNet_Model),\n    ('gb', GB)\n])\n\n# Submission1 = TrainML_TrainTestSplit(voting_model, test)\nSubmission1 = TrainML_StratifiedKFold(voting_model, test)\n\nSubmission1\n# Submission1.to_csv('submission.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:43:52.343042Z","iopub.execute_input":"2025-01-23T04:43:52.343378Z","iopub.status.idle":"2025-01-23T04:48:49.252647Z","shell.execute_reply.started":"2025-01-23T04:43:52.343346Z","shell.execute_reply":"2025-01-23T04:48:49.250946Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Submission 2","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_submission = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')\ntest = pd.merge(test, test_ts_encoded, how=\"left\", on='id')\n\nPCIATCols = [col for col in train.columns if 'PCIAT' in col]\ntrain = train.drop(columns=PCIATCols)\n\n# imputer = KNNImputer(n_neighbors=5)\n# numeric_cols = train.select_dtypes(include=['float64', 'float32','int64']).columns\n# imputed_data = imputer.fit_transform(train[numeric_cols])\n# train_imputed = pd.DataFrame(imputed_data, columns=numeric_cols)\n# train_imputed['sii'] = train_imputed['sii'].round().astype(int)\n\nseasonCols = [col for col in test.columns if 'Season' in col]\n\ndef update(df):\n    global seasonCols\n    for c in seasonCols: \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 seasonCols:\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\n\n# for col in train.columns:\n#     if col in numeric_cols:\n#         train[col] = train_imputed[col]\n        \n# train = train_imputed\n\ntrain = train.dropna(subset='sii')\n\n# imputer = KNNImputer(n_neighbors=5)\n# numeric_cols = test.select_dtypes(include=['float64', 'float32','int64']).columns\n# imputed_data = imputer.fit_transform(test[numeric_cols])\n# test_imputed = pd.DataFrame(imputed_data, columns=numeric_cols)\n# test_imputed['sii'] = test_imputed['sii'].round().astype(int)\n\n# for col in train.columns:\n#     if col in numeric_cols:\n#         test[col] = test_imputed[col]\n\ntrain = train.drop('id', axis=1)\ntest  = test.drop('id', axis=1) ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:48:49.254683Z","iopub.execute_input":"2025-01-23T04:48:49.255435Z","iopub.status.idle":"2025-01-23T04:48:49.382710Z","shell.execute_reply.started":"2025-01-23T04:48:49.255381Z","shell.execute_reply":"2025-01-23T04:48:49.381833Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = feature_engineering(train)\ntest = feature_engineering(test)\n\ntrain = train.dropna(thresh=10, axis=0)\n\ncorrelation_with_label = train.corr()['sii']\ncorr_threshold = 0.2\nhigh_corr_columns = correlation_with_label[abs(correlation_with_label) >= corr_threshold].index\nprint(\"Columns with high correlation:\")\nhigh_corr_name = []\nfor col_name in high_corr_columns:\n    print(col_name)\n    if 'PCIAT' not in col_name:\n        high_corr_name.append(col_name)\n\n# time_series_col_before = train_ts.columns.tolist()\n# time_series_col_before.remove('id')\n# high_corr_name += time_series_col_before + seasonCols\nhigh_corr_name += time_series_cols + seasonCols\n\ntrain = train[high_corr_name]\ntrain = train.dropna(subset='sii')\ncommon_columns = train.columns.intersection(test.columns)\ntest = test[common_columns]\n\ntrain = train.loc[:, ~train.columns.duplicated()]\ntest = test.loc[:, ~test.columns.duplicated()]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:48:49.384038Z","iopub.execute_input":"2025-01-23T04:48:49.384404Z","iopub.status.idle":"2025-01-23T04:48:49.522756Z","shell.execute_reply.started":"2025-01-23T04:48:49.384370Z","shell.execute_reply":"2025-01-23T04:48:49.521645Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Light = LGBMRegressor(**Params, random_state=42, verbose=-1, n_estimators=300)\n# XGB_Model = XGBRegressor(**XGB_Params)\n# CatBoost_Model = CatBoostRegressor(**CatBoost_Params)\n# TabNet_Model = TabNetWrapper(**TabNet_Params)\n# GB = GradientBoostingRegressor(random_state=42)\n# RF = RandomForestRegressor(random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:48:49.524130Z","iopub.execute_input":"2025-01-23T04:48:49.524469Z","iopub.status.idle":"2025-01-23T04:48:49.529220Z","shell.execute_reply.started":"2025-01-23T04:48:49.524436Z","shell.execute_reply":"2025-01-23T04:48:49.527984Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"imputer = SimpleImputer(strategy='median')\n\nvoting_model = VotingRegressor(estimators=[\n    ('lgb', Pipeline(steps=[('imputer', imputer), ('regressor', LGBMRegressor(random_state=42))])),\n    ('xgb', Pipeline(steps=[('imputer', imputer), ('regressor', XGBRegressor(random_state=42))])),\n    ('cat', Pipeline(steps=[('imputer', imputer), ('regressor', CatBoostRegressor(random_state=42, silent=True))])),\n    ('rf', Pipeline(steps=[('imputer', imputer), ('regressor', RandomForestRegressor(random_state=42))])),\n    ('gb', Pipeline(steps=[('imputer', imputer), ('regressor', GradientBoostingRegressor(random_state=42))])),\n    ('tabnet', Pipeline(steps=[('imputer', imputer), ('regressor', TabNetWrapper(**TabNet_Params))]))\n])\n\nSubmission2 = TrainML_StratifiedKFold(voting_model, test)\n\nSubmission2\n# Submission2.to_csv('submission.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:48:49.530601Z","iopub.execute_input":"2025-01-23T04:48:49.530940Z","iopub.status.idle":"2025-01-23T04:51:59.742247Z","shell.execute_reply.started":"2025-01-23T04:48:49.530873Z","shell.execute_reply":"2025-01-23T04:51:59.741090Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Submission 3","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_submission = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')\ntest = pd.merge(test, test_ts_encoded, how=\"left\", on='id')\n\nPCIATCols = [col for col in train.columns if 'PCIAT' in col]\ntrain = train.drop(columns=PCIATCols)\n\nimputer = KNNImputer(n_neighbors=5)\nnumeric_cols = train.select_dtypes(include=['float64', 'float32','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)\n\nseasonCols = [col for col in test.columns if 'Season' in col]\n\ndef update(df):\n    global seasonCols\n    for c in seasonCols: \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 seasonCols:\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\n\nfor col in train.columns:\n    if col in numeric_cols:\n        train[col] = train_imputed[col]\n        \n# train = train_imputed\n\ntrain = train.dropna(subset='sii')\n\nimputer = KNNImputer(n_neighbors=5)\nnumeric_cols = test.select_dtypes(include=['float64', 'float32','int64']).columns\nimputed_data = imputer.fit_transform(test[numeric_cols])\ntest_imputed = pd.DataFrame(imputed_data, columns=numeric_cols)\n# test_imputed['sii'] = test_imputed['sii'].round().astype(int)\n\nfor col in train.columns:\n    if col in numeric_cols:\n        test[col] = test_imputed[col]\n\ntrain = train.drop('id', axis=1)\ntest  = test.drop('id', axis=1) ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:51:59.743807Z","iopub.execute_input":"2025-01-23T04:51:59.744733Z","iopub.status.idle":"2025-01-23T04:52:12.432960Z","shell.execute_reply.started":"2025-01-23T04:51:59.744678Z","shell.execute_reply":"2025-01-23T04:52:12.432110Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = feature_engineering(train)\ntest = feature_engineering(test)\n\ntrain = train.dropna(thresh=10, axis=0)\n\ncorrelation_with_label = train.corr()['sii']\ncorr_threshold = 0.2\nhigh_corr_columns = correlation_with_label[abs(correlation_with_label) >= corr_threshold].index\nprint(\"Columns with high correlation:\")\nhigh_corr_name = []\nfor col_name in high_corr_columns:\n    print(col_name)\n    if 'PCIAT' not in col_name:\n        high_corr_name.append(col_name)\n\n# time_series_col_before = train_ts.columns.tolist()\n# time_series_col_before.remove('id')/\nhigh_corr_name += time_series_cols \n\ntrain = train[high_corr_name]\ntrain = train.dropna(subset='sii')\ncommon_columns = train.columns.intersection(test.columns)\ntest = test[common_columns]\n\ntrain = train.loc[:, ~train.columns.duplicated()]\ntest = test.loc[:, ~test.columns.duplicated()]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:52:12.434613Z","iopub.execute_input":"2025-01-23T04:52:12.435083Z","iopub.status.idle":"2025-01-23T04:52:12.666924Z","shell.execute_reply.started":"2025-01-23T04:52:12.435031Z","shell.execute_reply":"2025-01-23T04:52:12.665809Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Light = LGBMRegressor(**Params, random_state=42, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\nTabNet_Model = TabNetWrapper(**TabNet_Params)\nGB = GradientBoostingRegressor(random_state=42)\nRF = RandomForestRegressor(random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:52:12.668127Z","iopub.execute_input":"2025-01-23T04:52:12.668464Z","iopub.status.idle":"2025-01-23T04:52:12.674914Z","shell.execute_reply.started":"2025-01-23T04:52:12.668432Z","shell.execute_reply":"2025-01-23T04:52:12.673813Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"voting_model = VotingRegressor(estimators=[\n    ('lgb', LGBMRegressor(random_state=42)),\n    ('xgb', XGB_Model),\n    ('cat', CatBoost_Model),\n    ('rf', RF),\n    ('gb', GB),\n    ('tabnet', TabNet_Model) \n])\n\nSubmission3 = TrainML_StratifiedKFold(voting_model, test)\n\n# Submission2\n# Submission2.to_csv('submission.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:52:12.676138Z","iopub.execute_input":"2025-01-23T04:52:12.676541Z","iopub.status.idle":"2025-01-23T04:55:22.515961Z","shell.execute_reply.started":"2025-01-23T04:52:12.676495Z","shell.execute_reply":"2025-01-23T04:55:22.514785Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Ensemble submission","metadata":{}},{"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)\n\nprint(\"Majority voting completed and saved to 'Final_Submission.csv'\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:55:22.517781Z","iopub.execute_input":"2025-01-23T04:55:22.518597Z","iopub.status.idle":"2025-01-23T04:55:22.548501Z","shell.execute_reply.started":"2025-01-23T04:55:22.518543Z","shell.execute_reply":"2025-01-23T04:55:22.547391Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"final_submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-23T04:55:22.549762Z","iopub.execute_input":"2025-01-23T04:55:22.550153Z","iopub.status.idle":"2025-01-23T04:55:22.562181Z","shell.execute_reply.started":"2025-01-23T04:55:22.550112Z","shell.execute_reply":"2025-01-23T04:55:22.560876Z"}},"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},{"cell_type":"code","source":"","metadata":{"trusted":true},"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},{"cell_type":"code","source":"","metadata":{"trusted":true},"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},{"cell_type":"code","source":"","metadata":{"trusted":true},"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}]}