{"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":"markdown","source":"Im pọt","metadata":{}},{"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":"2024-12-21T07:30:05.337067Z","iopub.execute_input":"2024-12-21T07:30:05.337373Z","iopub.status.idle":"2024-12-21T07:30:46.348587Z","shell.execute_reply.started":"2024-12-21T07:30:05.337336Z","shell.execute_reply":"2024-12-21T07:30:46.347270Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport random\nimport warnings\nfrom concurrent.futures import ThreadPoolExecutor\n\nimport numpy as np\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\nimport matplotlib.gridspec as gridspec\nfrom matplotlib.ticker import MaxNLocator, FormatStrFormatter, PercentFormatter\nimport seaborn as sns\nimport plotly.express as px\nimport plotly\n\nfrom IPython.display import clear_output\n\nimport polars as pl\n\nfrom sklearn.model_selection import cross_val_score, StratifiedKFold, KFold\nfrom sklearn.metrics import make_scorer, cohen_kappa_score\nfrom sklearn.base import clone\nfrom sklearn.impute import SimpleImputer, KNNImputer\nfrom sklearn.ensemble import VotingRegressor, RandomForestRegressor, GradientBoostingRegressor\nfrom scipy.optimize import minimize\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.pipeline import Pipeline\n\nfrom lightgbm import LGBMRegressor\nfrom xgboost import XGBRegressor\nfrom catboost import CatBoostRegressor\n\nimport eli5\nfrom eli5.sklearn import PermutationImportance\n\nfrom imblearn.over_sampling import SMOTE\n\nfrom tqdm import tqdm\nfrom colorama import Fore, Style\n\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.nn.functional as F","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:30:46.350622Z","iopub.execute_input":"2024-12-21T07:30:46.350891Z","iopub.status.idle":"2024-12-21T07:31:04.636041Z","shell.execute_reply.started":"2024-12-21T07:30:46.350865Z","shell.execute_reply":"2024-12-21T07:31:04.635325Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv', index_col='id')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv', index_col='id')\ndata_dict = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/data_dictionary.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\nprint(\"Train data shape: \", train.shape)\nprint(\"Test data shape: \", test.shape)\nprint(\"Training data missing values: \", train.isna().sum().sum())\ndisplay(data_dict)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:04.637127Z","iopub.execute_input":"2024-12-21T07:31:04.637996Z","iopub.status.idle":"2024-12-21T07:31:04.735588Z","shell.execute_reply.started":"2024-12-21T07:31:04.637963Z","shell.execute_reply":"2024-12-21T07:31:04.734745Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(train.columns)\ndisplay(train.head().select_dtypes(exclude='number'))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:04.736676Z","iopub.execute_input":"2024-12-21T07:31:04.736949Z","iopub.status.idle":"2024-12-21T07:31:04.749754Z","shell.execute_reply.started":"2024-12-21T07:31:04.736923Z","shell.execute_reply":"2024-12-21T07:31:04.748831Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_season_cols = train.select_dtypes(exclude='number').columns\nseason_mapping = {'Spring': 1, 'Summer': 2, 'Fall': 3, 'Winter': 4}\n\nfor col in train_season_cols:\n    train[col] = train[col].apply(lambda x: season_mapping.get(x, 0))\n\ntest_season_cols = test.select_dtypes(exclude='number').columns\nfor col in test_season_cols:\n    test[col] = test[col].apply(lambda x: season_mapping.get(x, 0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:04.750820Z","iopub.execute_input":"2024-12-21T07:31:04.751085Z","iopub.status.idle":"2024-12-21T07:31:04.783137Z","shell.execute_reply.started":"2024-12-21T07:31:04.751062Z","shell.execute_reply":"2024-12-21T07:31:04.782332Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_with_sii = train[train['sii'].notna()]\nPCIAT_cols = [f'PCIAT-PCIAT_{i + 1:02d}' for i in range(20)]\n\ndef recalculate_sii(row):\n    if pd.isna(row['PCIAT-PCIAT_Total']):\n        return np.nan\n    max_possible = row['PCIAT-PCIAT_Total'] + row[PCIAT_cols].isna().sum() * 5\n    if row['PCIAT-PCIAT_Total'] <= 30 and max_possible <= 30:\n        return 0\n    elif 31 <= row['PCIAT-PCIAT_Total'] <= 49 and max_possible <= 49:\n        return 1\n    elif 50 <= row['PCIAT-PCIAT_Total'] <= 79 and max_possible <= 79:\n        return 2\n    elif row['PCIAT-PCIAT_Total'] >= 80 and max_possible >= 80:\n        return 3\n    return np.nan\n\ntrain['recalc_sii'] = train.apply(recalculate_sii, axis = 1)\n\n# sii_map = {0: '0 (None)', 1: '1 (Mild)', 2: '2 (Moderate)', 3: '3 (Severe)'}\ntrain['recalc_sii'] = train['recalc_sii'].fillna(-1)\n\n\n# sii_order = ['Missing', '0 (None)', '1 (Mild)', '2 (Moderate)', '3 (Severe)']\nsii_order = [0, 1, 2, 3]\ntrain['recalc_sii'] = pd.Categorical(train['recalc_sii'], categories=sii_order, ordered=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:04.784079Z","iopub.execute_input":"2024-12-21T07:31:04.784319Z","iopub.status.idle":"2024-12-21T07:31:06.106260Z","shell.execute_reply.started":"2024-12-21T07:31:04.784289Z","shell.execute_reply":"2024-12-21T07:31:06.105556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sii_counts = train['recalc_sii'].value_counts().reset_index()\n\nsii_counts['percentage'] = sii_counts['count'] / sii_counts['count'].sum() * 100\nfig, axes = plt.subplots(1, 2, figsize=(14,5))\n\nsns.barplot(x='recalc_sii', y='count', data=sii_counts, palette='Blues_d', ax=axes[0])\naxes[0].set_title('Distribution of Severity Impairment Index (sii)', fontsize=14)\nfor p in axes[0].patches:\n    height = p.get_height()\n    percentage = sii_counts.loc[sii_counts['count'] == height, 'percentage'].values[0]\n    axes[0].text(p.get_x() + p.get_width() / 2, height + 5, f'{percentage:.2f}%', ha='center', fontsize=12)\n\n\n\naxes[1].set_title('Distribution of PCIAT_Total', fontsize=14)\naxes[1].set_xlabel('PCIAT_Total for Complete PCIAT responses')\nsns.histplot(train['PCIAT-PCIAT_Total'], bins=20, kde=True, ax = axes[1])\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:06.108567Z","iopub.execute_input":"2024-12-21T07:31:06.108852Z","iopub.status.idle":"2024-12-21T07:31:06.737979Z","shell.execute_reply.started":"2024-12-21T07:31:06.108827Z","shell.execute_reply":"2024-12-21T07:31:06.737188Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"fig = px.scatter(train, x = 'PCIAT-PCIAT_Total', color = 'sii', marginal_x=\"box\", title = 'PCIAT Total')\nfig = fig.update_layout(yaxis_title=\"\")\nfig.update_yaxes(showticklabels=False)\nfig.show(renderer='iframe_connected')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:06.739290Z","iopub.execute_input":"2024-12-21T07:31:06.739666Z","iopub.status.idle":"2024-12-21T07:31:08.103551Z","shell.execute_reply.started":"2024-12-21T07:31:06.739627Z","shell.execute_reply":"2024-12-21T07:31:08.102736Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.104896Z","iopub.execute_input":"2024-12-21T07:31:08.105254Z","iopub.status.idle":"2024-12-21T07:31:08.112150Z","shell.execute_reply.started":"2024-12-21T07:31:08.105216Z","shell.execute_reply":"2024-12-21T07:31:08.110970Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train['sii'] = train['recalc_sii'].astype(np.number)\ntrain.drop(columns='recalc_sii', inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.113510Z","iopub.execute_input":"2024-12-21T07:31:08.114113Z","iopub.status.idle":"2024-12-21T07:31:08.129006Z","shell.execute_reply.started":"2024-12-21T07:31:08.114063Z","shell.execute_reply":"2024-12-21T07:31:08.128140Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_cols = set(train.columns)\ntest_cols = set(test.columns)\ndifcols = sorted(list(train_cols - test_cols))\ndifcols.remove('sii')\ndifcols.remove('PCIAT-PCIAT_Total')\n# difcols.remove('recalc_sii')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.130078Z","iopub.execute_input":"2024-12-21T07:31:08.130342Z","iopub.status.idle":"2024-12-21T07:31:08.135202Z","shell.execute_reply.started":"2024-12-21T07:31:08.130316Z","shell.execute_reply":"2024-12-21T07:31:08.134325Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(difcols)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.136164Z","iopub.execute_input":"2024-12-21T07:31:08.136442Z","iopub.status.idle":"2024-12-21T07:31:08.143802Z","shell.execute_reply.started":"2024-12-21T07:31:08.136415Z","shell.execute_reply":"2024-12-21T07:31:08.143055Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = train.drop(columns = difcols)\ntrain.columns\nprint(train.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.144741Z","iopub.execute_input":"2024-12-21T07:31:08.144982Z","iopub.status.idle":"2024-12-21T07:31:08.154125Z","shell.execute_reply.started":"2024-12-21T07:31:08.144958Z","shell.execute_reply":"2024-12-21T07:31:08.153356Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = train.dropna(subset='sii')\ncorr = pd.DataFrame(train.corr()['PCIAT-PCIAT_Total'].sort_values(ascending = False))\ncorr","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.155106Z","iopub.execute_input":"2024-12-21T07:31:08.155358Z","iopub.status.idle":"2024-12-21T07:31:08.190796Z","shell.execute_reply.started":"2024-12-21T07:31:08.155335Z","shell.execute_reply":"2024-12-21T07:31:08.190042Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# selected_features = corr[(corr['PCIAT-PCIAT_Total'] > 0.05) | (corr['PCIAT-PCIAT_Total'] < -0.05)]\n# selected_features = [col for col in selected_features.index]\n# # selected_features.remove('sii')\n# # selected_features.remove('recalc_sii')\n# selected_features.remove('PCIAT-PCIAT_Total')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.191668Z","iopub.execute_input":"2024-12-21T07:31:08.191908Z","iopub.status.idle":"2024-12-21T07:31:08.195524Z","shell.execute_reply.started":"2024-12-21T07:31:08.191883Z","shell.execute_reply":"2024-12-21T07:31:08.194595Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Correlation Matrix","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv', index_col='id')\nfeatures_num_train_test = ['Basic_Demos-Age', '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', 'Fitness_Endurance-Time_Mins', \n                           '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', 'SDS-SDS_Total_T', \n                           'PreInt_EduHx-computerinternet_hoursday', 'sii']\nfeatures_num_train_test = sorted(features_num_train_test)\ncorr_spearman = train[features_num_train_test].corr(method='spearman')\n\nplt.figure(figsize=(16,14))\nsns.heatmap(corr_spearman, annot=False, cmap='RdYlGn', \n            fmt='.2f', linecolor='black', linewidths=0.5,\n            vmin=-1, vmax=+1)\nplt.title('Spearman Correlation')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:08.196893Z","iopub.execute_input":"2024-12-21T07:31:08.197515Z","iopub.status.idle":"2024-12-21T07:31:09.416055Z","shell.execute_reply.started":"2024-12-21T07:31:08.197472Z","shell.execute_reply":"2024-12-21T07:31:09.415218Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Missing data","metadata":{}},{"cell_type":"code","source":"season_dtype = pl.Enum(['Spring', 'Summer', 'Fall', 'Winter'])\n\ntrain = (\n    pl.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\n    .with_columns(pl.col('^.*Season$').cast(season_dtype))\n)\n\nsupervised_usable = (\n    train\n)\n\nmissing_count = (\n    supervised_usable\n    .null_count()\n    .transpose(include_header=True,\n               header_name='feature',\n               column_names=['null_count'])\n    .sort('null_count', descending=True)\n    .with_columns((pl.col('null_count') / len(supervised_usable)).alias('null_ratio'))\n)\nplt.figure(figsize=(6, 15))\nplt.title(f'Missing values over the {len(supervised_usable)} samples which have a target')\nplt.barh(np.arange(len(missing_count)), missing_count.get_column('null_ratio'), color='coral', label='missing')\nplt.barh(np.arange(len(missing_count)), \n         1 - missing_count.get_column('null_ratio'),\n         left=missing_count.get_column('null_ratio'),\n         color='darkseagreen', label='available')\nplt.yticks(np.arange(len(missing_count)), missing_count.get_column('feature'))\nplt.gca().xaxis.set_major_formatter(PercentFormatter(xmax=1, decimals=0))\nplt.xlim(0, 1)\nplt.legend()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:09.417312Z","iopub.execute_input":"2024-12-21T07:31:09.417662Z","iopub.status.idle":"2024-12-21T07:31:10.509905Z","shell.execute_reply.started":"2024-12-21T07:31:09.417625Z","shell.execute_reply":"2024-12-21T07:31:10.509046Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"drop PAQ_A-PAQ_A_Total, Fitness_Endurance-Time_Sec, Fitness_Endurance-Time_Mins","metadata":{}},{"cell_type":"code","source":"cat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', 'Fitness_Endurance-Season', 'FGC-Season',\n         'BIA-Season', '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\ndef quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\ndef threshold_Rounder(oof_non_rounded, thresholds):\n    return np.where(oof_non_rounded < thresholds[0], 0,\n                    np.where(oof_non_rounded < thresholds[1], 1,\n                             np.where(oof_non_rounded < thresholds[2], 2, 3)))\n\ndef evaluate_predictions(thresholds, y_true, oof_non_rounded):\n    rounded_p = threshold_Rounder(oof_non_rounded, thresholds)\n    return -quadratic_weighted_kappa(y_true, rounded_p)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:10.511127Z","iopub.execute_input":"2024-12-21T07:31:10.511721Z","iopub.status.idle":"2024-12-21T07:31:10.520337Z","shell.execute_reply.started":"2024-12-21T07:31:10.511682Z","shell.execute_reply":"2024-12-21T07:31:10.519332Z"}},"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    df['BMI_PHR'] = df['Physical-BMI'] * df['Physical-HeartRate']\n    \n    return df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:10.521357Z","iopub.execute_input":"2024-12-21T07:31:10.521646Z","iopub.status.idle":"2024-12-21T07:31:10.533486Z","shell.execute_reply.started":"2024-12-21T07:31:10.521587Z","shell.execute_reply":"2024-12-21T07:31:10.532644Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Encode data","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.LeakyReLU(0.2),\n            nn.Linear(encoding_dim*3, encoding_dim*2),\n            nn.LeakyReLU(0.2),\n            nn.Linear(encoding_dim*2, encoding_dim),\n            nn.LeakyReLU(0.2)\n        )\n        self.decoder = nn.Sequential(\n            nn.Linear(encoding_dim, input_dim*2),\n            nn.LeakyReLU(0.2),\n            nn.Linear(input_dim*2, input_dim*3),\n            nn.LeakyReLU(0.2),\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":"2024-12-21T07:31:10.534714Z","iopub.execute_input":"2024-12-21T07:31:10.535068Z","iopub.status.idle":"2024-12-21T07:31:10.546986Z","shell.execute_reply.started":"2024-12-21T07:31:10.535029Z","shell.execute_reply":"2024-12-21T07:31:10.546240Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def process_file(filename, dirname):\n    df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n    df.drop('step', axis=1, inplace=True)\n    return df.describe().values.reshape(-1), filename.split('=')[1]\n\ndef load_time_series(dirname) -> pd.DataFrame:\n    ids = os.listdir(dirname)\n    \n    with ThreadPoolExecutor() as executor:\n        results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n    \n    stats, indexes = zip(*results)\n    \n    df = pd.DataFrame(stats, columns=[f\"stat_{i}\" for i in range(len(stats[0]))])\n    df['id'] = indexes\n    return df\n\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":"2024-12-21T07:31:10.548053Z","iopub.execute_input":"2024-12-21T07:31:10.548389Z","iopub.status.idle":"2024-12-21T07:31:10.560807Z","shell.execute_reply.started":"2024-12-21T07:31:10.548353Z","shell.execute_reply":"2024-12-21T07:31:10.560051Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Tabnet","metadata":{}},{"cell_type":"code","source":"from pytorch_tabnet.tab_model import TabNetRegressor\nimport torch","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:10.566289Z","iopub.execute_input":"2024-12-21T07:31:10.566919Z","iopub.status.idle":"2024-12-21T07:31:10.582293Z","shell.execute_reply.started":"2024-12-21T07:31:10.566880Z","shell.execute_reply":"2024-12-21T07:31:10.581409Z"}},"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=200,\n            patience=20,\n            batch_size=1024,\n            virtual_batch_size=128,\n            num_workers=0,\n            drop_last=False,\n            callbacks=[\n                TabNetPretrainedModelCheckpoint(\n                    filepath=self.best_model_path,\n                    monitor='valid_mse',\n                    mode='min',\n                    save_best_only=True,\n                    verbose=True\n                )\n            ]\n        )\n        \n        # Load the best model\n        if os.path.exists(self.best_model_path):\n            self.model.load_model(self.best_model_path)\n            os.remove(self.best_model_path)  # Remove temporary file\n        \n        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': 0,\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":"2024-12-21T07:31:10.583719Z","iopub.execute_input":"2024-12-21T07:31:10.584007Z","iopub.status.idle":"2024-12-21T07:31:10.657635Z","shell.execute_reply.started":"2024-12-21T07:31:10.583981Z","shell.execute_reply":"2024-12-21T07:31:10.656504Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model 1","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')\n\ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\ndf_train = train_ts.drop('id', axis=1)\ndf_test = test_ts.drop('id', axis=1)\n\ntrain_ts_encoded = perform_autoencoder(df_train, encoding_dim=60, epochs=100, batch_size=32)\ntest_ts_encoded = perform_autoencoder(df_test, encoding_dim=60, epochs=100, batch_size=32)\n\ntime_series_cols = train_ts_encoded.columns.tolist()\ntrain_ts_encoded[\"id\"]=train_ts[\"id\"]\ntest_ts_encoded['id']=test_ts[\"id\"]\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')\ntest = pd.merge(test, test_ts_encoded, how=\"left\", on='id')\n\ncolumns = [f'Enc_{i + 1}' for i in range(60)] + ['sii']\n\nimputer = KNNImputer(n_neighbors=5)\n\nnumeric_cols = train.select_dtypes(include=['float64', 'int64']).columns\nnumeric = numeric_cols.tolist()\nnew_numeric = [bla for bla in numeric if bla not in columns]\nnumeric_cols = new_numeric\n\nimputed_data = imputer.fit_transform(train[numeric_cols])\ntrain_imputed = pd.DataFrame(imputed_data, columns=numeric_cols)\n# train_imputed['sii'] = train_imputed['sii'].round().astype(int)\nfor col in train.columns:\n    if col not in numeric_cols:\n        train_imputed[col] = train[col]\n        \ntrain = train_imputed\n\ntrain = feature_engineering(train)\ntrain = train.dropna(thresh=10, axis=0)\ntest = feature_engineering(test)\n\ntrain = train.drop('id', axis=1)\ntest  = test .drop('id', axis=1)   \n\n\nfeaturesCols = ['Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-CGAS_Score', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday', 'sii', 'BMI_Age','Internet_Hours_Age','BMI_Internet_Hours',\n                'BFP_BMI', 'FFMI_BFP', 'FMI_BFP', 'LST_TBW', 'BFP_BMR', 'BFP_DEE', 'BMR_Weight', 'DEE_Weight',\n                'SMM_Height', 'Muscle_to_Fat', 'Hydration_Status', 'ICW_TBW','BMI_PHR']\n\nfeaturesCols += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n\nfeaturesCols = ['Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-CGAS_Score', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday', 'BMI_Age','Internet_Hours_Age','BMI_Internet_Hours',\n                'BFP_BMI', 'FFMI_BFP', 'FMI_BFP', 'LST_TBW', 'BFP_BMR', 'BFP_DEE', 'BMR_Weight', 'DEE_Weight',\n                'SMM_Height', 'Muscle_to_Fat', 'Hydration_Status', 'ICW_TBW','BMI_PHR']\n\nfeaturesCols += time_series_cols\ntest = test[featuresCols]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:31:10.659296Z","iopub.execute_input":"2024-12-21T07:31:10.659637Z","iopub.status.idle":"2024-12-21T07:32:44.332366Z","shell.execute_reply.started":"2024-12-21T07:31:10.659582Z","shell.execute_reply":"2024-12-21T07:32:44.331655Z"}},"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":"2024-12-21T07:32:44.333436Z","iopub.execute_input":"2024-12-21T07:32:44.334099Z","iopub.status.idle":"2024-12-21T07:32:44.341391Z","shell.execute_reply.started":"2024-12-21T07:32:44.334069Z","shell.execute_reply":"2024-12-21T07:32:44.340490Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"n_splits = 5\ndef modelTraining(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=None)\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['id'],\n        'sii': tpTuned\n    })\n\n    return submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:32:44.342571Z","iopub.execute_input":"2024-12-21T07:32:44.342886Z","iopub.status.idle":"2024-12-21T07:32:44.354411Z","shell.execute_reply.started":"2024-12-21T07:32:44.342859Z","shell.execute_reply":"2024-12-21T07:32:44.353552Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"SEED = None\nParams = {\n    'learning_rate': 0.046,\n    'max_depth': 12,\n    'num_leaves': 478,\n    'min_data_in_leaf': 13,\n    'feature_fraction': 0.893,\n    'bagging_fraction': 0.784,\n    'bagging_freq': 4,\n    'lambda_l1': 10,\n    'lambda_l2': 0.01,\n    'device': 'cpu'\n}\n\n# XGBoost parameters\nXGB_Params = {\n    'learning_rate': 0.05,\n    'max_depth': 6,\n    'n_estimators': 200,\n    'subsample': 0.8,\n    'colsample_bytree': 0.8,\n    'reg_alpha': 1, \n    'reg_lambda': 5, \n    'random_state': SEED,\n    'tree_method': 'hist',\n    'device': 'cuda'\n\n}\n\n\n# CatBoost parameters including specification of categorical features\nCatBoost_Params = {\n    'learning_rate': 0.05,\n    'depth': 6,\n    'iterations': 200,\n    'random_seed': SEED,\n    # 'cat_features': cat_c,  # Important: ensure this parameter is configured correctly\n    'verbose': 0,\n    'l2_leaf_reg': 20,\n    'task_type': 'GPU'\n}\n\n\nLight = LGBMRegressor(**Params, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\nTabNet_Model = TabNetWrapper(**TabNet_Params) \n\nvoting_model = VotingRegressor(estimators=[\n    ('lightgbm', Light),\n    ('xgboost', XGB_Model),\n    ('catboost', CatBoost_Model),\n    ('tabnet', TabNet_Model)\n    # ('rf', Pipeline(steps=[('imputer', imputer), ('regressor', RandomForestRegressor(random_state=SEED))])),\n    # ('gb', Pipeline(steps=[('imputer', imputer), ('regressor', GradientBoostingRegressor(random_state=SEED))]))\n], weights=[4.0, 4.0, 5.0, 4.0])\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:32:44.355466Z","iopub.execute_input":"2024-12-21T07:32:44.355832Z","iopub.status.idle":"2024-12-21T07:32:44.376550Z","shell.execute_reply.started":"2024-12-21T07:32:44.355805Z","shell.execute_reply":"2024-12-21T07:32:44.375778Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission1 = modelTraining(voting_model, test)\n\n\n# Submission1.to_csv('submission.csv', index=False)\nprint(Submission1['sii'].value_counts())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:32:44.377550Z","iopub.execute_input":"2024-12-21T07:32:44.377826Z","iopub.status.idle":"2024-12-21T07:33:07.750162Z","shell.execute_reply.started":"2024-12-21T07:32:44.377803Z","shell.execute_reply":"2024-12-21T07:33:07.749147Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:33:07.751590Z","iopub.execute_input":"2024-12-21T07:33:07.752293Z","iopub.status.idle":"2024-12-21T07:33:07.762382Z","shell.execute_reply.started":"2024-12-21T07:33:07.752245Z","shell.execute_reply":"2024-12-21T07:33:07.761442Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model 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')\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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T07:33:07.763387Z","iopub.execute_input":"2024-12-21T07:33:07.763766Z","execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def TrainML(model_class, test_data):\n    # for feature in sorted_feature_names:\n    #     if feature in train.columns:\n    #         train[feature] = np.log1p(train[feature])\n    # train_transformed = train.copy()\n    # train_transformed[common_feature[0]] = np.log1p(train_transformed[common_feature[0]])\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['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\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])\n\n# Train the ensemble model\nSubmission2 = TrainML(voting_model, test)","metadata":{"trusted":true,"execution":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission2","metadata":{"trusted":true,"execution":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model 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')\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\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)","metadata":{"trusted":true,"execution":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def TrainML(model_class, test_data):\n    # for feature in sorted_feature_names:\n    #     if feature in train.columns:\n    #         train[feature] = np.log1p(train[feature])\n    # train_transformed = train.copy()\n    # train_transformed[common_feature[0]] = np.log1p(train_transformed[common_feature[0]])\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=None)\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['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\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])\n\nSubmission3 = TrainML(voting_model, test)","metadata":{"trusted":true,"execution":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission3","metadata":{"trusted":true,"execution":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 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":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"final_submission","metadata":{"trusted":true,"execution":{"execution_failed":"2024-12-21T07:33:30.983Z"}},"outputs":[],"execution_count":null}]}