{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30822,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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\nimport matplotlib.pyplot as plt\nimport seaborn as sns\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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T16:49:16.197186Z","iopub.execute_input":"2024-12-19T16:49:16.197601Z","iopub.status.idle":"2024-12-19T16:49:16.204839Z","shell.execute_reply.started":"2024-12-19T16:49:16.197565Z","shell.execute_reply":"2024-12-19T16:49:16.203698Z"}},"outputs":[],"execution_count":null},{"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\ndef optimize_lgbm(trial):\n    param = {\n        'objective': 'regression',\n        'metric': 'None',  # Tắt metric mặc định\n        'boosting_type': 'gbdt',\n        'learning_rate': trial.suggest_loguniform('learning_rate', 0.01, 0.1),\n        'num_leaves': trial.suggest_int('num_leaves', 31, 1023),\n        'max_depth': trial.suggest_int('max_depth', -1, 16),\n        'min_data_in_leaf': trial.suggest_int('min_data_in_leaf', 10, 100),\n        'feature_fraction': trial.suggest_uniform('feature_fraction', 0.6, 1.0),\n        'bagging_fraction': trial.suggest_uniform('bagging_fraction', 0.6, 1.0),\n        'bagging_freq': trial.suggest_int('bagging_freq', 1, 10),\n        'lambda_l1': trial.suggest_loguniform('lambda_l1', 1e-3, 10.0),\n        'lambda_l2': trial.suggest_loguniform('lambda_l2', 1e-3, 10.0),\n        'random_state': SEED\n    }\n\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n    oof_non_rounded = np.zeros(len(y), dtype=float)\n\n    for train_idx, val_idx in SKF.split(X, y):\n        X_train, X_val = X.iloc[train_idx], X.iloc[val_idx]\n        y_train, y_val = y.iloc[train_idx], y.iloc[val_idx]\n\n        model = lgb.LGBMRegressor(**param, n_estimators=500)\n        model.fit(X_train, y_train,\n                  eval_set=[(X_val, y_val)])\n\n        oof_non_rounded[val_idx] = model.predict(X_val)\n\n    # Tối ưu QWK dựa trên ngưỡng\n    KappaOptimizer = minimize(\n        evaluate_predictions,\n        x0=[0.5, 1.5, 2.5],\n        args=(y, oof_non_rounded),\n        method='Nelder-Mead'\n    )\n    oof_tuned = threshold_Rounder(oof_non_rounded, KappaOptimizer.x)\n    qwk_score = quadratic_weighted_kappa(y, oof_tuned)\n    return -qwk_score  # Optuna sẽ tối ưu hóa dựa trên QWK\n\n\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\n\nfor col in cat_c:\n    mapping_train = create_mapping(col, train)\n    mapping_test = create_mapping(col, test)\n\n    train[col] = train[col].replace(mapping_train).astype(int)\n    test[col] = test[col].replace(mapping_test).astype(int)\n\nprint(f'Train Shape : {train.shape} || Test Shape : {test.shape}')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T17:51:20.501585Z","iopub.execute_input":"2024-12-19T17:51:20.501967Z","iopub.status.idle":"2024-12-19T17:52:37.274591Z","shell.execute_reply.started":"2024-12-19T17:51:20.501939Z","shell.execute_reply":"2024-12-19T17:52:37.273600Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\ntrain.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T17:33:46.192710Z","iopub.execute_input":"2024-12-19T17:33:46.193196Z","iopub.status.idle":"2024-12-19T17:33:46.301609Z","shell.execute_reply.started":"2024-12-19T17:33:46.193165Z","shell.execute_reply":"2024-12-19T17:33:46.300447Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\ntest.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T17:33:49.336426Z","iopub.execute_input":"2024-12-19T17:33:49.336802Z","iopub.status.idle":"2024-12-19T17:33:49.439981Z","shell.execute_reply.started":"2024-12-19T17:33:49.336772Z","shell.execute_reply":"2024-12-19T17:33:49.438974Z"}},"outputs":[],"execution_count":null},{"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\nstudy = optuna.create_study(direction='maximize')  # Chuyển thành maximize\nstudy.optimize(optimize_lgbm, n_trials=50)\nbest_params = study.best_params\nprint(\"Best Parameters:\", best_params)\n\n\nLight = lgb.LGBMRegressor(**best_params)\n\ndef TrainML(model_class, test_data):\n\n    X = train.drop(['sii'], axis=1)\n    y = train['sii']\n\n    SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n\n    train_S = []\n    test_S = []\n\n    oof_non_rounded = np.zeros(len(y), dtype=float)\n    oof_rounded = np.zeros(len(y), dtype=int)\n    test_preds = np.zeros((len(test_data), n_splits))\n\n    for fold, (train_idx, test_idx) in enumerate(tqdm(SKF.split(X, y), desc=\"Training Folds\", total=n_splits)):\n        X_train, X_val = X.iloc[train_idx], X.iloc[test_idx]\n        y_train, y_val = y.iloc[train_idx], y.iloc[test_idx]\n\n        model = clone(model_class)\n        model.fit(X_train, y_train)\n\n        y_train_pred = model.predict(X_train)\n        y_val_pred = model.predict(X_val)\n\n        oof_non_rounded[test_idx] = y_val_pred\n        y_val_pred_rounded = y_val_pred.round(0).astype(int)\n        oof_rounded[test_idx] = y_val_pred_rounded\n\n        train_kappa = quadratic_weighted_kappa(y_train, y_train_pred.round(0).astype(int))\n        val_kappa = quadratic_weighted_kappa(y_val, y_val_pred_rounded)\n\n        train_S.append(train_kappa)\n        test_S.append(val_kappa)\n\n        test_preds[:, fold] = model.predict(test_data)\n\n        print(f\"Fold {fold+1} - Train QWK: {train_kappa:.4f}, Validation QWK: {val_kappa:.4f}\")\n        clear_output(wait=True)\n\n    print(f\"Mean Train QWK --> {np.mean(train_S):.4f}\")\n    print(f\"Mean Validation QWK ---> {np.mean(test_S):.4f}\")\n\n    KappaOPtimizer = minimize(evaluate_predictions,\n                              x0=[0.5, 1.5, 2.5], args=(y, oof_non_rounded),\n                              method='Nelder-Mead') # Nelder-Mead | # Powell\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,model\n\nSubmission,model = TrainML(Light,test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T17:52:45.738108Z","iopub.execute_input":"2024-12-19T17:52:45.738440Z","iopub.status.idle":"2024-12-19T18:02:49.734795Z","shell.execute_reply.started":"2024-12-19T17:52:45.738414Z","shell.execute_reply":"2024-12-19T18:02:49.733884Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\nfeature_importance_df = pd.DataFrame({\n    'Feature': model.booster_.feature_name(),\n    'Importance': model.booster_.feature_importance(importance_type='gain')\n})\n\nfeature_importance_df = feature_importance_df.sort_values(by='Importance', ascending=False)\n\nplt.figure(figsize=(20, 40))\nsns.barplot(x='Importance', y='Feature', data=feature_importance_df.head(100))\nplt.title(\"Top Feature Importance\")\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T17:14:09.621216Z","iopub.execute_input":"2024-12-19T17:14:09.621583Z","iopub.status.idle":"2024-12-19T17:14:11.185980Z","shell.execute_reply.started":"2024-12-19T17:14:09.621555Z","shell.execute_reply":"2024-12-19T17:14:11.184756Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\nSubmission.to_csv('submission.csv', index=False)\n# print(Submission['sii'].value_counts())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-19T17:14:31.930619Z","iopub.execute_input":"2024-12-19T17:14:31.931120Z","iopub.status.idle":"2024-12-19T17:14:31.938461Z","shell.execute_reply.started":"2024-12-19T17:14:31.931083Z","shell.execute_reply":"2024-12-19T17:14:31.936891Z"}},"outputs":[],"execution_count":null}]}