Child Mind Institute | SIngleLGBM
","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":"2024-09-25T09:34:22.766939Z","iopub.execute_input":"2024-09-25T09:34:22.767427Z","iopub.status.idle":"2024-09-25T09:34:27.265529Z","shell.execute_reply.started":"2024-09-25T09:34:22.767379Z","shell.execute_reply":"2024-09-25T09:34:27.264353Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Basic Preprocess
","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\ndef cal_winsorize(train_data, test_data, limits=[0.01, 0.01]):\n data = pd.concat([train_data, test_data])\n for col in data.columns:\n data[col] = np.clip(data[col].values, np.nanquantile(data[col].values, limits[0]), np.nanquantile(data[col].values, 1 - limits[1]))\n return data.iloc[:len(train_data)], data.iloc[len(train_data):]\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','PCIAT-PCIAT_Total', 'sii']\n\nfeaturesCols += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='PCIAT-PCIAT_Total')\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']\nnum_c = [x for x in featuresCols if x not in cat_c + time_series_cols + ['PCIAT-PCIAT_Total', 'sii']]\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\ntrain[num_c], test[num_c] = cal_winsorize(train[num_c], test[num_c])\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":"2024-09-25T09:40:58.353104Z","iopub.execute_input":"2024-09-25T09:40:58.354931Z","iopub.status.idle":"2024-09-25T09:42:33.512803Z","shell.execute_reply.started":"2024-09-25T09:40:58.354874Z","shell.execute_reply":"2024-09-25T09:42:33.511677Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2024-09-25T09:42:53.200025Z","iopub.execute_input":"2024-09-25T09:42:53.200499Z","iopub.status.idle":"2024-09-25T09:42:53.365373Z","shell.execute_reply.started":"2024-09-25T09:42:53.200454Z","shell.execute_reply":"2024-09-25T09:42:53.364273Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2024-09-25T09:42:56.014731Z","iopub.execute_input":"2024-09-25T09:42:56.015172Z","iopub.status.idle":"2024-09-25T09:42:56.171084Z","shell.execute_reply.started":"2024-09-25T09:42:56.015128Z","shell.execute_reply":"2024-09-25T09:42:56.170099Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Modeling | Single LGBM
","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 round_cut(data):\n data = data.round()\n return np.digitize(data, [0, 31, 50, 80], right=False)- 1\n\ndef TrainML(model_class, test_data, tune=False):\n \n X = train.drop(['PCIAT-PCIAT_Total', 'sii'], axis=1)\n y = train['PCIAT-PCIAT_Total']\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, train['sii']), 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 = round_cut(y_val_pred)\n oof_rounded[test_idx] = y_val_pred_rounded\n\n train_kappa = quadratic_weighted_kappa(round_cut(y_train), round_cut(y_train_pred))\n val_kappa = quadratic_weighted_kappa(round_cut(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=[31, 50, 80], args=(round_cut(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(round_cut(y), oof_tuned)\n\n print(f\"----> || Optimized QWK SCORE :: {Fore.CYAN}{Style.BRIGHT} {tKappa:.3f}{Style.RESET_ALL}\")\n \n if tune:\n return tKappa\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 print(KappaOPtimizer.x)\n\n return submission","metadata":{"execution":{"iopub.status.busy":"2024-09-25T09:43:08.703860Z","iopub.execute_input":"2024-09-25T09:43:08.704369Z","iopub.status.idle":"2024-09-25T09:43:08.726137Z","shell.execute_reply.started":"2024-09-25T09:43:08.704321Z","shell.execute_reply":"2024-09-25T09:43:08.724905Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# %%time\n\n# def objective(trial):\n# # 定义需要调节的参数\n# param = {\n# 'learning_rate': trial.suggest_loguniform('learning_rate', 1e-4, 1e-1),\n# 'max_depth': trial.suggest_int('max_depth', 4, 16),\n# 'num_leaves': trial.suggest_int('num_leaves', 20, 512),\n# 'min_data_in_leaf': trial.suggest_int('min_data_in_leaf', 5, 50),\n# 'feature_fraction': trial.suggest_uniform('feature_fraction', 0.5, 1.0),\n# 'bagging_fraction': trial.suggest_uniform('bagging_fraction', 0.5, 1.0),\n# 'bagging_freq': trial.suggest_int('bagging_freq', 1, 10),\n# 'lambda_l1': trial.suggest_loguniform('lambda_l1', 1e-8, 10.0),\n# 'lambda_l2': trial.suggest_loguniform('lambda_l2', 1e-8, 10.0)\n# }\n# return TrainML(lgb.LGBMRegressor(**param,random_state=SEED, verbose=-1,n_estimators=200), test, True)\n\n\n# study = optuna.create_study(direction='maximize') # 目标是最大化Kappa\n# study.optimize(objective, n_trials=100) # 运行100次实验\n\n# print(\"Best params: \", study.best_params)\n# print(\"Best score: \", study.best_value)","metadata":{"execution":{"iopub.status.busy":"2024-09-25T09:43:36.048623Z","iopub.execute_input":"2024-09-25T09:43:36.049077Z","iopub.status.idle":"2024-09-25T10:05:40.091051Z","shell.execute_reply.started":"2024-09-25T09:43:36.049036Z","shell.execute_reply":"2024-09-25T10:05:40.089855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\n# Params = {'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} \nParams = {'learning_rate': 0.011848748173646595, 'max_depth': 4, 'num_leaves': 291, 'min_data_in_leaf': 37, \n 'feature_fraction': 0.6864077110679211, 'bagging_fraction': 0.5759321360298651, 'bagging_freq': 8, \n 'lambda_l1': 4.055468790477275, 'lambda_l2': 1.3057819206112604}\n\nLight = lgb.LGBMRegressor(**Params,random_state=SEED, verbose=-1,n_estimators=200)\nSubmission = TrainML(Light,test)","metadata":{"execution":{"iopub.status.busy":"2024-09-25T10:06:28.681347Z","iopub.execute_input":"2024-09-25T10:06:28.681801Z","iopub.status.idle":"2024-09-25T10:06:35.126127Z","shell.execute_reply.started":"2024-09-25T10:06:28.681757Z","shell.execute_reply":"2024-09-25T10:06:35.125076Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Submission
","metadata":{}},{"cell_type":"code","source":"%%time\n\nSubmission.to_csv('submission.csv', index=False)\nprint(Submission['sii'].value_counts())","metadata":{"execution":{"iopub.status.busy":"2024-09-25T06:18:59.194915Z","iopub.execute_input":"2024-09-25T06:18:59.195411Z","iopub.status.idle":"2024-09-25T06:18:59.206754Z","shell.execute_reply.started":"2024-09-25T06:18:59.195359Z","shell.execute_reply":"2024-09-25T06:18:59.205495Z"},"trusted":true},"execution_count":null,"outputs":[]}]}