{"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":30761,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### ℹ️ **Info**\n* **forked original great work kernels**\n    * https://www.kaggle.com/code/abdmental01/cmi-single-lgbm\n    \n* **2024/09/26 My Changed**\n    * add more \"stat\" fe※\n    * FeatureSelection & ReTrain\n\n```\n※\"stat_\"FE\nThe columns with the 'stat_' prefix represent numerical features (statistics) that were extracted from each actigraphy dataset file. \nThe process_file function likely computes various statistical measures (such as mean, median, standard deviation, min, max, etc.) for each column in the original time-series data. \n\nsee:https://www.kaggle.com/code/abdmental01/cmi-single-lgbm/comments#2997965\n```","metadata":{}},{"cell_type":"markdown","source":"# <p style=\"background-color:#6A1B9A; font-family:'Dancing Script', cursive; color:#FFFFFF; font-size:150%; text-align:center; border: 3px solid #FFEB3B; border-radius:40px; padding: 10px;\">Child Mind Institute | SIngleLGBM</p>","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\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","execution":{"iopub.status.busy":"2024-09-27T02:47:20.557703Z","iopub.execute_input":"2024-09-27T02:47:20.558161Z","iopub.status.idle":"2024-09-27T02:47:25.661886Z","shell.execute_reply.started":"2024-09-27T02:47:20.558117Z","shell.execute_reply":"2024-09-27T02:47:25.660621Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <p style=\"background-color:#6A1B9A; font-family:'Dancing Script', cursive; color:#FFFFFF; font-size:120%; text-align:center; border: 3px solid #FFEB3B; border-radius:40px; padding: 10px;\">Basic Preprocess</p>","metadata":{}},{"cell_type":"code","source":"%%time\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\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_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','FGC-Season',\n 'BIA-Season','PAQ_A-Season','PAQ_C-Season','SDS-Season','PreInt_EduHx-Season']\n\ndef update(df):\n    \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        \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\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":{"execution":{"iopub.status.busy":"2024-09-27T02:47:25.664398Z","iopub.execute_input":"2024-09-27T02:47:25.665039Z","iopub.status.idle":"2024-09-27T02:49:06.964532Z","shell.execute_reply.started":"2024-09-27T02:47:25.664992Z","shell.execute_reply":"2024-09-27T02:49:06.963295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n### **》》》Add FE**\n---","metadata":{}},{"cell_type":"code","source":"# fe index check\nfor i in train.columns.to_list():\n    if i.startswith('stat_'):\n        print(f\"{train.columns.to_list().index(i)},{i}\")","metadata":{"scrolled":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-09-27T02:49:06.966358Z","iopub.execute_input":"2024-09-27T02:49:06.966837Z","iopub.status.idle":"2024-09-27T02:49:06.976292Z","shell.execute_reply.started":"2024-09-27T02:49:06.966784Z","shell.execute_reply":"2024-09-27T02:49:06.974932Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\"\"\"\n59,stat_0\n154,stat_95\n\"\"\"\nfor i in range(59,154,5):\n    train[f\"stat_mean{i}\"] = train.iloc[:, i:i+5].mean(axis=1)\n#     train[f\"stat_sum{i}\"] = train.iloc[:, i:i+5].sum(axis=1)\n\ntrain[f\"stat_mean_all\"] = train.iloc[:, 59:154].mean(axis=1)\n# train[f\"stat_sum_all\"] = train.iloc[:, 59:154].sum(axis=1)\n\n# ---------------------------------------------------------------- #\nfor i in range(58,153,5):\n    test[f\"stat_mean{i+1}\"] = test.iloc[:, i:i+5].mean(axis=1)\n#     test[f\"stat_sum{i+1}\"] = test.iloc[:, i:i+5].sum(axis=1)\n\ntest[f\"stat_mean_all\"] = test.iloc[:, 58:153].mean(axis=1)\n# test[f\"stat_sum_all\"] = test.iloc[:, 58:153].sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:06.979783Z","iopub.execute_input":"2024-09-27T02:49:06.980344Z","iopub.status.idle":"2024-09-27T02:49:07.062959Z","shell.execute_reply.started":"2024-09-27T02:49:06.980287Z","shell.execute_reply":"2024-09-27T02:49:07.061516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:07.064562Z","iopub.execute_input":"2024-09-27T02:49:07.064950Z","iopub.status.idle":"2024-09-27T02:49:07.237902Z","shell.execute_reply.started":"2024-09-27T02:49:07.064911Z","shell.execute_reply":"2024-09-27T02:49:07.236597Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:07.239656Z","iopub.execute_input":"2024-09-27T02:49:07.240122Z","iopub.status.idle":"2024-09-27T02:49:07.414495Z","shell.execute_reply.started":"2024-09-27T02:49:07.240070Z","shell.execute_reply":"2024-09-27T02:49:07.413294Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <p style=\"background-color:#6A1B9A; font-family:'Dancing Script', cursive; color:#FFFFFF; font-size:120%; text-align:center; border: 3px solid #FFEB3B; border-radius:40px; padding: 10px;\">Modeling | Single LGBM</p>","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    models = []\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        models.append(model)\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, models, X","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:07.415891Z","iopub.execute_input":"2024-09-27T02:49:07.416361Z","iopub.status.idle":"2024-09-27T02:49:07.435669Z","shell.execute_reply.started":"2024-09-27T02:49:07.416319Z","shell.execute_reply":"2024-09-27T02:49:07.434473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\nParams = {'learning_rate': 0.04603534510792164, 'max_depth': 12, 'num_leaves': 478, 'min_data_in_leaf': 13,\n          'feature_fraction': 0.8935304204489449, 'bagging_fraction': 0.7840117449237969, 'bagging_freq': 4,\n          'lambda_l1': 6.596560434072009, 'lambda_l2': 2.680080551210706e-06} \n\nLight = lgb.LGBMRegressor(**Params,random_state=SEED, verbose=-1,n_estimators=200)\nSubmission, models_train1, X = TrainML(Light,test)","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:07.437040Z","iopub.execute_input":"2024-09-27T02:49:07.437528Z","iopub.status.idle":"2024-09-27T02:49:30.656609Z","shell.execute_reply.started":"2024-09-27T02:49:07.437475Z","shell.execute_reply":"2024-09-27T02:49:30.653731Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n### **》》》Importance&FeatureSelection**\n---","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimportance_df = pd.DataFrame(np.sum([model.feature_importances_ for model in models_train1], axis=0), index=X.columns, columns=['importance']).sort_values('importance',ascending=True)\nimportance_df\n\nfig = plt.figure(figsize=(10, 30))\nplt.barh(importance_df.index, importance_df[\"importance\"], align=\"center\")\nplt.title(\"Feature Importance\")","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:30.659591Z","iopub.execute_input":"2024-09-27T02:49:30.660257Z","iopub.status.idle":"2024-09-27T02:49:33.631702Z","shell.execute_reply.started":"2024-09-27T02:49:30.660154Z","shell.execute_reply":"2024-09-27T02:49:33.630312Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMPOTTANCE_TH = 10\ndrop_fes = importance_df[importance_df[\"importance\"]<=IMPOTTANCE_TH].index.to_list()\ndrop_fes","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:33.636236Z","iopub.execute_input":"2024-09-27T02:49:33.636766Z","iopub.status.idle":"2024-09-27T02:49:33.648964Z","shell.execute_reply.started":"2024-09-27T02:49:33.636713Z","shell.execute_reply":"2024-09-27T02:49:33.647523Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = train.drop(columns=drop_fes)\ntest = test.drop(columns=drop_fes)","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:33.650704Z","iopub.execute_input":"2024-09-27T02:49:33.651201Z","iopub.status.idle":"2024-09-27T02:49:33.670499Z","shell.execute_reply.started":"2024-09-27T02:49:33.651145Z","shell.execute_reply":"2024-09-27T02:49:33.669087Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n### **》》》ReTrain**\n---","metadata":{}},{"cell_type":"code","source":"%%time\n\nParams = {'learning_rate': 0.04603534510792164, 'max_depth': 12, 'num_leaves': 478, 'min_data_in_leaf': 13,\n          'feature_fraction': 0.8935304204489449, 'bagging_fraction': 0.7840117449237969, 'bagging_freq': 4,\n          'lambda_l1': 6.596560434072009, 'lambda_l2': 2.680080551210706e-06} \n\nLight = lgb.LGBMRegressor(**Params,random_state=SEED, verbose=-1,n_estimators=200)\nSubmission, models_train1, X = TrainML(Light,test)","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:33.672416Z","iopub.execute_input":"2024-09-27T02:49:33.672922Z","iopub.status.idle":"2024-09-27T02:49:50.268362Z","shell.execute_reply.started":"2024-09-27T02:49:33.672869Z","shell.execute_reply":"2024-09-27T02:49:50.267050Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimportance_df = pd.DataFrame(np.sum([model.feature_importances_ for model in models_train1], axis=0), index=X.columns, columns=['importance']).sort_values('importance',ascending=True)\nimportance_df\n\nfig = plt.figure(figsize=(10, 30))\nplt.barh(importance_df.index, importance_df[\"importance\"], align=\"center\")\nplt.title(\"Feature Importance\")","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:50.270043Z","iopub.execute_input":"2024-09-27T02:49:50.270507Z","iopub.status.idle":"2024-09-27T02:49:52.468815Z","shell.execute_reply.started":"2024-09-27T02:49:50.270454Z","shell.execute_reply":"2024-09-27T02:49:52.467449Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <p style=\"background-color:#6A1B9A; font-family:'Dancing Script', cursive; color:#FFFFFF; font-size:120%; text-align:center; border: 3px solid #FFEB3B; border-radius:40px; padding: 10px;\">Submission</p>","metadata":{}},{"cell_type":"code","source":"%%time\n\nSubmission.to_csv('submission.csv', index=False)\nprint(Submission['sii'].value_counts())","metadata":{"execution":{"iopub.status.busy":"2024-09-27T02:49:52.470572Z","iopub.execute_input":"2024-09-27T02:49:52.471057Z","iopub.status.idle":"2024-09-27T02:49:52.487765Z","shell.execute_reply.started":"2024-09-27T02:49:52.470992Z","shell.execute_reply":"2024-09-27T02:49:52.486291Z"},"trusted":true},"execution_count":null,"outputs":[]}]}