{"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":"gpu","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30775,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# EVERYONE,WELCOME TO MY NOTEBOOK !","metadata":{}},{"cell_type":"markdown","source":"\n\n
\n

\n CMI 🧭\n

\n
\n","metadata":{}},{"cell_type":"markdown","source":" \n 1 ✨ | \n Import Packages\n\n","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport re\nfrom sklearn.base import clone\nfrom sklearn.metrics import cohen_kappa_score\nfrom sklearn.model_selection import StratifiedKFold\nfrom scipy.optimize import minimize\nfrom concurrent.futures import ThreadPoolExecutor\nfrom tqdm import tqdm\n\nfrom sklearn.preprocessing import StandardScaler\nimport matplotlib.pyplot as plt\nfrom keras.models import Model\nfrom keras.layers import Input, Dense\nfrom keras.optimizers import Adam\n\nfrom colorama import Fore, Style\nfrom IPython.display import clear_output\nimport warnings\nfrom lightgbm import LGBMRegressor\nfrom xgboost import XGBRegressor\nfrom catboost import CatBoostRegressor\nfrom sklearn.ensemble import VotingRegressor, RandomForestRegressor, GradientBoostingRegressor\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.pipeline import Pipeline\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:12:23.158742Z","iopub.execute_input":"2024-10-15T18:12:23.159026Z","iopub.status.idle":"2024-10-15T18:12:41.053387Z","shell.execute_reply.started":"2024-10-15T18:12:23.158995Z","shell.execute_reply":"2024-10-15T18:12:41.052560Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"SEED = 42\nn_splits = 5","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:12:41.054966Z","iopub.execute_input":"2024-10-15T18:12:41.055616Z","iopub.status.idle":"2024-10-15T18:12:41.059759Z","shell.execute_reply.started":"2024-10-15T18:12:41.055580Z","shell.execute_reply":"2024-10-15T18:12:41.058815Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 2 ✨ | \n Data Preprocessing Function\n\n","metadata":{}},{"cell_type":"code","source":"\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\n\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 return df\n\ndef build_autoencoder(input_dim, encoding_dim):\n input_layer = Input(shape=(input_dim,))\n encoded = Dense(encoding_dim, activation='relu')(input_layer)\n decoded = Dense(input_dim, activation='sigmoid')(encoded)\n autoencoder = Model(inputs=input_layer, outputs=decoded)\n encoder = Model(inputs=input_layer, outputs=encoded)\n autoencoder.compile(optimizer=Adam(), loss='mse')\n \n return autoencoder, encoder\n\ndef perform_autoencoder(df, encoding_dim=50, epochs=50, batch_size=32):\n scaler = StandardScaler()\n df_scaled = scaler.fit_transform(df)\n \n input_dim = df_scaled.shape[1]\n autoencoder, encoder = build_autoencoder(input_dim, encoding_dim)\n \n autoencoder.fit(df_scaled, df_scaled, epochs=epochs, batch_size=batch_size, shuffle=True, verbose=1)\n encoded_data = encoder.predict(df_scaled)\n \n df_encoded = pd.DataFrame(encoded_data, columns=[f'Enc_{i+1}' for i in range(encoded_data.shape[1])])\n \n return df_encoded","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:12:41.060810Z","iopub.execute_input":"2024-10-15T18:12:41.061108Z","iopub.status.idle":"2024-10-15T18:12:41.078061Z","shell.execute_reply.started":"2024-10-15T18:12:41.061074Z","shell.execute_reply":"2024-10-15T18:12:41.077163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 3 ✨ | \n Data Loading\n","metadata":{}},{"cell_type":"code","source":"\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\")\n","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:12:41.079160Z","iopub.execute_input":"2024-10-15T18:12:41.079472Z","iopub.status.idle":"2024-10-15T18:14:03.201150Z","shell.execute_reply.started":"2024-10-15T18:12:41.079442Z","shell.execute_reply":"2024-10-15T18:14:03.200191Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndf_train = train_ts.drop('id', axis=1)\ndf_test = test_ts.drop('id', axis=1)\n\ntrain_ts_encoded = perform_autoencoder(df_train, encoding_dim=50, epochs=100, batch_size=32)\ntest_ts_encoded = perform_autoencoder(df_test, encoding_dim=50, epochs=100, batch_size=32)\n\ntime_series_cols = train_ts_encoded.columns.tolist()\ntrain_ts_encoded['id'] = train_ts['id']\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')\ntest = pd.merge(test, train_ts_encoded, 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)","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:14:03.204249Z","iopub.execute_input":"2024-10-15T18:14:03.204631Z","iopub.status.idle":"2024-10-15T18:14:15.885467Z","shell.execute_reply.started":"2024-10-15T18:14:03.204598Z","shell.execute_reply":"2024-10-15T18:14:15.884671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 4 ✨ | \n Feature Analysis\n\n","metadata":{}},{"cell_type":"code","source":"featuresCols = ['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', \n 'Fitness_Endurance-Season', 'FGC-Season', 'BIA-Season', \n 'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:14:15.886536Z","iopub.execute_input":"2024-10-15T18:14:15.886826Z","iopub.status.idle":"2024-10-15T18:14:15.899807Z","shell.execute_reply.started":"2024-10-15T18:14:15.886795Z","shell.execute_reply":"2024-10-15T18:14:15.898981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 5 ✨ | \n Model1\n\n","metadata":{}},{"cell_type":"code","source":"def update(df):\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 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 = 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)\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)\ndef TrainML(model_class, 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 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')\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","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:14:15.901377Z","iopub.execute_input":"2024-10-15T18:14:15.901789Z","iopub.status.idle":"2024-10-15T18:14:15.984861Z","shell.execute_reply.started":"2024-10-15T18:14:15.901724Z","shell.execute_reply":"2024-10-15T18:14:15.984101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 6 ✨ | \n Hyperperameter Tuning 1\n\n","metadata":{}},{"cell_type":"code","source":"\nParams = {\n 'learning_rate': 0.046,\n 'max_depth': 12,\n 'num_leaves': 478,\n 'min_data_in_leaf': 13,\n 'feature_fraction': 0.893,\n 'bagging_fraction': 0.784,\n 'bagging_freq': 4,\n 'lambda_l1': 10, # Increased from 6.59\n 'lambda_l2': 0.01 # Increased from 2.68e-06\n}\n\n\nXGB_Params = {\n 'learning_rate': 0.05,\n 'max_depth': 6,\n 'n_estimators': 200,\n 'subsample': 0.8,\n 'colsample_bytree': 0.8,\n 'reg_alpha': 1, # Increased from 0.1\n 'reg_lambda': 5, # Increased from 1\n 'random_state': SEED,\n 'tree_method': 'exact'\n}\n\n\nCatBoost_Params = {\n 'learning_rate': 0.05,\n 'depth': 6,\n 'iterations': 200,\n 'random_seed': SEED,\n 'cat_features': cat_c,\n 'verbose': 0,\n 'l2_leaf_reg': 10 # Increase this value\n}\n","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:14:15.985946Z","iopub.execute_input":"2024-10-15T18:14:15.986274Z","iopub.status.idle":"2024-10-15T18:14:15.993381Z","shell.execute_reply.started":"2024-10-15T18:14:15.986240Z","shell.execute_reply":"2024-10-15T18:14:15.992335Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 7 ✨ | \n Submission 1\n\n","metadata":{}},{"cell_type":"code","source":"# Create model instances\nLight = LGBMRegressor(**Params, random_state=SEED, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\n\n# Combine models using Voting Regressor\nvoting_model = VotingRegressor(estimators=[\n ('lightgbm', Light),\n ('xgboost', XGB_Model),\n ('catboost', CatBoost_Model)\n])\nSubmission1 = TrainML(voting_model, test)","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:14:15.994792Z","iopub.execute_input":"2024-10-15T18:14:15.995846Z","iopub.status.idle":"2024-10-15T18:14:51.725906Z","shell.execute_reply.started":"2024-10-15T18:14:15.995812Z","shell.execute_reply":"2024-10-15T18:14:51.724802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 8 ✨ | \n Same process 2\n\n","metadata":{}},{"cell_type":"code","source":"train = 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\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\ncat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', \n 'Fitness_Endurance-Season', 'FGC-Season', 'BIA-Season', \n 'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\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\")\n\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 += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n\ndef update(df):\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 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 = 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)\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 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')\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\n\nParams = {\n 'learning_rate': 0.046,\n 'max_depth': 12,\n 'num_leaves': 478,\n 'min_data_in_leaf': 13,\n 'feature_fraction': 0.893,\n 'bagging_fraction': 0.784,\n 'bagging_freq': 4,\n 'lambda_l1': 10, # Increased from 6.59\n 'lambda_l2': 0.01 # Increased from 2.68e-06\n}\n\nXGB_Params = {\n 'learning_rate': 0.05,\n 'max_depth': 6,\n 'n_estimators': 200,\n 'subsample': 0.8,\n 'colsample_bytree': 0.8,\n 'reg_alpha': 1, # Increased from 0.1\n 'reg_lambda': 5, # Increased from 1\n 'random_state': SEED,\n 'tree_method': 'exact'\n}\n\nCatBoost_Params = {\n 'learning_rate': 0.05,\n 'depth': 6,\n 'iterations': 200,\n 'random_seed': SEED,\n 'cat_features': cat_c,\n 'verbose': 0,\n 'l2_leaf_reg': 10 # Increase this value\n}\n\nLight = LGBMRegressor(**Params, random_state=SEED, verbose=-1, n_estimators=300)\nXGB_Model = XGBRegressor(**XGB_Params)\nCatBoost_Model = CatBoostRegressor(**CatBoost_Params)\n\nvoting_model = VotingRegressor(estimators=[\n ('lightgbm', Light),\n ('xgboost', XGB_Model),\n ('catboost', CatBoost_Model)\n])\n\nSubmission2 = TrainML(voting_model, test)","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:14:51.727430Z","iopub.execute_input":"2024-10-15T18:14:51.727828Z","iopub.status.idle":"2024-10-15T18:16:57.777380Z","shell.execute_reply.started":"2024-10-15T18:14:51.727782Z","shell.execute_reply":"2024-10-15T18:16:57.776340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 9 ✨ | \n Same process 3\n\n","metadata":{}},{"cell_type":"code","source":"train = 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\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\ncat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', \n 'Fitness_Endurance-Season', 'FGC-Season', 'BIA-Season', \n 'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\n\n#train_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\n#test_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\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 += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n\ndef update(df):\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 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 = 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)\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 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')\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 tp_rounded = threshold_Rounder(tpm, KappaOPtimizer.x)\n\n return tp_rounded\n\nimputer = SimpleImputer(strategy='median')\n\nensemble = VotingRegressor(estimators=[\n ('lgb', Pipeline(steps=[('imputer', imputer), ('regressor', LGBMRegressor(random_state=SEED))])),\n ('xgb', Pipeline(steps=[('imputer', imputer), ('regressor', XGBRegressor(random_state=SEED))])),\n ('cat', Pipeline(steps=[('imputer', imputer), ('regressor', CatBoostRegressor(random_state=SEED, silent=True))])),\n ('rf', Pipeline(steps=[('imputer', imputer), ('regressor', RandomForestRegressor(random_state=SEED))])),\n ('gb', Pipeline(steps=[('imputer', imputer), ('regressor', GradientBoostingRegressor(random_state=SEED))]))\n])\n\nSubmission3 = TrainML(ensemble, test)\nsample['sii'] = Submission3\nSubmission3 = sample","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:16:57.779261Z","iopub.execute_input":"2024-10-15T18:16:57.779901Z","iopub.status.idle":"2024-10-15T18:19:03.055258Z","shell.execute_reply.started":"2024-10-15T18:16:57.779854Z","shell.execute_reply":"2024-10-15T18:19:03.054267Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" \n 10 ✨ | \n Blending\n\n","metadata":{}},{"cell_type":"code","source":"sub1 = Submission1\nsub2 = Submission2\nsub3 = Submission3\n\nsub1 = sub1.sort_values(by='id').reset_index(drop=True)\nsub2 = sub2.sort_values(by='id').reset_index(drop=True)\nsub3 = sub3.sort_values(by='id').reset_index(drop=True)\n\nsub1 = sub1.rename(columns={'sii': 'sii_1'})\nsub2 = sub2.rename(columns={'sii': 'sii_2'})\nsub3 = sub3.rename(columns={'sii': 'sii_3'})\nsubs = pd.merge(sub1,sub2,on=['id'])\nsubs = pd.merge(subs,sub3,on=['id'])\n\n#subs['sii_s'] = subs['sii_1'] *0.555 + 0.001* subs['sii_2'] + 0.444* subs['sii_3']\n#subs['sii_s'] = subs['sii_1'] *0.450 + 0.450* subs['sii_2'] + 0.100* subs['sii_3']\n#subs['sii_s'] = subs['sii_1'] *0.525 + 0.050* subs['sii_2'] + 0.425* subs['sii_3']\n#subs['sii_s'] = subs['sii_1'] *0.500 + 0.100* subs['sii_2'] + 0.400* subs['sii_3']\n\nsubs['sii_s'] = np.round(subs['sii_1'] *0.85 + 0.10* subs['sii_2'] + 0.05* subs['sii_3'])\n\nsubs['sii_s'] = subs['sii_s'].astype(int)\n\ncombined = pd.DataFrame({\n \n 'id' : sub1['id'],\n \n 'sii_1': sub1['sii_1'],\n 'sii_2': sub2['sii_2'],\n 'sii_3': sub3['sii_3'],\n \n 'sii_s': subs['sii_s'],\n})\n\ndisplay(combined)\n\ndef majority_vote(row):\n return row.mode()[0]\n \ncombined['final_sii'] = combined[['sii_1', 'sii_2', 'sii_3', 'sii_s']].apply(majority_vote, axis=1)\n\nfinal_submission = combined[['id', 'final_sii']].rename(columns={'final_sii': 'sii'})\n\nfinal_submission.to_csv('submission.csv', index=False)\n\nprint(\"Majority voting completed and saved to 'Final_Submission.csv'\")","metadata":{"execution":{"iopub.status.busy":"2024-10-15T18:19:51.880348Z","iopub.execute_input":"2024-10-15T18:19:51.881281Z","iopub.status.idle":"2024-10-15T18:19:51.923392Z","shell.execute_reply.started":"2024-10-15T18:19:51.881219Z","shell.execute_reply":"2024-10-15T18:19:51.922467Z"},"trusted":true},"execution_count":null,"outputs":[]}]}