{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.14"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30761,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false},"papermill":{"default_parameters":{},"duration":121.587074,"end_time":"2024-12-18T22:04:16.978423","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-12-18T22:02:15.391349","version":"2.6.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport polars as pl\nimport pandas as pd\nfrom sklearn.base import clone\nfrom copy import deepcopy\nimport optuna\nfrom scipy.optimize import minimize\nimport os\nfrom scipy.stats import mode\n\nimport re\nfrom colorama import Fore, Style\n\nfrom tqdm import tqdm\nfrom IPython.display import clear_output\nfrom concurrent.futures import ThreadPoolExecutor\n\nimport warnings\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None\n\nimport lightgbm as lgb\nfrom catboost import CatBoostRegressor, CatBoostClassifier\nfrom xgboost import XGBRegressor\nfrom sklearn.ensemble import VotingRegressor\nfrom sklearn.model_selection import *\nfrom sklearn.metrics import *\n\nSEED = 42\nn_splits = 5","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.status.busy":"2025-01-13T20:33:16.394984Z","iopub.execute_input":"2025-01-13T20:33:16.395433Z","iopub.status.idle":"2025-01-13T20:33:16.405133Z","shell.execute_reply.started":"2025-01-13T20:33:16.395400Z","shell.execute_reply":"2025-01-13T20:33:16.403854Z"},"papermill":{"duration":5.77022,"end_time":"2024-12-18T22:02:24.80587","exception":false,"start_time":"2024-12-18T22:02:19.03565","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Pre-processing","metadata":{}},{"cell_type":"code","source":"%%time\n\ndef process_file(filename, dirname):\n    df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n    df.drop('step', axis=1, inplace=True)\n    return df.describe().values.reshape(-1), filename.split('=')[1]\n\ndef load_time_series(dirname) -> pd.DataFrame:\n    ids = os.listdir(dirname)\n    \n    with ThreadPoolExecutor() as executor:\n        results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n    \n    stats, indexes = zip(*results)\n    \n    df = pd.DataFrame(stats, columns=[f\"Stat_{i}\" for i in range(len(stats[0]))])\n    df['id'] = indexes\n    \n    return df\n\ntrain = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\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', 'Fitness_Endurance-Season', \n          'FGC-Season', 'BIA-Season', 'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\n\ndef update(df):\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_train = create_mapping(col, train)\n    \n    train[col] = train[col].replace(mapping_train).astype(int)\n    test[col] = test[col].replace(mapping_train).astype(int)\n\nprint(f'Train Shape : {train.shape} || Test Shape : {test.shape}')","metadata":{"execution":{"iopub.status.busy":"2025-01-13T20:33:16.407649Z","iopub.execute_input":"2025-01-13T20:33:16.408056Z","iopub.status.idle":"2025-01-13T20:35:50.883166Z","shell.execute_reply.started":"2025-01-13T20:33:16.408020Z","shell.execute_reply":"2025-01-13T20:35:50.881406Z"},"papermill":{"duration":96.353436,"end_time":"2024-12-18T22:04:01.16841","exception":false,"start_time":"2024-12-18T22:02:24.814974","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2025-01-13T20:35:50.885858Z","iopub.execute_input":"2025-01-13T20:35:50.886328Z","iopub.status.idle":"2025-01-13T20:35:51.002061Z","shell.execute_reply.started":"2025-01-13T20:35:50.886277Z","shell.execute_reply":"2025-01-13T20:35:51.000898Z"},"papermill":{"duration":0.153815,"end_time":"2024-12-18T22:04:01.355634","exception":false,"start_time":"2024-12-18T22:04:01.201819","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2025-01-13T20:35:51.003823Z","iopub.execute_input":"2025-01-13T20:35:51.004315Z","iopub.status.idle":"2025-01-13T20:35:51.120450Z","shell.execute_reply.started":"2025-01-13T20:35:51.004264Z","shell.execute_reply":"2025-01-13T20:35:51.119431Z"},"papermill":{"duration":0.142224,"end_time":"2024-12-18T22:04:01.522817","exception":false,"start_time":"2024-12-18T22:04:01.380593","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#  Model Building","metadata":{}},{"cell_type":"code","source":"%%time\n\ndef quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\ndef threshold_Rounder(oof_non_rounded, thresholds):\n    return np.where(oof_non_rounded < thresholds[0], 0,\n                    np.where(oof_non_rounded < thresholds[1], 1,\n                             np.where(oof_non_rounded < thresholds[2], 2, 3)))\n\ndef evaluate_predictions(thresholds, y_true, oof_non_rounded):\n    rounded_p = threshold_Rounder(oof_non_rounded, thresholds)\n    return -quadratic_weighted_kappa(y_true, rounded_p)\n\nX = train.drop(['sii'], axis=1)\ny = train['sii']\n\ndef TrainML(model_class, test_data, seed_list):\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=False,)\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        \n        random_seed = np.random.choice(seed_list)\n        \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        if hasattr(model, 'random_state'):\n            model.set_params(random_state=random_seed)\n\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\"Train : {np.mean(train_S):.4f}\")\n    print(f\"Validation : {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 : {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":{"execution":{"iopub.status.busy":"2025-01-13T20:35:51.122558Z","iopub.execute_input":"2025-01-13T20:35:51.122908Z","iopub.status.idle":"2025-01-13T20:35:51.141690Z","shell.execute_reply.started":"2025-01-13T20:35:51.122874Z","shell.execute_reply":"2025-01-13T20:35:51.140302Z"},"papermill":{"duration":0.046972,"end_time":"2024-12-18T22:04:01.648747","exception":false,"start_time":"2024-12-18T22:04:01.601775","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\nLatestParams = {'learning_rate': 0.03755757104848504, 'max_depth': 12, 'num_leaves': 18, 'min_data_in_leaf': 3, \n                'feature_fraction': 0.723690362968002, 'bagging_fraction': 0.688232590484764, 'bagging_freq': 5,\n                'lambda_l1': 0.18512987285245963, 'lambda_l2': 0.18435628737334625}\n\nseed_list = [42, 0, 2024, 7269173, 1234]\nLight = lgb.LGBMRegressor(**LatestParams, verbose=-1, n_estimators=200)\n\nSubmissionEstimator1 = TrainML(Light,test,seed_list)","metadata":{"execution":{"iopub.status.busy":"2025-01-13T20:35:51.143148Z","iopub.execute_input":"2025-01-13T20:35:51.143485Z","iopub.status.idle":"2025-01-13T20:36:05.884965Z","shell.execute_reply.started":"2025-01-13T20:35:51.143453Z","shell.execute_reply":"2025-01-13T20:36:05.883816Z"},"papermill":{"duration":14.2325,"end_time":"2024-12-18T22:04:15.906784","exception":false,"start_time":"2024-12-18T22:04:01.674284","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"print(SubmissionEstimator1['sii'].value_counts())\nSubmissionEstimator1.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2025-01-13T20:36:05.886657Z","iopub.execute_input":"2025-01-13T20:36:05.887147Z","iopub.status.idle":"2025-01-13T20:36:05.900834Z","shell.execute_reply.started":"2025-01-13T20:36:05.887098Z","shell.execute_reply":"2025-01-13T20:36:05.899420Z"},"papermill":{"duration":0.043537,"end_time":"2024-12-18T22:04:16.027502","exception":false,"start_time":"2024-12-18T22:04:15.983965","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null}]}