{"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":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30786,"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:04:38.530535Z","iopub.execute_input":"2024-11-10T13:04:38.531044Z","iopub.status.idle":"2024-11-10T13:04:38.544209Z","shell.execute_reply.started":"2024-11-10T13:04:38.530988Z","shell.execute_reply":"2024-11-10T13:04:38.542412Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## child mind institute Competition ","metadata":{}},{"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":"2024-11-10T13:04:38.546503Z","iopub.execute_input":"2024-11-10T13:04:38.546953Z","iopub.status.idle":"2024-11-10T13:04:38.561440Z","shell.execute_reply.started":"2024-11-10T13:04:38.546909Z","shell.execute_reply":"2024-11-10T13:04:38.560043Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Preprocess","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\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":"2024-11-10T13:04:38.563039Z","iopub.execute_input":"2024-11-10T13:04:38.563429Z","iopub.status.idle":"2024-11-10T13:06:22.995557Z","shell.execute_reply.started":"2024-11-10T13:04:38.563389Z","shell.execute_reply":"2024-11-10T13:06:22.994175Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\ntrain.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:22.997740Z","iopub.execute_input":"2024-11-10T13:06:22.998194Z","iopub.status.idle":"2024-11-10T13:06:23.156728Z","shell.execute_reply.started":"2024-11-10T13:06:22.998150Z","shell.execute_reply":"2024-11-10T13:06:23.155312Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\ntest.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:04:38.369971Z","iopub.execute_input":"2024-11-10T13:04:38.370461Z","iopub.status.idle":"2024-11-10T13:04:38.528486Z","shell.execute_reply.started":"2024-11-10T13:04:38.370405Z","shell.execute_reply":"2024-11-10T13:04:38.526934Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Modeling","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\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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:23.216402Z","iopub.execute_input":"2024-11-10T13:06:23.216986Z","iopub.status.idle":"2024-11-10T13:06:23.246246Z","shell.execute_reply.started":"2024-11-10T13:06:23.216928Z","shell.execute_reply":"2024-11-10T13:06:23.244547Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\nParams7 = {'learning_rate': 0.03884249148676395, 'max_depth': 12, 'num_leaves': 413, 'min_data_in_leaf': 14,\n           'feature_fraction': 0.7987976913702801, 'bagging_fraction': 0.7602261703576205, 'bagging_freq': 2, \n           'lambda_l1': 4.735462555910575, 'lambda_l2': 4.735028557007343e-06} # CV : 0.4094 | LB : 0.471\n\nLight = lgb.LGBMRegressor(**Params7,random_state=SEED, verbose=-1,n_estimators=200)\nSubmission,model = TrainML(Light,test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:23.247756Z","iopub.execute_input":"2024-11-10T13:06:23.248299Z","iopub.status.idle":"2024-11-10T13:06:40.535253Z","shell.execute_reply.started":"2024-11-10T13:06:23.248254Z","shell.execute_reply":"2024-11-10T13:06:40.533931Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:40.537045Z","iopub.execute_input":"2024-11-10T13:06:40.537567Z","iopub.status.idle":"2024-11-10T13:06:40.551606Z","shell.execute_reply.started":"2024-11-10T13:06:40.537509Z","shell.execute_reply":"2024-11-10T13:06:40.550116Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import xgboost as xgb\n# from sklearn.ensemble import VotingRegressor\n\n# XGB_Params = {\n#     'learning_rate': 0.05,\n#     'max_depth': 6,\n#     'n_estimators': 200,\n#     'random_state': SEED\n# }\n\n# XGB = xgb.XGBRegressor(**XGB_Params)\n\n\n# ensemble_model = VotingRegressor(\n#     estimators=[('lgbm', Light), ('xgb', XGB)],\n#     weights=[0.1, 0.9]  # 필요에 따라 조정\n# )\n\n# def TrainML(model, test_data):\n#     X = train.drop(['sii'], axis=1)\n#     y = train['sii']\n\n#     SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n    \n#     train_S = []\n#     test_S = []\n    \n#     oof_non_rounded = np.zeros(len(y), dtype=float) \n#     oof_rounded = np.zeros(len(y), dtype=int) \n#     test_preds = np.zeros((len(test_data), n_splits))\n    \n#     for fold, (train_idx, test_idx) in enumerate(tqdm(SKF.split(X, y), desc=\"Training Folds\", total=n_splits)):\n#         X_train, X_val = X.iloc[train_idx], X.iloc[test_idx]\n#         y_train, y_val = y.iloc[train_idx], y.iloc[test_idx]\n        \n#         # 모델 학습\n#         model.fit(X_train, y_train)\n        \n#         # 예측\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#     # 임계값 최적화\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 :: {tKappa:.3f}\")\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\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:40.553715Z","iopub.execute_input":"2024-11-10T13:06:40.554263Z","iopub.status.idle":"2024-11-10T13:06:40.569917Z","shell.execute_reply.started":"2024-11-10T13:06:40.554207Z","shell.execute_reply":"2024-11-10T13:06:40.568097Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Submission, model = TrainML(ensemble_model, test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:49.536674Z","iopub.execute_input":"2024-11-10T13:06:49.537136Z","iopub.status.idle":"2024-11-10T13:06:49.547290Z","shell.execute_reply.started":"2024-11-10T13:06:49.537094Z","shell.execute_reply":"2024-11-10T13:06:49.545852Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"Submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:49.977892Z","iopub.execute_input":"2024-11-10T13:06:49.978348Z","iopub.status.idle":"2024-11-10T13:06:49.991790Z","shell.execute_reply.started":"2024-11-10T13:06:49.978304Z","shell.execute_reply":"2024-11-10T13:06:49.990062Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# %%time\n\n# feature_importance_df = pd.DataFrame({\n#     'Feature': model.booster_.feature_name(),\n#     'Importance': model.booster_.feature_importance(importance_type='gain')\n# })\n\n# feature_importance_df = feature_importance_df.sort_values(by='Importance', ascending=False)\n\n# plt.figure(figsize=(20, 40))\n# sns.barplot(x='Importance', y='Feature', data=feature_importance_df.head(100)) \n# plt.title(\"Top Feature Importance\")\n# plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:54.010103Z","iopub.execute_input":"2024-11-10T13:06:54.010588Z","iopub.status.idle":"2024-11-10T13:06:54.016265Z","shell.execute_reply.started":"2024-11-10T13:06:54.010544Z","shell.execute_reply":"2024-11-10T13:06:54.014849Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\n\nSubmission.to_csv('submission.csv', index=False)\nprint(Submission['sii'].value_counts())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-10T13:06:54.442490Z","iopub.execute_input":"2024-11-10T13:06:54.442974Z","iopub.status.idle":"2024-11-10T13:06:54.459235Z","shell.execute_reply.started":"2024-11-10T13:06:54.442928Z","shell.execute_reply":"2024-11-10T13:06:54.457968Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}