{ "metadata": { "kernelspec": { "language": "python", "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python", "version": "3.10.13", "mimetype": "text/x-python", "codemirror_mode": { "name": "ipython", "version": 3 }, "pygments_lexer": "ipython3", "nbconvert_exporter": "python", "file_extension": ".py" }, "kaggle": { "accelerator": "nvidiaTeslaT4", "dataSources": [ { "sourceId": 8572275, "sourceType": "datasetVersion", "datasetId": 5125812 } ], "dockerImageVersionId": 30716, "isInternetEnabled": true, "language": "python", "sourceType": "notebook", "isGpuEnabled": true } }, "nbformat_minor": 4, "nbformat": 4, "cells": [ { "cell_type": "code", "source": [ "!pip install -qq optuna-integration\n", "!pip install -qq feature-engine" ], "metadata": { "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5", "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19", "execution": { "iopub.status.busy": "2024-05-31T20:47:35.917638Z", "iopub.execute_input": "2024-05-31T20:47:35.917915Z", "iopub.status.idle": "2024-05-31T20:48:06.623648Z", "shell.execute_reply.started": "2024-05-31T20:47:35.917890Z", "shell.execute_reply": "2024-05-31T20:48:06.622567Z" }, "trusted": true }, "execution_count": 1, "outputs": [ { "name": "stdout", "text": "\u001B[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\nspopt 0.6.0 requires shapely>=2.0.1, but you have shapely 1.8.5.post1 which is incompatible.\u001B[0m\u001B[31m\n\u001B[0m", "output_type": "stream" } ] }, { "cell_type": "code", "source": [ "import os\n", "import numpy as np\n", "import pandas as pd\n", "import xgboost as xgb\n", "import optuna\n", "from optuna_integration import XGBoostPruningCallback\n", "from feature_engine.timeseries.forecasting import LagFeatures\n", "from functools import partial\n", "from sklearn.metrics import roc_auc_score\n", "dset_path = '/kaggle/input/stocks-and-sentiments'\n", "fpaths = [dset_path + f'/{fname}' for fname in os.listdir(dset_path)]\n", "df = pd.read_csv(fpaths[0], index_col='date', parse_dates=['date']).drop(columns=['blob_sub_med', 'finbert_sent', 'blob_sub'])\n", "df['clabel'] = df['return'].map(lambda x: 1 if x > 0 else 0)\n", "print(fpaths[0].split('/')[-1][:-4])" ], "metadata": { "execution": { "iopub.status.busy": "2024-05-31T20:50:54.778415Z", "iopub.execute_input": "2024-05-31T20:50:54.779125Z", "iopub.status.idle": "2024-05-31T20:50:54.808823Z", "shell.execute_reply.started": "2024-05-31T20:50:54.779096Z", "shell.execute_reply": "2024-05-31T20:50:54.807898Z" }, "trusted": true }, "execution_count": 7, "outputs": [ { "name": "stdout", "text": "AAPL\n", "output_type": "stream" } ] }, { "cell_type": "code", "source": [ "def tts_last_n(feature_sequences, target, n: int = 365) -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:\n", "\n", " train_sequences = feature_sequences[:-n]\n", " test_sequences = feature_sequences[-n:]\n", " train_target = target[:-n]\n", " test_target = target[-n:]\n", "\n", " return train_sequences, test_sequences, train_target, test_target\n", "\n", "def objective(trial, df):\n", " lags = trial.suggest_int('lags', 2, 20)\n", " og_cols = df.columns.tolist()\n", " og_cols.remove('clabel')\n", " lag_transformer = LagFeatures(periods=[x for x in range(1, lags + 1)])\n", " lagged_df = lag_transformer.fit_transform(df)\n", " lagged_df = lagged_df.dropna().drop(columns=og_cols)\n", " X = lagged_df.drop(columns=['clabel'])\n", " y = lagged_df.clabel\n", " X_train, X_test, y_train, y_test = tts_last_n(X, y, 252)\n", " params = {\n", " 'objective': 'binary:logistic',\n", " 'eval_metric': 'auc',\n", "# 'device': 'cuda',\n", " 'max_depth': trial.suggest_int('max_depth', 3, 10),\n", " 'learning_rate': trial.suggest_float('learning_rate', 0.001, 0.1, log=True),\n", " 'subsample': trial.suggest_float('subsample', 0.5, 1.0),\n", " 'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1.0),\n", " 'reg_alpha': trial.suggest_float('reg_alpha', 1e-10, 100.0, log=True),\n", " 'reg_lambda': trial.suggest_float('reg_lambda', 1e-10, 100.0, log=True),\n", " 'random_state': 21052003\n", " }\n", " num_boost_round = trial.suggest_int('num_boost_rounds', 100, 1500)\n", " X_opt, X_val, y_opt, y_val = tts_last_n(X_train, y_train, 252)\n", " dopt = xgb.DMatrix(X_opt, y_opt)\n", " dval = xgb.DMatrix(X_val, y_val)\n", " \n", " pruning_callback = XGBoostPruningCallback(trial, 'validation-auc')\n", " bst = xgb.train(params=params,\n", " dtrain=dopt,\n", " evals=[(dval, 'validation')],\n", " callbacks=[pruning_callback],\n", " num_boost_round=num_boost_round,\n", " verbose_eval=False)\n", " y_pred = bst.predict(dval)\n", " return roc_auc_score(y_val, y_pred)\n", "\n", "objective_w = partial(objective, df=df)\n", "study = optuna.create_study(direction='maximize')\n", "study.optimize(objective_w, n_trials=1000)\n", "\n", "\n", "with open('/kaggle/working/output.txt', 'w') as of:\n", " print('Number of finished trials:', len(study.trials))\n", " print('Best trial:', file=of)\n", " trial = study.best_trial\n", " print(' Value: {:.5f}'.format(trial.value), file=of)\n", " print(' Params: ', file=of)\n", " for key, value in trial.params.items():\n", " print(' {}: {}'.format(key, value), file=of)\n", "\n", "# model_name = input('Model name: ')\n", "\n", "best_params = trial.params\n", "\n", "const_params = {\n", " 'objective': 'binary:logistic',\n", " 'eval_metric': 'auc',\n", "# 'device': 'cuda',\n", " 'random_state': 21052003\n", "}\n", "\n", "n_rounds = best_params['num_boost_rounds']\n", "best_params.pop('num_boost_rounds')\n", "best_params.update(const_params)\n", "\n" ], "metadata": { "execution": { "iopub.status.busy": "2024-05-31T20:50:59.960154Z", "iopub.execute_input": "2024-05-31T20:50:59.960874Z", "iopub.status.idle": "2024-05-31T21:10:03.037229Z", "shell.execute_reply.started": "2024-05-31T20:50:59.960844Z", "shell.execute_reply": "2024-05-31T21:10:03.036212Z" }, "trusted": true }, "execution_count": 8, "outputs": [ { "name": "stderr", "text": "[I 2024-05-31 20:50:59,974] A new study created in memory with name: no-name-1f2adffd-4c2a-4d9b-99eb-c4c639020e63\n[I 2024-05-31 20:51:00,828] Trial 0 finished with value: 0.5 and parameters: {'lags': 3, 'max_depth': 8, 'learning_rate': 0.041257651223674495, 'subsample': 0.8030454506957634, 'colsample_bytree': 0.9222608790811524, 'reg_alpha': 98.12765417499399, 'reg_lambda': 88.82809347407957, 'num_boost_rounds': 620}. Best is trial 0 with value: 0.5.\n[I 2024-05-31 20:51:36,970] Trial 1 finished with value: 0.5224464060529634 and parameters: {'lags': 18, 'max_depth': 6, 'learning_rate': 0.00601488341385521, 'subsample': 0.7490540779095216, 'colsample_bytree': 0.9808296599477502, 'reg_alpha': 4.396204441958627e-09, 'reg_lambda': 2.286306099468803e-07, 'num_boost_rounds': 854}. Best is trial 1 with value: 0.5224464060529634.\n[I 2024-05-31 20:51:44,487] Trial 2 finished with value: 0.5461538461538461 and parameters: {'lags': 4, 'max_depth': 5, 'learning_rate': 0.013798461445524306, 'subsample': 0.7187940702831268, 'colsample_bytree': 0.8770706207406898, 'reg_alpha': 1.3074087174683996e-06, 'reg_lambda': 4.0523515355269925e-05, 'num_boost_rounds': 1360}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:52:15,188] Trial 3 finished with value: 0.4906683480453973 and parameters: {'lags': 18, 'max_depth': 5, 'learning_rate': 0.0023948090957416276, 'subsample': 0.5880194412253327, 'colsample_bytree': 0.8016724653404349, 'reg_alpha': 2.175487541138761e-09, 'reg_lambda': 16.48791333327894, 'num_boost_rounds': 1051}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:52:32,697] Trial 4 finished with value: 0.5087011349306432 and parameters: {'lags': 10, 'max_depth': 6, 'learning_rate': 0.059840687993313636, 'subsample': 0.5174633498111607, 'colsample_bytree': 0.6689476831105898, 'reg_alpha': 4.368917956454396e-09, 'reg_lambda': 1.308946811062505, 'num_boost_rounds': 1486}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:52:36,338] Trial 5 finished with value: 0.5311475409836066 and parameters: {'lags': 2, 'max_depth': 5, 'learning_rate': 0.0350905445665603, 'subsample': 0.9864513235874872, 'colsample_bytree': 0.8334711019961488, 'reg_alpha': 7.552479608828925e-09, 'reg_lambda': 2.1048510080575938e-09, 'num_boost_rounds': 1039}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:52:36,421] Trial 6 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:36,611] Trial 7 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:36,809] Trial 8 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:37,230] Trial 9 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:44,902] Trial 10 finished with value: 0.5460277427490543 and parameters: {'lags': 8, 'max_depth': 3, 'learning_rate': 0.014836379433534573, 'subsample': 0.654182881261698, 'colsample_bytree': 0.6309735682081875, 'reg_alpha': 2.718399450581611e-06, 'reg_lambda': 0.0003846188890188795, 'num_boost_rounds': 1473}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:52:45,051] Trial 11 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:45,229] Trial 12 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:45,533] Trial 13 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:45,690] Trial 14 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:45,803] Trial 15 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:46,032] Trial 16 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:46,266] Trial 17 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:46,406] Trial 18 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:52:46,605] Trial 19 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:05,040] Trial 20 finished with value: 0.5092686002522068 and parameters: {'lags': 15, 'max_depth': 7, 'learning_rate': 0.0012177104104949797, 'subsample': 0.6131817292783416, 'colsample_bytree': 0.6457744218509318, 'reg_alpha': 2.8820492765055246e-05, 'reg_lambda': 3.038060904950554e-08, 'num_boost_rounds': 468}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:53:05,175] Trial 21 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:05,294] Trial 22 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:09,502] Trial 23 finished with value: 0.5144388398486759 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.036321589387983334, 'subsample': 0.7088398078571585, 'colsample_bytree': 0.7612539006548975, 'reg_alpha': 7.624261943325732e-08, 'reg_lambda': 1.614035979607079e-05, 'num_boost_rounds': 1487}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:53:09,631] Trial 24 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:09,745] Trial 25 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:09,972] Trial 26 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:10,072] Trial 27 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:10,219] Trial 28 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:10,368] Trial 29 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:10,475] Trial 30 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:10,784] Trial 31 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:11,022] Trial 32 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:11,371] Trial 33 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:46,829] Trial 34 finished with value: 0.5306431273644389 and parameters: {'lags': 19, 'max_depth': 6, 'learning_rate': 0.014528975712471569, 'subsample': 0.8046103211609698, 'colsample_bytree': 0.7907433079616492, 'reg_alpha': 5.2037769037734175e-09, 'reg_lambda': 8.285656351694151e-09, 'num_boost_rounds': 1037}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:53:47,182] Trial 35 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:47,324] Trial 36 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:47,526] Trial 37 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:47,748] Trial 38 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:47,935] Trial 39 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:48,041] Trial 40 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:48,345] Trial 41 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:48,762] Trial 42 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:49,210] Trial 43 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:49,542] Trial 44 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:49,758] Trial 45 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:50,225] Trial 46 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:50,462] Trial 47 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:50,609] Trial 48 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:50,941] Trial 49 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:51,376] Trial 50 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:56,475] Trial 51 finished with value: 0.501954602774275 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.048482192619544534, 'subsample': 0.7025023154033994, 'colsample_bytree': 0.7511029831143637, 'reg_alpha': 6.02248693403054e-08, 'reg_lambda': 5.441183857110287e-06, 'num_boost_rounds': 1431}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:53:56,575] Trial 52 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:56,705] Trial 53 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:53:56,819] Trial 54 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:02,986] Trial 55 finished with value: 0.5452080706179067 and parameters: {'lags': 5, 'max_depth': 4, 'learning_rate': 0.008960369178243189, 'subsample': 0.7846096276316427, 'colsample_bytree': 0.5402402729546301, 'reg_alpha': 1.4690869496775898e-06, 'reg_lambda': 0.0020176136854256803, 'num_boost_rounds': 1292}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:54:03,154] Trial 56 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:08,557] Trial 57 finished with value: 0.5368221941992434 and parameters: {'lags': 5, 'max_depth': 4, 'learning_rate': 0.002956819634282859, 'subsample': 0.7802622370289116, 'colsample_bytree': 0.5369570006673475, 'reg_alpha': 1.8490733868197024e-05, 'reg_lambda': 0.012373839655147014, 'num_boost_rounds': 1129}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:54:08,685] Trial 58 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:08,822] Trial 59 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:08,959] Trial 60 pruned. Trial was pruned at iteration 2.\n[I 2024-05-31 20:54:17,924] Trial 61 finished with value: 0.4889659520807061 and parameters: {'lags': 6, 'max_depth': 5, 'learning_rate': 0.006823692618891812, 'subsample': 0.8059630298256031, 'colsample_bytree': 0.5860764341438679, 'reg_alpha': 4.90001058383779e-07, 'reg_lambda': 0.06987675401470674, 'num_boost_rounds': 1201}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:54:18,092] Trial 62 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:18,218] Trial 63 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:18,329] Trial 64 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:18,489] Trial 65 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:18,633] Trial 66 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:18,800] Trial 67 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:18,985] Trial 68 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,123] Trial 69 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,374] Trial 70 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,480] Trial 71 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,599] Trial 72 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,699] Trial 73 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,841] Trial 74 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:19,968] Trial 75 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:20,095] Trial 76 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:20,207] Trial 77 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:20,587] Trial 78 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:20,725] Trial 79 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:20,945] Trial 80 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:21,316] Trial 81 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:21,651] Trial 82 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:52,041] Trial 83 finished with value: 0.5064943253467843 and parameters: {'lags': 16, 'max_depth': 6, 'learning_rate': 0.001240983287436723, 'subsample': 0.58002906003983, 'colsample_bytree': 0.7859174218918807, 'reg_alpha': 0.00014875134125463346, 'reg_lambda': 1.4710853976080728e-08, 'num_boost_rounds': 910}. Best is trial 2 with value: 0.5461538461538461.\n[I 2024-05-31 20:54:52,417] Trial 84 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:52,869] Trial 85 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:54,779] Trial 86 finished with value: 0.548108448928121 and parameters: {'lags': 2, 'max_depth': 10, 'learning_rate': 0.009586216436931347, 'subsample': 0.9709774146750181, 'colsample_bytree': 0.6374688016820524, 'reg_alpha': 0.0008411313745304683, 'reg_lambda': 2.6880992137328127e-08, 'num_boost_rounds': 198}. Best is trial 86 with value: 0.548108448928121.\n[I 2024-05-31 20:54:54,890] Trial 87 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:54:55,032] Trial 88 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:01,942] Trial 89 finished with value: 0.55359394703657 and parameters: {'lags': 2, 'max_depth': 10, 'learning_rate': 0.00938351904799828, 'subsample': 0.9782741665887742, 'colsample_bytree': 0.5755705801349024, 'reg_alpha': 2.665240814383687e-09, 'reg_lambda': 6.461516198258842e-05, 'num_boost_rounds': 778}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:55:08,735] Trial 90 finished with value: 0.5487389659520807 and parameters: {'lags': 2, 'max_depth': 10, 'learning_rate': 0.009595783863803666, 'subsample': 0.9757368323893889, 'colsample_bytree': 0.5830511755219482, 'reg_alpha': 5.598536776830718e-10, 'reg_lambda': 1.1305876108484547e-09, 'num_boost_rounds': 967}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:55:08,860] Trial 91 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:09,042] Trial 92 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:09,166] Trial 93 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:09,300] Trial 94 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:09,490] Trial 95 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:09,616] Trial 96 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:09,898] Trial 97 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:10,090] Trial 98 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:10,300] Trial 99 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:10,550] Trial 100 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:10,710] Trial 101 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:10,828] Trial 102 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:10,945] Trial 103 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,120] Trial 104 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,336] Trial 105 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,453] Trial 106 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,580] Trial 107 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,712] Trial 108 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,831] Trial 109 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:11,951] Trial 110 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:12,309] Trial 111 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:26,962] Trial 112 finished with value: 0.505296343001261 and parameters: {'lags': 17, 'max_depth': 9, 'learning_rate': 0.011136784858424406, 'subsample': 0.9698099181249945, 'colsample_bytree': 0.6601781485082453, 'reg_alpha': 3.906240393566474e-05, 'reg_lambda': 1.00320033300129e-08, 'num_boost_rounds': 203}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:55:27,215] Trial 113 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:27,464] Trial 114 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:27,890] Trial 115 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:28,201] Trial 116 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:28,535] Trial 117 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:28,736] Trial 118 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:28,894] Trial 119 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:29,519] Trial 120 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:30,199] Trial 121 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:30,404] Trial 122 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:30,692] Trial 123 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:30,913] Trial 124 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:31,043] Trial 125 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:31,334] Trial 126 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:31,499] Trial 127 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:31,798] Trial 128 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:32,119] Trial 129 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:32,256] Trial 130 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:32,579] Trial 131 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:32,901] Trial 132 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:33,261] Trial 133 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:33,574] Trial 134 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:33,871] Trial 135 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:33,997] Trial 136 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:34,169] Trial 137 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:34,365] Trial 138 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:34,493] Trial 139 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:34,623] Trial 140 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:35,149] Trial 141 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:44,626] Trial 142 finished with value: 0.5297604035308954 and parameters: {'lags': 16, 'max_depth': 9, 'learning_rate': 0.010224784553421788, 'subsample': 0.6204653986973785, 'colsample_bytree': 0.6614874700692855, 'reg_alpha': 3.807795303437778e-05, 'reg_lambda': 9.293599403058644e-09, 'num_boost_rounds': 147}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:55:44,971] Trial 143 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:45,454] Trial 144 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:53,633] Trial 145 finished with value: 0.5319041614123581 and parameters: {'lags': 16, 'max_depth': 9, 'learning_rate': 0.009976902597424467, 'subsample': 0.6187353283879737, 'colsample_bytree': 0.6400345777110376, 'reg_alpha': 3.1748814187877306e-09, 'reg_lambda': 2.7411825635324402e-08, 'num_boost_rounds': 131}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:55:53,765] Trial 146 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:54,107] Trial 147 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:54,577] Trial 148 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:55:55,047] Trial 149 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:03,005] Trial 150 finished with value: 0.526796973518285 and parameters: {'lags': 17, 'max_depth': 9, 'learning_rate': 0.00745373058893199, 'subsample': 0.5972985972080038, 'colsample_bytree': 0.6230226224724058, 'reg_alpha': 1.5781776868618516e-09, 'reg_lambda': 6.372134028017799e-05, 'num_boost_rounds': 103}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:56:03,465] Trial 151 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:03,941] Trial 152 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:04,364] Trial 153 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:04,816] Trial 154 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:05,403] Trial 155 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:05,923] Trial 156 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:06,392] Trial 157 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:06,536] Trial 158 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:06,688] Trial 159 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:06,978] Trial 160 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:07,303] Trial 161 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:56:07,687] Trial 162 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:16,424] Trial 163 finished with value: 0.5139974779319042 and parameters: {'lags': 16, 'max_depth': 8, 'learning_rate': 0.011030004230681581, 'subsample': 0.6077650159597072, 'colsample_bytree': 0.9842253324843935, 'reg_alpha': 0.00032349104657550135, 'reg_lambda': 1.2500282037944479e-08, 'num_boost_rounds': 1498}. Best is trial 89 with value: 0.55359394703657.\n[I 2024-05-31 20:57:16,827] Trial 164 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:17,201] Trial 165 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:17,482] Trial 166 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:17,627] Trial 167 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:18,072] Trial 168 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:18,687] Trial 169 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:23,223] Trial 170 finished with value: 0.5622320302648172 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.008815389011970412, 'subsample': 0.6290678121728437, 'colsample_bytree': 0.912328634495344, 'reg_alpha': 3.127573736385257e-07, 'reg_lambda': 5.209060154782433e-09, 'num_boost_rounds': 1119}. Best is trial 170 with value: 0.5622320302648172.\n[I 2024-05-31 20:57:27,726] Trial 171 finished with value: 0.5596469104665827 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.008877978575241745, 'subsample': 0.6327318006303958, 'colsample_bytree': 0.8500110399765174, 'reg_alpha': 7.733558479723786e-07, 'reg_lambda': 4.692421360235513e-09, 'num_boost_rounds': 1121}. Best is trial 170 with value: 0.5622320302648172.\n[I 2024-05-31 20:57:27,900] Trial 172 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:32,352] Trial 173 finished with value: 0.5619798234552332 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.007365703053028056, 'subsample': 0.6305308608289399, 'colsample_bytree': 0.888214726611087, 'reg_alpha': 6.367601129739694e-07, 'reg_lambda': 1.7652472154729355e-09, 'num_boost_rounds': 1111}. Best is trial 170 with value: 0.5622320302648172.\n[I 2024-05-31 20:57:37,921] Trial 174 finished with value: 0.5658259773013872 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.006224669870687056, 'subsample': 0.6277115178012963, 'colsample_bytree': 0.8903742156303042, 'reg_alpha': 7.381602352281778e-07, 'reg_lambda': 2.2402948498679317e-09, 'num_boost_rounds': 1104}. Best is trial 174 with value: 0.5658259773013872.\n[I 2024-05-31 20:57:42,339] Trial 175 finished with value: 0.5608448928121059 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.007373596345620487, 'subsample': 0.6245688662482518, 'colsample_bytree': 0.8889981146571844, 'reg_alpha': 1.764252044177217e-07, 'reg_lambda': 2.066057808920593e-09, 'num_boost_rounds': 1095}. Best is trial 174 with value: 0.5658259773013872.\n[I 2024-05-31 20:57:42,481] Trial 176 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:42,634] Trial 177 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:57:46,893] Trial 178 finished with value: 0.5741488020176545 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004840659003692007, 'subsample': 0.6245165493199292, 'colsample_bytree': 0.8857750423130878, 'reg_alpha': 1.1830462209405324e-06, 'reg_lambda': 3.0010747705947087e-09, 'num_boost_rounds': 1054}. Best is trial 178 with value: 0.5741488020176545.\n[I 2024-05-31 20:57:51,521] Trial 179 finished with value: 0.5713114754098361 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.00518274394344178, 'subsample': 0.6191870594364021, 'colsample_bytree': 0.8914856427285002, 'reg_alpha': 1.0752202966292936e-06, 'reg_lambda': 1.4433319064903722e-09, 'num_boost_rounds': 1147}. Best is trial 178 with value: 0.5741488020176545.\n[I 2024-05-31 20:57:56,176] Trial 180 finished with value: 0.5697982345523329 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0060857994052184415, 'subsample': 0.6270014938944257, 'colsample_bytree': 0.8933326493040521, 'reg_alpha': 9.814254288813223e-07, 'reg_lambda': 1.1785731091590724e-10, 'num_boost_rounds': 1137}. Best is trial 178 with value: 0.5741488020176545.\n[I 2024-05-31 20:58:00,751] Trial 181 finished with value: 0.5671500630517025 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.00506073640317432, 'subsample': 0.6261771591086083, 'colsample_bytree': 0.8920099251838846, 'reg_alpha': 7.884175907975156e-07, 'reg_lambda': 1.9534974890857318e-10, 'num_boost_rounds': 1134}. Best is trial 178 with value: 0.5741488020176545.\n[I 2024-05-31 20:58:05,126] Trial 182 finished with value: 0.5817150063051703 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004634997618335966, 'subsample': 0.6287999888798684, 'colsample_bytree': 0.8800322670436729, 'reg_alpha': 9.761293557210888e-07, 'reg_lambda': 1.190835946717516e-10, 'num_boost_rounds': 1152}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:10,876] Trial 183 finished with value: 0.5680958385876418 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.00531989455132743, 'subsample': 0.6296494845451979, 'colsample_bytree': 0.8912515986651396, 'reg_alpha': 1.053834359169914e-06, 'reg_lambda': 1.3121767181120834e-10, 'num_boost_rounds': 1133}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:15,607] Trial 184 finished with value: 0.580390920554855 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0046089193625335175, 'subsample': 0.6317473488581882, 'colsample_bytree': 0.8935635326730775, 'reg_alpha': 1.3350189384052583e-06, 'reg_lambda': 1.153077818179966e-10, 'num_boost_rounds': 1149}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:15,743] Trial 185 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:58:15,896] Trial 186 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:58:20,840] Trial 187 finished with value: 0.5755359394703657 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.005326915103256831, 'subsample': 0.6310095555103838, 'colsample_bytree': 0.9118176528914589, 'reg_alpha': 4.354180771138683e-07, 'reg_lambda': 3.5188869044844694e-10, 'num_boost_rounds': 1219}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:20,981] Trial 188 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:58:21,123] Trial 189 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:58:21,269] Trial 190 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:58:21,419] Trial 191 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:58:25,944] Trial 192 finished with value: 0.5656998738965953 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0043627788963625045, 'subsample': 0.618375403668719, 'colsample_bytree': 0.8876679290999084, 'reg_alpha': 3.1358534118106407e-07, 'reg_lambda': 2.6886978384115635e-10, 'num_boost_rounds': 1112}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:30,269] Trial 193 finished with value: 0.5704287515762927 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.005296229174851516, 'subsample': 0.6131156985851521, 'colsample_bytree': 0.8677838218630901, 'reg_alpha': 2.3118054273257785e-07, 'reg_lambda': 2.827024349842976e-10, 'num_boost_rounds': 1114}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:34,670] Trial 194 finished with value: 0.5697982345523329 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0045184997825932745, 'subsample': 0.6144344589398884, 'colsample_bytree': 0.8658629690382784, 'reg_alpha': 2.662992646437114e-07, 'reg_lambda': 2.9909360780316644e-10, 'num_boost_rounds': 1108}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:40,283] Trial 195 finished with value: 0.5688524590163935 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004409343275570297, 'subsample': 0.6152745174399, 'colsample_bytree': 0.8666583984523728, 'reg_alpha': 2.3532006947463542e-07, 'reg_lambda': 2.9107428204662195e-10, 'num_boost_rounds': 1115}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:44,822] Trial 196 finished with value: 0.5686002522068097 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004643067789578831, 'subsample': 0.6125468903278606, 'colsample_bytree': 0.88954127518774, 'reg_alpha': 2.0610095029438564e-07, 'reg_lambda': 1.0332965538504568e-10, 'num_boost_rounds': 1108}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:49,427] Trial 197 finished with value: 0.5763556116015132 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004360313193601474, 'subsample': 0.6172284507651077, 'colsample_bytree': 0.865737128684549, 'reg_alpha': 2.0956630494986442e-07, 'reg_lambda': 2.991289520157286e-10, 'num_boost_rounds': 1108}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:53,708] Trial 198 finished with value: 0.5684110970996217 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004348448277353807, 'subsample': 0.6131956321216411, 'colsample_bytree': 0.86738965181293, 'reg_alpha': 1.8629543590336393e-07, 'reg_lambda': 1.0556057149128621e-10, 'num_boost_rounds': 1104}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:58:58,158] Trial 199 finished with value: 0.566078184110971 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004378346423973847, 'subsample': 0.6162031760227797, 'colsample_bytree': 0.8703921346883932, 'reg_alpha': 1.8604213792097904e-07, 'reg_lambda': 1.0111160590412107e-10, 'num_boost_rounds': 1099}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:02,498] Trial 200 finished with value: 0.5609079445145019 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004555101988582631, 'subsample': 0.6120985203987567, 'colsample_bytree': 0.8661485719205897, 'reg_alpha': 1.671657855193609e-07, 'reg_lambda': 2.6400827415083775e-10, 'num_boost_rounds': 1064}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:06,717] Trial 201 finished with value: 0.5699873896595209 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004485732271589557, 'subsample': 0.6163076160691109, 'colsample_bytree': 0.8670461317348105, 'reg_alpha': 1.479268604977733e-07, 'reg_lambda': 2.58386645892006e-10, 'num_boost_rounds': 1064}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:12,264] Trial 202 finished with value: 0.5602143757881463 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004447313914958717, 'subsample': 0.6120502335680859, 'colsample_bytree': 0.8664957052711659, 'reg_alpha': 2.830705159947589e-07, 'reg_lambda': 1.0792147979723903e-10, 'num_boost_rounds': 1065}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:16,910] Trial 203 finished with value: 0.5655737704918031 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.00409088243466668, 'subsample': 0.6126876613830011, 'colsample_bytree': 0.8708745228551322, 'reg_alpha': 1.2603084207731561e-07, 'reg_lambda': 2.49327751490367e-10, 'num_boost_rounds': 1170}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:17,059] Trial 204 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:21,730] Trial 205 finished with value: 0.5709331651954603 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.00400627329285632, 'subsample': 0.6166542413035063, 'colsample_bytree': 0.8976812031602498, 'reg_alpha': 3.464517184724397e-07, 'reg_lambda': 1.9085031437937538e-10, 'num_boost_rounds': 1172}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:26,603] Trial 206 finished with value: 0.5642496847414881 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004044466459761734, 'subsample': 0.6169774213147514, 'colsample_bytree': 0.8995635377905851, 'reg_alpha': 3.5128771341085643e-07, 'reg_lambda': 1.8974120154212455e-10, 'num_boost_rounds': 1169}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:26,748] Trial 207 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:26,988] Trial 208 pruned. Trial was pruned at iteration 28.\n[I 2024-05-31 20:59:27,141] Trial 209 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:27,281] Trial 210 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:27,438] Trial 211 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:31,994] Trial 212 finished with value: 0.5687894073139975 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.005415768499497596, 'subsample': 0.6137515484515061, 'colsample_bytree': 0.8593473945814745, 'reg_alpha': 3.8564794437571403e-07, 'reg_lambda': 1.0130452106027954e-10, 'num_boost_rounds': 1142}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:32,152] Trial 213 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:36,544] Trial 214 finished with value: 0.5621059268600253 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0042594812977075295, 'subsample': 0.6121952409686496, 'colsample_bytree': 0.8690051413461168, 'reg_alpha': 1.1337007808580934e-07, 'reg_lambda': 1.8978367982489716e-10, 'num_boost_rounds': 1150}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:42,104] Trial 215 finished with value: 0.5684741488020176 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004954834967973938, 'subsample': 0.615195494298333, 'colsample_bytree': 0.8823009655111321, 'reg_alpha': 2.0135964435067874e-07, 'reg_lambda': 6.711816925580849e-10, 'num_boost_rounds': 1174}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:42,258] Trial 216 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:42,397] Trial 217 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:42,542] Trial 218 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:42,698] Trial 219 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:42,826] Trial 220 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:42,980] Trial 221 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:47,493] Trial 222 finished with value: 0.5759773013871374 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.005127573155925416, 'subsample': 0.6139231293743852, 'colsample_bytree': 0.8607714807090324, 'reg_alpha': 2.2981287555329883e-07, 'reg_lambda': 1.0303366286043323e-10, 'num_boost_rounds': 1142}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:47,729] Trial 223 pruned. Trial was pruned at iteration 26.\n[I 2024-05-31 20:59:47,874] Trial 224 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:48,010] Trial 225 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:48,155] Trial 226 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:48,306] Trial 227 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:48,460] Trial 228 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:48,597] Trial 229 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:48,723] Trial 230 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:53,535] Trial 231 finished with value: 0.573076923076923 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004117934631292866, 'subsample': 0.6161835041250437, 'colsample_bytree': 0.8968062598129203, 'reg_alpha': 3.398137561939506e-07, 'reg_lambda': 1.8303278669598845e-10, 'num_boost_rounds': 1219}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 20:59:53,691] Trial 232 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:53,844] Trial 233 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:54,001] Trial 234 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:54,130] Trial 235 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:54,277] Trial 236 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:54,432] Trial 237 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 20:59:54,578] Trial 238 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:54,714] Trial 239 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 20:59:58,086] Trial 240 finished with value: 0.5698612862547289 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004258352031860571, 'subsample': 0.6333725759026173, 'colsample_bytree': 0.8478523454501778, 'reg_alpha': 1.7276961707455247e-07, 'reg_lambda': 4.739615569992579e-10, 'num_boost_rounds': 1123}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:01,477] Trial 241 finished with value: 0.5656368221941993 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.00419254433362509, 'subsample': 0.6251366544395046, 'colsample_bytree': 0.8488486941580577, 'reg_alpha': 1.5502970154313773e-07, 'reg_lambda': 4.3821044386292863e-10, 'num_boost_rounds': 1124}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:01,610] Trial 242 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:04,790] Trial 243 finished with value: 0.5692938209331653 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004339178066099981, 'subsample': 0.6252331279104824, 'colsample_bytree': 0.8461666696292708, 'reg_alpha': 7.041804922341832e-07, 'reg_lambda': 4.334932901542296e-10, 'num_boost_rounds': 1073}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:08,099] Trial 244 finished with value: 0.5600882723833543 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.005390063163703204, 'subsample': 0.6236561644895388, 'colsample_bytree': 0.8633761526409891, 'reg_alpha': 6.177865356109005e-07, 'reg_lambda': 1.0417184192342253e-09, 'num_boost_rounds': 1071}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:11,384] Trial 245 finished with value: 0.5583228247162673 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004864271516615578, 'subsample': 0.6339347711931188, 'colsample_bytree': 0.8441302101084869, 'reg_alpha': 3.6287383228331987e-07, 'reg_lambda': 3.456006424167299e-10, 'num_boost_rounds': 1100}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:11,537] Trial 246 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:11,677] Trial 247 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:16,138] Trial 248 finished with value: 0.5733921815889029 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.003692361230770042, 'subsample': 0.6182799984400066, 'colsample_bytree': 0.8927457309750221, 'reg_alpha': 2.973921109437905e-07, 'reg_lambda': 5.42844662797213e-10, 'num_boost_rounds': 1081}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:16,269] Trial 249 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:16,418] Trial 250 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:16,572] Trial 251 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:16,702] Trial 252 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:16,863] Trial 253 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:17,016] Trial 254 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:17,171] Trial 255 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:17,319] Trial 256 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:17,455] Trial 257 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:20,821] Trial 258 finished with value: 0.564312736443884 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004203389532507804, 'subsample': 0.6261670378017262, 'colsample_bytree': 0.8958343977733866, 'reg_alpha': 9.210050312748045e-07, 'reg_lambda': 2.3434747066827934e-10, 'num_boost_rounds': 1083}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:21,052] Trial 259 pruned. Trial was pruned at iteration 25.\n[I 2024-05-31 21:00:21,199] Trial 260 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:21,330] Trial 261 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:21,513] Trial 262 pruned. Trial was pruned at iteration 14.\n[I 2024-05-31 21:00:21,663] Trial 263 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:21,799] Trial 264 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:21,925] Trial 265 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:26,382] Trial 266 finished with value: 0.5725725094577554 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0048818730172509655, 'subsample': 0.6158520916699115, 'colsample_bytree': 0.8562884788283451, 'reg_alpha': 4.725500565424295e-07, 'reg_lambda': 3.057428128683843e-10, 'num_boost_rounds': 1113}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:31,068] Trial 267 finished with value: 0.5677805800756621 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.003888707211908234, 'subsample': 0.6116623910947194, 'colsample_bytree': 0.8537590078677969, 'reg_alpha': 1.6600935855735278e-07, 'reg_lambda': 3.0392627578461726e-10, 'num_boost_rounds': 1168}. Best is trial 182 with value: 0.5817150063051703.\n[I 2024-05-31 21:00:31,202] Trial 268 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:31,360] Trial 269 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:31,530] Trial 270 pruned. Trial was pruned at iteration 8.\n[I 2024-05-31 21:00:31,688] Trial 271 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:31,829] Trial 272 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:31,960] Trial 273 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:32,125] Trial 274 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:32,268] Trial 275 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:32,400] Trial 276 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:32,557] Trial 277 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:32,702] Trial 278 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:32,855] Trial 279 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:32,984] Trial 280 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:33,138] Trial 281 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:33,280] Trial 282 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:33,412] Trial 283 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:33,553] Trial 284 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:33,732] Trial 285 pruned. Trial was pruned at iteration 8.\n[I 2024-05-31 21:00:33,888] Trial 286 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:37,417] Trial 287 finished with value: 0.5831651954602775 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.003907836559798272, 'subsample': 0.6320167444173408, 'colsample_bytree': 0.9110180398493726, 'reg_alpha': 5.779611064987497e-07, 'reg_lambda': 4.738541273305722e-10, 'num_boost_rounds': 1142}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:00:37,554] Trial 288 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:37,689] Trial 289 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:37,818] Trial 290 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:37,973] Trial 291 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:41,390] Trial 292 finished with value: 0.5742118537200506 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004000725353743675, 'subsample': 0.6317096600995545, 'colsample_bytree': 0.834072613725727, 'reg_alpha': 1.696679095096854e-07, 'reg_lambda': 2.8631245087835933e-10, 'num_boost_rounds': 1146}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:00:44,702] Trial 293 finished with value: 0.5614754098360656 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.005856984487433664, 'subsample': 0.641317145409479, 'colsample_bytree': 0.832168950932575, 'reg_alpha': 1.31920360341286e-06, 'reg_lambda': 1.033307984327611e-10, 'num_boost_rounds': 1060}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:00:44,840] Trial 294 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:45,052] Trial 295 pruned. Trial was pruned at iteration 28.\n[I 2024-05-31 21:00:45,196] Trial 296 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:45,342] Trial 297 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:45,502] Trial 298 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:45,631] Trial 299 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:45,792] Trial 300 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:45,942] Trial 301 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:46,073] Trial 302 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:46,225] Trial 303 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:46,390] Trial 304 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:46,527] Trial 305 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:50,269] Trial 306 finished with value: 0.5745901639344262 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004818482921387882, 'subsample': 0.6329775689235076, 'colsample_bytree': 0.8838236722713755, 'reg_alpha': 1.7271131678364075e-06, 'reg_lambda': 1.5086255204016356e-10, 'num_boost_rounds': 1186}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:00:50,403] Trial 307 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:50,538] Trial 308 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:50,675] Trial 309 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:50,808] Trial 310 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:51,015] Trial 311 pruned. Trial was pruned at iteration 16.\n[I 2024-05-31 21:00:51,229] Trial 312 pruned. Trial was pruned at iteration 28.\n[I 2024-05-31 21:00:51,397] Trial 313 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:51,555] Trial 314 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:51,690] Trial 315 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:51,840] Trial 316 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:51,999] Trial 317 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:55,726] Trial 318 finished with value: 0.567780580075662 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004710837017043754, 'subsample': 0.6228502065701703, 'colsample_bytree': 0.8382945748882044, 'reg_alpha': 4.897949099283962e-07, 'reg_lambda': 1.7334227561271366e-10, 'num_boost_rounds': 1220}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:00:55,875] Trial 319 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:56,031] Trial 320 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:56,179] Trial 321 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:00:59,660] Trial 322 finished with value: 0.5576292559899116 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.006393816456210652, 'subsample': 0.6319021397549724, 'colsample_bytree': 0.8472278187640526, 'reg_alpha': 8.732174813875759e-07, 'reg_lambda': 2.5173396932430906e-10, 'num_boost_rounds': 1167}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:00:59,819] Trial 323 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:00:59,976] Trial 324 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:00,110] Trial 325 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:00,263] Trial 326 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:00,411] Trial 327 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:04,164] Trial 328 finished with value: 0.5667717528373266 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.003729774545571872, 'subsample': 0.6266224718294071, 'colsample_bytree': 0.831171833264232, 'reg_alpha': 1.4129999556140654e-06, 'reg_lambda': 3.971508524338127e-10, 'num_boost_rounds': 1243}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:04,307] Trial 329 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:04,443] Trial 330 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:04,585] Trial 331 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:04,758] Trial 332 pruned. Trial was pruned at iteration 8.\n[I 2024-05-31 21:01:04,912] Trial 333 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:05,078] Trial 334 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:05,233] Trial 335 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:05,384] Trial 336 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:05,530] Trial 337 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:05,671] Trial 338 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:05,839] Trial 339 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:05,973] Trial 340 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:06,126] Trial 341 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:06,271] Trial 342 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:06,417] Trial 343 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:06,554] Trial 344 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:06,713] Trial 345 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:06,881] Trial 346 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:07,018] Trial 347 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:07,226] Trial 348 pruned. Trial was pruned at iteration 16.\n[I 2024-05-31 21:01:07,704] Trial 349 pruned. Trial was pruned at iteration 53.\n[I 2024-05-31 21:01:07,843] Trial 350 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:07,989] Trial 351 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:08,155] Trial 352 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:08,313] Trial 353 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:08,452] Trial 354 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:08,599] Trial 355 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:08,767] Trial 356 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:09,042] Trial 357 pruned. Trial was pruned at iteration 49.\n[I 2024-05-31 21:01:09,203] Trial 358 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:09,376] Trial 359 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:09,517] Trial 360 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:13,914] Trial 361 finished with value: 0.5716897856242118 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.00506597125492803, 'subsample': 0.6169906658197404, 'colsample_bytree': 0.8945978285465968, 'reg_alpha': 3.8610152536396404e-07, 'reg_lambda': 3.729917380667487e-10, 'num_boost_rounds': 1110}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:18,816] Trial 362 finished with value: 0.5728877679697352 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.006420722493181244, 'subsample': 0.6330675404210284, 'colsample_bytree': 0.9038661789327315, 'reg_alpha': 4.5778077392316873e-07, 'reg_lambda': 6.372839591080654e-10, 'num_boost_rounds': 1185}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:18,984] Trial 363 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:19,181] Trial 364 pruned. Trial was pruned at iteration 12.\n[I 2024-05-31 21:01:19,324] Trial 365 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:19,484] Trial 366 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:19,680] Trial 367 pruned. Trial was pruned at iteration 13.\n[I 2024-05-31 21:01:23,281] Trial 368 finished with value: 0.5672131147540984 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.005189042979194305, 'subsample': 0.6226284654000174, 'colsample_bytree': 0.8920756845156327, 'reg_alpha': 7.537914416217554e-07, 'reg_lambda': 2.2741299168091574e-10, 'num_boost_rounds': 1154}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:23,509] Trial 369 pruned. Trial was pruned at iteration 14.\n[I 2024-05-31 21:01:23,670] Trial 370 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:23,809] Trial 371 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:23,956] Trial 372 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:29,080] Trial 373 finished with value: 0.5738965952080706 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0037376134883190916, 'subsample': 0.6121306093438866, 'colsample_bytree': 0.9012019904008, 'reg_alpha': 0.02933688736411748, 'reg_lambda': 3.4852867632383885e-10, 'num_boost_rounds': 1217}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:29,219] Trial 374 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:29,379] Trial 375 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:29,547] Trial 376 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:29,716] Trial 377 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:29,857] Trial 378 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:30,018] Trial 379 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:30,166] Trial 380 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:30,307] Trial 381 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:30,472] Trial 382 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:30,633] Trial 383 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:30,779] Trial 384 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:30,950] Trial 385 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:31,100] Trial 386 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:31,249] Trial 387 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:31,404] Trial 388 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:31,637] Trial 389 pruned. Trial was pruned at iteration 16.\n[I 2024-05-31 21:01:31,797] Trial 390 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:31,941] Trial 391 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:32,110] Trial 392 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:32,390] Trial 393 pruned. Trial was pruned at iteration 49.\n[I 2024-05-31 21:01:32,539] Trial 394 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:32,711] Trial 395 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:32,876] Trial 396 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:33,028] Trial 397 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:37,968] Trial 398 finished with value: 0.558953341740227 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.004360245840103036, 'subsample': 0.6178738914664731, 'colsample_bytree': 0.8838652361659229, 'reg_alpha': 7.023376218982477e-08, 'reg_lambda': 2.850995090501444e-09, 'num_boost_rounds': 1185}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:38,111] Trial 399 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:38,283] Trial 400 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:38,441] Trial 401 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:38,600] Trial 402 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:38,740] Trial 403 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:38,909] Trial 404 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:39,104] Trial 405 pruned. Trial was pruned at iteration 12.\n[I 2024-05-31 21:01:39,265] Trial 406 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:39,409] Trial 407 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:39,584] Trial 408 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:39,730] Trial 409 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:39,884] Trial 410 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:40,051] Trial 411 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:01:40,213] Trial 412 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:44,179] Trial 413 finished with value: 0.5686002522068097 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.004939245835950606, 'subsample': 0.6059702935886054, 'colsample_bytree': 0.9480231762234494, 'reg_alpha': 5.568218538392643e-08, 'reg_lambda': 3.6725028021293584e-10, 'num_boost_rounds': 1214}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:44,334] Trial 414 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:44,497] Trial 415 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:44,642] Trial 416 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:49,082] Trial 417 finished with value: 0.5630517023959647 and parameters: {'lags': 3, 'max_depth': 4, 'learning_rate': 0.0038397485842575386, 'subsample': 0.6121315586886121, 'colsample_bytree': 0.8902378097412343, 'reg_alpha': 5.087314727608549e-07, 'reg_lambda': 6.454931204164634e-10, 'num_boost_rounds': 1082}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:49,227] Trial 418 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:49,429] Trial 419 pruned. Trial was pruned at iteration 12.\n[I 2024-05-31 21:01:49,597] Trial 420 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:49,753] Trial 421 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:53,289] Trial 422 finished with value: 0.5735182849936948 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0038804470120965195, 'subsample': 0.6059586925948769, 'colsample_bytree': 0.8761765529809418, 'reg_alpha': 3.376314198193446e-07, 'reg_lambda': 1.0158331226626826e-10, 'num_boost_rounds': 1146}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:53,434] Trial 423 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:53,579] Trial 424 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:57,154] Trial 425 finished with value: 0.575031525851198 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0027899983030592918, 'subsample': 0.6296880230850394, 'colsample_bytree': 0.8744272328940288, 'reg_alpha': 5.873297401459121e-07, 'reg_lambda': 3.679409123630473e-10, 'num_boost_rounds': 1133}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:01:57,305] Trial 426 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:57,559] Trial 427 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:01:57,838] Trial 428 pruned. Trial was pruned at iteration 49.\n[I 2024-05-31 21:01:57,987] Trial 429 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:01,470] Trial 430 finished with value: 0.5777427490542244 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0030865925918461394, 'subsample': 0.6250233230183533, 'colsample_bytree': 0.8733229583363944, 'reg_alpha': 4.242653554923553e-07, 'reg_lambda': 1.0089239728119608e-10, 'num_boost_rounds': 1126}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:05,192] Trial 431 finished with value: 0.5779319041614123 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0029305876147135827, 'subsample': 0.630847478063828, 'colsample_bytree': 0.8777882864603437, 'reg_alpha': 4.447948297516684e-07, 'reg_lambda': 1.0186222432574183e-10, 'num_boost_rounds': 1165}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:05,347] Trial 432 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:08,987] Trial 433 finished with value: 0.5594577553593948 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.002927262346109264, 'subsample': 0.6642605839479081, 'colsample_bytree': 0.8866559475271693, 'reg_alpha': 1.1632949425887938e-06, 'reg_lambda': 1.0245468420394586e-10, 'num_boost_rounds': 1154}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:09,132] Trial 434 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:12,758] Trial 435 finished with value: 0.5651954602774275 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0032612627621102044, 'subsample': 0.6295290379531854, 'colsample_bytree': 0.8806836734865862, 'reg_alpha': 8.084122609931379e-07, 'reg_lambda': 1.0269189313445204e-10, 'num_boost_rounds': 1157}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:12,900] Trial 436 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:16,517] Trial 437 finished with value: 0.5780580075662043 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0025819095574256636, 'subsample': 0.6237271477959235, 'colsample_bytree': 0.8935293139394784, 'reg_alpha': 1.6303725788026812e-07, 'reg_lambda': 1.817043123461283e-10, 'num_boost_rounds': 1127}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:19,984] Trial 438 finished with value: 0.5792559899117276 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.0028839729877854397, 'subsample': 0.6220186833278408, 'colsample_bytree': 0.8730171878331102, 'reg_alpha': 5.0314895775288086e-08, 'reg_lambda': 1.9552282191162116e-10, 'num_boost_rounds': 1127}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:20,130] Trial 439 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:24,191] Trial 440 finished with value: 0.5795712484237074 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.002922008356103449, 'subsample': 0.6224915490946503, 'colsample_bytree': 0.887281321969704, 'reg_alpha': 5.863706730072978e-08, 'reg_lambda': 2.1676222844833776e-10, 'num_boost_rounds': 1287}. Best is trial 287 with value: 0.5831651954602775.\n[I 2024-05-31 21:02:24,341] Trial 441 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:28,602] Trial 442 finished with value: 0.5854350567465321 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.002511398254446226, 'subsample': 0.6217853315920165, 'colsample_bytree': 0.8865506028166856, 'reg_alpha': 7.115997216732502e-08, 'reg_lambda': 1.626444748885696e-10, 'num_boost_rounds': 1321}. Best is trial 442 with value: 0.5854350567465321.\n[I 2024-05-31 21:02:28,752] Trial 443 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:32,762] Trial 444 finished with value: 0.5825977301387137 and parameters: {'lags': 2, 'max_depth': 4, 'learning_rate': 0.002381293245052894, 'subsample': 0.624209071592035, 'colsample_bytree': 0.901433282975492, 'reg_alpha': 2.5827412699810894e-08, 'reg_lambda': 1.0449177332131814e-10, 'num_boost_rounds': 1311}. Best is trial 442 with value: 0.5854350567465321.\n[I 2024-05-31 21:02:35,939] Trial 445 finished with value: 0.5776166456494326 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.002297128840663006, 'subsample': 0.6272641530785954, 'colsample_bytree': 0.9042031147635575, 'reg_alpha': 2.6823646308210834e-08, 'reg_lambda': 1.4466193352711502e-10, 'num_boost_rounds': 1267}. Best is trial 442 with value: 0.5854350567465321.\n[I 2024-05-31 21:02:36,085] Trial 446 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:36,235] Trial 447 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:36,388] Trial 448 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:39,529] Trial 449 finished with value: 0.5813997477931904 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.002227203819100962, 'subsample': 0.626718404205504, 'colsample_bytree': 0.9117933048785294, 'reg_alpha': 1.308893783973423e-08, 'reg_lambda': 1.7105370842753335e-10, 'num_boost_rounds': 1289}. Best is trial 442 with value: 0.5854350567465321.\n[I 2024-05-31 21:02:39,683] Trial 450 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:39,834] Trial 451 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:39,978] Trial 452 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:43,225] Trial 453 finished with value: 0.5834804539722573 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0027785161990690178, 'subsample': 0.6269536864675819, 'colsample_bytree': 0.9234842228948483, 'reg_alpha': 3.871718238644018e-08, 'reg_lambda': 2.2508745600653436e-10, 'num_boost_rounds': 1330}. Best is trial 442 with value: 0.5854350567465321.\n[I 2024-05-31 21:02:43,376] Trial 454 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:43,523] Trial 455 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:43,675] Trial 456 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:43,824] Trial 457 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:43,986] Trial 458 pruned. Trial was pruned at iteration 5.\n[I 2024-05-31 21:02:44,135] Trial 459 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:47,565] Trial 460 finished with value: 0.585813366960908 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0022991876489173208, 'subsample': 0.6236475233008044, 'colsample_bytree': 0.9175944156698146, 'reg_alpha': 4.39077497806674e-08, 'reg_lambda': 1.518648405577074e-10, 'num_boost_rounds': 1385}. Best is trial 460 with value: 0.585813366960908.\n[I 2024-05-31 21:02:47,718] Trial 461 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:47,874] Trial 462 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:48,021] Trial 463 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:48,173] Trial 464 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:51,328] Trial 465 finished with value: 0.5880201765447667 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0016860891609448022, 'subsample': 0.6237949350998843, 'colsample_bytree': 0.9152596322116155, 'reg_alpha': 4.697205380819707e-08, 'reg_lambda': 1.0464298219519939e-10, 'num_boost_rounds': 1280}. Best is trial 465 with value: 0.5880201765447667.\n[I 2024-05-31 21:02:51,479] Trial 466 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:51,632] Trial 467 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:51,785] Trial 468 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:55,079] Trial 469 finished with value: 0.591046658259773 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.002464277615215694, 'subsample': 0.6221757053045096, 'colsample_bytree': 0.9182853446425219, 'reg_alpha': 3.320996202136488e-08, 'reg_lambda': 1.0244696163309044e-10, 'num_boost_rounds': 1322}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:02:55,254] Trial 470 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:55,413] Trial 471 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:55,568] Trial 472 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:55,725] Trial 473 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:55,989] Trial 474 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:56,144] Trial 475 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:56,308] Trial 476 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:59,528] Trial 477 finished with value: 0.5834174022698613 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0020605319338990154, 'subsample': 0.6238488083904223, 'colsample_bytree': 0.9218342428426275, 'reg_alpha': 7.840010124042958e-09, 'reg_lambda': 1.7130845204644527e-10, 'num_boost_rounds': 1295}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:02:59,687] Trial 478 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:02:59,954] Trial 479 pruned. Trial was pruned at iteration 53.\n[I 2024-05-31 21:03:00,109] Trial 480 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:03,383] Trial 481 finished with value: 0.5834804539722573 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.002049908504419513, 'subsample': 0.625584686840804, 'colsample_bytree': 0.9176701884886711, 'reg_alpha': 2.005899903161409e-08, 'reg_lambda': 1.7858226009819503e-10, 'num_boost_rounds': 1299}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:03,541] Trial 482 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:06,865] Trial 483 finished with value: 0.5838587641866331 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0016544296785422961, 'subsample': 0.6289395480807106, 'colsample_bytree': 0.9220859970642282, 'reg_alpha': 2.4789525462265958e-08, 'reg_lambda': 3.15579707698832e-06, 'num_boost_rounds': 1320}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:07,079] Trial 484 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:07,250] Trial 485 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:07,407] Trial 486 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:07,563] Trial 487 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:07,718] Trial 488 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:10,811] Trial 489 finished with value: 0.5863808322824716 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013335313873860223, 'subsample': 0.6276489558121936, 'colsample_bytree': 0.9200700313810587, 'reg_alpha': 1.8264946956044292e-08, 'reg_lambda': 2.8572986500365833e-10, 'num_boost_rounds': 1267}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:10,967] Trial 490 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:11,236] Trial 491 pruned. Trial was pruned at iteration 53.\n[I 2024-05-31 21:03:11,397] Trial 492 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:11,555] Trial 493 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:11,720] Trial 494 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:11,944] Trial 495 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:12,097] Trial 496 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:12,256] Trial 497 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:12,413] Trial 498 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:12,571] Trial 499 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:12,726] Trial 500 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:12,880] Trial 501 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:16,061] Trial 502 finished with value: 0.5791298865069356 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.002979586181332574, 'subsample': 0.6284105253146767, 'colsample_bytree': 0.9072844238898587, 'reg_alpha': 5.4215401908939904e-08, 'reg_lambda': 3.691044377555653e-10, 'num_boost_rounds': 1254}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:16,216] Trial 503 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:16,378] Trial 504 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:16,537] Trial 505 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:16,697] Trial 506 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:16,856] Trial 507 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:17,012] Trial 508 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:17,175] Trial 509 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:17,336] Trial 510 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:17,491] Trial 511 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:20,790] Trial 512 finished with value: 0.5851197982345523 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001529158976633383, 'subsample': 0.6221751792080672, 'colsample_bytree': 0.9034021242018, 'reg_alpha': 4.686591452528704e-09, 'reg_lambda': 1.005753119041399e-10, 'num_boost_rounds': 1322}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:20,952] Trial 513 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:21,196] Trial 514 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:21,366] Trial 515 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:21,529] Trial 516 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:21,692] Trial 517 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:21,853] Trial 518 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:22,012] Trial 519 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:22,167] Trial 520 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:25,518] Trial 521 finished with value: 0.5872635561160151 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012114447673140058, 'subsample': 0.6257343322562422, 'colsample_bytree': 0.9063532325654965, 'reg_alpha': 3.9710406491378053e-08, 'reg_lambda': 1.6032689546114813e-10, 'num_boost_rounds': 1307}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:25,684] Trial 522 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:29,147] Trial 523 finished with value: 0.5908890290037832 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012188282452573862, 'subsample': 0.6217452326237397, 'colsample_bytree': 0.9009613894207171, 'reg_alpha': 6.682427600230462e-08, 'reg_lambda': 1.6347247644047746e-10, 'num_boost_rounds': 1385}. Best is trial 469 with value: 0.591046658259773.\n[I 2024-05-31 21:03:32,719] Trial 524 finished with value: 0.5920554854981085 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010658085820049994, 'subsample': 0.6266054508484534, 'colsample_bytree': 0.9012296220952136, 'reg_alpha': 6.570043800766914e-08, 'reg_lambda': 1.691010210614606e-10, 'num_boost_rounds': 1408}. Best is trial 524 with value: 0.5920554854981085.\n[I 2024-05-31 21:03:32,876] Trial 525 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:36,582] Trial 526 finished with value: 0.5878940731399749 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010705911826885558, 'subsample': 0.6288164131721538, 'colsample_bytree': 0.9130812332499348, 'reg_alpha': 2.2620817716661675e-08, 'reg_lambda': 1.6387400046733878e-10, 'num_boost_rounds': 1452}. Best is trial 524 with value: 0.5920554854981085.\n[I 2024-05-31 21:03:36,749] Trial 527 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:36,911] Trial 528 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:40,658] Trial 529 finished with value: 0.5902269861286255 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010963349256114727, 'subsample': 0.627058739794362, 'colsample_bytree': 0.9124904232196214, 'reg_alpha': 1.0465312750912957e-08, 'reg_lambda': 1.0174037196779518e-10, 'num_boost_rounds': 1461}. Best is trial 524 with value: 0.5920554854981085.\n[I 2024-05-31 21:03:40,824] Trial 530 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:40,993] Trial 531 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:41,156] Trial 532 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:44,729] Trial 533 finished with value: 0.5869482976040353 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010018270850986962, 'subsample': 0.6214720769784475, 'colsample_bytree': 0.9188227925778257, 'reg_alpha': 3.033754425442182e-08, 'reg_lambda': 1.0084272975543114e-10, 'num_boost_rounds': 1403}. Best is trial 524 with value: 0.5920554854981085.\n[I 2024-05-31 21:03:44,893] Trial 534 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:45,070] Trial 535 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:49,000] Trial 536 finished with value: 0.5887767969735185 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001026536722012052, 'subsample': 0.6245836321836391, 'colsample_bytree': 0.9367608118737392, 'reg_alpha': 3.1801584790374174e-08, 'reg_lambda': 0.12757686794821346, 'num_boost_rounds': 1444}. Best is trial 524 with value: 0.5920554854981085.\n[I 2024-05-31 21:03:49,171] Trial 537 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:49,344] Trial 538 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:49,633] Trial 539 pruned. Trial was pruned at iteration 49.\n[I 2024-05-31 21:03:49,801] Trial 540 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:49,974] Trial 541 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:50,144] Trial 542 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:53,903] Trial 543 finished with value: 0.5891551071878941 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001211413830400571, 'subsample': 0.6050201608108776, 'colsample_bytree': 0.9149425733908406, 'reg_alpha': 1.0861687112240375e-08, 'reg_lambda': 0.00048402574651894715, 'num_boost_rounds': 1451}. Best is trial 524 with value: 0.5920554854981085.\n[I 2024-05-31 21:03:54,070] Trial 544 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:54,320] Trial 545 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:57,668] Trial 546 pruned. Trial was pruned at iteration 1291.\n[I 2024-05-31 21:03:57,838] Trial 547 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:58,008] Trial 548 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:58,177] Trial 549 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:58,346] Trial 550 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:03:58,519] Trial 551 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:01,944] Trial 552 pruned. Trial was pruned at iteration 1376.\n[I 2024-05-31 21:04:05,682] Trial 553 finished with value: 0.594640605296343 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013979522610496889, 'subsample': 0.6237277316067849, 'colsample_bytree': 0.9042718075355117, 'reg_alpha': 1.4450336952596253e-08, 'reg_lambda': 0.10679884658418518, 'num_boost_rounds': 1450}. Best is trial 553 with value: 0.594640605296343.\n[I 2024-05-31 21:04:05,845] Trial 554 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:06,009] Trial 555 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:06,292] Trial 556 pruned. Trial was pruned at iteration 52.\n[I 2024-05-31 21:04:10,127] Trial 557 finished with value: 0.5934426229508197 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013322460918069993, 'subsample': 0.6254900746656231, 'colsample_bytree': 0.9330404419610074, 'reg_alpha': 8.105400989450882e-09, 'reg_lambda': 0.30073574027020217, 'num_boost_rounds': 1471}. Best is trial 553 with value: 0.594640605296343.\n[I 2024-05-31 21:04:10,300] Trial 558 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:10,468] Trial 559 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:10,633] Trial 560 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:10,803] Trial 561 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:11,014] Trial 562 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:11,187] Trial 563 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:14,970] Trial 564 finished with value: 0.5913619167717529 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010002330568313874, 'subsample': 0.6216205643865044, 'colsample_bytree': 0.9157591332552772, 'reg_alpha': 1.4632851156363232e-08, 'reg_lambda': 0.43822823841815517, 'num_boost_rounds': 1495}. Best is trial 553 with value: 0.594640605296343.\n[I 2024-05-31 21:04:15,181] Trial 565 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:15,368] Trial 566 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:15,536] Trial 567 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:15,704] Trial 568 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:19,114] Trial 569 pruned. Trial was pruned at iteration 1291.\n[I 2024-05-31 21:04:19,294] Trial 570 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:19,466] Trial 571 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:19,640] Trial 572 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:19,925] Trial 573 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:23,490] Trial 574 finished with value: 0.5867591424968475 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0011136087218003648, 'subsample': 0.6051864382098223, 'colsample_bytree': 0.9052229815718463, 'reg_alpha': 2.203497957679601e-08, 'reg_lambda': 0.05186398984754703, 'num_boost_rounds': 1399}. Best is trial 553 with value: 0.594640605296343.\n[I 2024-05-31 21:04:23,667] Trial 575 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:23,838] Trial 576 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:24,008] Trial 577 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:24,183] Trial 578 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:27,899] Trial 579 finished with value: 0.594703656998739 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010023852856570624, 'subsample': 0.6067552486384392, 'colsample_bytree': 0.9233018570987394, 'reg_alpha': 2.7089822161774944e-08, 'reg_lambda': 2.4896471224409265, 'num_boost_rounds': 1378}. Best is trial 579 with value: 0.594703656998739.\n[I 2024-05-31 21:04:28,070] Trial 580 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:28,238] Trial 581 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:33,005] Trial 582 finished with value: 0.5926229508196721 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014007165388760503, 'subsample': 0.6045188292863349, 'colsample_bytree': 0.9285862328342488, 'reg_alpha': 8.645947688804703e-09, 'reg_lambda': 1.5436801034740737, 'num_boost_rounds': 1354}. Best is trial 579 with value: 0.594703656998739.\n[I 2024-05-31 21:04:33,179] Trial 583 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:33,353] Trial 584 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:33,650] Trial 585 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:33,826] Trial 586 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:33,994] Trial 587 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:34,164] Trial 588 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:37,446] Trial 589 pruned. Trial was pruned at iteration 1189.\n[I 2024-05-31 21:04:41,044] Trial 590 finished with value: 0.5950819672131148 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0015281544594155413, 'subsample': 0.6097043659660323, 'colsample_bytree': 0.9145510339467656, 'reg_alpha': 1.7721608220032474e-08, 'reg_lambda': 1.7370043737188905, 'num_boost_rounds': 1384}. Best is trial 590 with value: 0.5950819672131148.\n[I 2024-05-31 21:04:41,216] Trial 591 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:45,205] Trial 592 finished with value: 0.5904791929382094 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0010029895504360794, 'subsample': 0.6072583802516953, 'colsample_bytree': 0.9185381330862751, 'reg_alpha': 1.834662482307028e-08, 'reg_lambda': 1.3694512624872826, 'num_boost_rounds': 1499}. Best is trial 590 with value: 0.5950819672131148.\n[I 2024-05-31 21:04:45,398] Trial 593 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:45,662] Trial 594 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:49,609] Trial 595 finished with value: 0.5969735182849937 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0011018721638371563, 'subsample': 0.6107627655560063, 'colsample_bytree': 0.9194607151784616, 'reg_alpha': 2.0265579874432394e-08, 'reg_lambda': 3.3491712013479957, 'num_boost_rounds': 1498}. Best is trial 595 with value: 0.5969735182849937.\n[I 2024-05-31 21:04:49,972] Trial 596 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:50,249] Trial 597 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:50,430] Trial 598 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:50,624] Trial 599 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:50,812] Trial 600 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:50,990] Trial 601 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:51,176] Trial 602 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:51,360] Trial 603 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:51,555] Trial 604 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:55,375] Trial 605 finished with value: 0.5970996216897857 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0015355042731792887, 'subsample': 0.6134341953046542, 'colsample_bytree': 0.9194759194956363, 'reg_alpha': 1.1203705204521807e-08, 'reg_lambda': 3.262193643744098, 'num_boost_rounds': 1429}. Best is trial 605 with value: 0.5970996216897857.\n[I 2024-05-31 21:04:55,551] Trial 606 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:55,729] Trial 607 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:55,917] Trial 608 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:59,615] Trial 609 finished with value: 0.594829760403531 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013499564777330285, 'subsample': 0.6018632705687343, 'colsample_bytree': 0.9196102388904842, 'reg_alpha': 5.457126132473073e-09, 'reg_lambda': 1.9306281316748255, 'num_boost_rounds': 1399}. Best is trial 605 with value: 0.5970996216897857.\n[I 2024-05-31 21:04:59,797] Trial 610 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:04:59,971] Trial 611 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:00,301] Trial 612 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:04,902] Trial 613 finished with value: 0.5926229508196721 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014349185592032877, 'subsample': 0.6037470373438104, 'colsample_bytree': 0.8998258618005557, 'reg_alpha': 2.2358311425581394e-09, 'reg_lambda': 1.1806619397253062, 'num_boost_rounds': 1459}. Best is trial 605 with value: 0.5970996216897857.\n[I 2024-05-31 21:05:05,093] Trial 614 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:05,305] Trial 615 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:05,487] Trial 616 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:05,680] Trial 617 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:05,859] Trial 618 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:06,038] Trial 619 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:09,738] Trial 620 finished with value: 0.5959646910466584 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013226692256695953, 'subsample': 0.6084390057980615, 'colsample_bytree': 0.9106455127389178, 'reg_alpha': 1.1793804730144217e-08, 'reg_lambda': 1.9065587652576232, 'num_boost_rounds': 1425}. Best is trial 605 with value: 0.5970996216897857.\n[I 2024-05-31 21:05:09,926] Trial 621 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:14,011] Trial 622 finished with value: 0.5919924337957125 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001288703162384369, 'subsample': 0.6032697590462041, 'colsample_bytree': 0.9279870737095259, 'reg_alpha': 1.3568303789259111e-08, 'reg_lambda': 1.3161609947626474, 'num_boost_rounds': 1470}. Best is trial 605 with value: 0.5970996216897857.\n[I 2024-05-31 21:05:14,210] Trial 623 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:14,388] Trial 624 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:14,573] Trial 625 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:14,798] Trial 626 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:18,965] Trial 627 finished with value: 0.6000630517023959 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012719176149288839, 'subsample': 0.6087501486870088, 'colsample_bytree': 0.9263159354405333, 'reg_alpha': 1.2557805606858702e-08, 'reg_lambda': 3.495474103295276, 'num_boost_rounds': 1479}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:05:19,156] Trial 628 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:19,333] Trial 629 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:19,510] Trial 630 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:23,177] Trial 631 finished with value: 0.5934426229508196 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001000807810485056, 'subsample': 0.604694123606575, 'colsample_bytree': 0.9208359450950981, 'reg_alpha': 8.212351839912691e-09, 'reg_lambda': 0.6213210206631975, 'num_boost_rounds': 1440}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:05:23,365] Trial 632 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:23,539] Trial 633 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:23,720] Trial 634 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:23,907] Trial 635 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:24,079] Trial 636 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:24,253] Trial 637 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:24,442] Trial 638 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:24,615] Trial 639 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:24,845] Trial 640 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:25,030] Trial 641 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:28,252] Trial 642 pruned. Trial was pruned at iteration 1268.\n[I 2024-05-31 21:05:28,438] Trial 643 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:28,616] Trial 644 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:28,802] Trial 645 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:28,977] Trial 646 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:29,158] Trial 647 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:29,438] Trial 648 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:29,616] Trial 649 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:29,793] Trial 650 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:29,972] Trial 651 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:34,754] Trial 652 finished with value: 0.5976040353089535 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013802850232596839, 'subsample': 0.6044135929019165, 'colsample_bytree': 0.9141360194652166, 'reg_alpha': 2.990380719053383e-08, 'reg_lambda': 0.6201853418037692, 'num_boost_rounds': 1441}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:05:34,939] Trial 653 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:35,138] Trial 654 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:35,332] Trial 655 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:35,510] Trial 656 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:35,693] Trial 657 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:35,876] Trial 658 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:36,059] Trial 659 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:36,236] Trial 660 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:39,627] Trial 661 pruned. Trial was pruned at iteration 1287.\n[I 2024-05-31 21:05:39,813] Trial 662 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:41,257] Trial 663 pruned. Trial was pruned at iteration 190.\n[I 2024-05-31 21:05:41,453] Trial 664 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:41,638] Trial 665 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:41,823] Trial 666 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:42,010] Trial 667 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:42,202] Trial 668 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:42,391] Trial 669 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:42,575] Trial 670 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:42,781] Trial 671 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:46,451] Trial 672 pruned. Trial was pruned at iteration 1325.\n[I 2024-05-31 21:05:46,650] Trial 673 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:46,848] Trial 674 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:47,062] Trial 675 pruned. Trial was pruned at iteration 11.\n[I 2024-05-31 21:05:47,258] Trial 676 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:47,457] Trial 677 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:47,653] Trial 678 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:47,841] Trial 679 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:51,164] Trial 680 pruned. Trial was pruned at iteration 1257.\n[I 2024-05-31 21:05:51,372] Trial 681 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:51,564] Trial 682 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:55,361] Trial 683 finished with value: 0.5959016393442623 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0016256977288620752, 'subsample': 0.6169090570121832, 'colsample_bytree': 0.9088154055705965, 'reg_alpha': 1.3274908142197087e-08, 'reg_lambda': 2.4140864790793573, 'num_boost_rounds': 1435}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:05:55,558] Trial 684 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:55,742] Trial 685 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:59,602] Trial 686 finished with value: 0.5928751576292559 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001750034358751101, 'subsample': 0.6158690387381698, 'colsample_bytree': 0.9183107352748484, 'reg_alpha': 4.770400017782253e-09, 'reg_lambda': 6.747488794446564, 'num_boost_rounds': 1453}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:05:59,795] Trial 687 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:05:59,991] Trial 688 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:00,174] Trial 689 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:00,362] Trial 690 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:00,561] Trial 691 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:05,581] Trial 692 finished with value: 0.5964691046658259 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001550796687530132, 'subsample': 0.6141487215602203, 'colsample_bytree': 0.9051133682127935, 'reg_alpha': 2.6806403385966006e-09, 'reg_lambda': 3.288026503611473, 'num_boost_rounds': 1449}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:05,773] Trial 693 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:05,958] Trial 694 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:06,152] Trial 695 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:06,342] Trial 696 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:06,529] Trial 697 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:06,734] Trial 698 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:06,924] Trial 699 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:07,110] Trial 700 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:10,954] Trial 701 finished with value: 0.5981084489281211 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012690922430618795, 'subsample': 0.6050699217083122, 'colsample_bytree': 0.9060734925981332, 'reg_alpha': 7.807751137449029e-09, 'reg_lambda': 3.593763333255446, 'num_boost_rounds': 1481}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:11,171] Trial 702 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:11,381] Trial 703 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:11,585] Trial 704 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:11,792] Trial 705 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:12,001] Trial 706 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:15,933] Trial 707 finished with value: 0.5933795712484238 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014026429939268264, 'subsample': 0.6066569323304797, 'colsample_bytree': 0.9025496751588392, 'reg_alpha': 1.7911259437078703e-09, 'reg_lambda': 1.9126989025943173, 'num_boost_rounds': 1457}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:19,943] Trial 708 finished with value: 0.5937578814627995 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014097986667871182, 'subsample': 0.6144471132644788, 'colsample_bytree': 0.8945690275675879, 'reg_alpha': 1.9959243577959444e-09, 'reg_lambda': 1.722492171169765, 'num_boost_rounds': 1477}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:20,137] Trial 709 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:20,323] Trial 710 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:20,527] Trial 711 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:24,408] Trial 712 finished with value: 0.5953341740226987 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0018916188881412885, 'subsample': 0.6137909376805049, 'colsample_bytree': 0.9016319795195893, 'reg_alpha': 5.88681424411224e-10, 'reg_lambda': 1.6860791768660175, 'num_boost_rounds': 1482}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:28,355] Trial 713 finished with value: 0.5922446406052964 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0018687970194535943, 'subsample': 0.6161856775404582, 'colsample_bytree': 0.9006448280712177, 'reg_alpha': 3.353637668182194e-10, 'reg_lambda': 2.3115662399256975, 'num_boost_rounds': 1428}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:28,563] Trial 714 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:28,762] Trial 715 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:32,733] Trial 716 finished with value: 0.5920554854981084 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0019036143691343176, 'subsample': 0.6134585119098432, 'colsample_bytree': 0.8922193792671207, 'reg_alpha': 4.726708254365273e-10, 'reg_lambda': 2.078713464587389, 'num_boost_rounds': 1470}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:33,012] Trial 717 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:33,211] Trial 718 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:33,405] Trial 719 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:33,614] Trial 720 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:33,896] Trial 721 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:34,139] Trial 722 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:38,758] Trial 723 finished with value: 0.596595208070618 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001575207885053813, 'subsample': 0.6075150570508653, 'colsample_bytree': 0.9008696373387277, 'reg_alpha': 5.257375913653858e-10, 'reg_lambda': 8.272868646421609, 'num_boost_rounds': 1453}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:38,957] Trial 724 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:39,145] Trial 725 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:42,990] Trial 726 finished with value: 0.5982345523329131 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001590330538179591, 'subsample': 0.6044974304798519, 'colsample_bytree': 0.8873588444463826, 'reg_alpha': 5.996189715594538e-10, 'reg_lambda': 11.13275783292433, 'num_boost_rounds': 1414}. Best is trial 627 with value: 0.6000630517023959.\n[I 2024-05-31 21:06:43,211] Trial 727 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:43,415] Trial 728 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:43,601] Trial 729 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:47,509] Trial 730 finished with value: 0.6001261034047919 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0017706695628210032, 'subsample': 0.6067671912668138, 'colsample_bytree': 0.8862738762987291, 'reg_alpha': 8.279557278965221e-10, 'reg_lambda': 7.36544108437067, 'num_boost_rounds': 1428}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:06:47,699] Trial 731 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:47,895] Trial 732 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:48,083] Trial 733 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:48,267] Trial 734 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:48,467] Trial 735 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:48,658] Trial 736 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:48,854] Trial 737 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:49,056] Trial 738 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:52,614] Trial 739 finished with value: 0.5994325346784364 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001428392967998145, 'subsample': 0.606559303831009, 'colsample_bytree': 0.9070926531040482, 'reg_alpha': 1.530016681737232e-09, 'reg_lambda': 4.34512534056128, 'num_boost_rounds': 1381}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:06:52,811] Trial 740 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:53,007] Trial 741 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:53,213] Trial 742 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:53,412] Trial 743 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:53,618] Trial 744 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:57,724] Trial 745 finished with value: 0.5951450189155107 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0017691076097858705, 'subsample': 0.6074332046883166, 'colsample_bytree': 0.8966185704267025, 'reg_alpha': 2.927920805788474e-10, 'reg_lambda': 3.2773017697097693, 'num_boost_rounds': 1452}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:06:57,922] Trial 746 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:58,115] Trial 747 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:06:58,325] Trial 748 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:02,325] Trial 749 finished with value: 0.5981084489281211 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0017361334462875997, 'subsample': 0.6045631032491324, 'colsample_bytree': 0.8821099190099346, 'reg_alpha': 8.068358290784919e-10, 'reg_lambda': 3.220363344538042, 'num_boost_rounds': 1430}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:07:02,524] Trial 750 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:02,720] Trial 751 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:02,926] Trial 752 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:03,120] Trial 753 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:03,434] Trial 754 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:03,636] Trial 755 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:03,847] Trial 756 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:04,041] Trial 757 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:04,246] Trial 758 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:04,455] Trial 759 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:04,648] Trial 760 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:04,843] Trial 761 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:09,793] Trial 762 finished with value: 0.5971626733921815 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0015349905700369607, 'subsample': 0.6073011125287782, 'colsample_bytree': 0.915222431657619, 'reg_alpha': 1.1656240132005568e-09, 'reg_lambda': 3.558525265254323, 'num_boost_rounds': 1417}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:07:10,008] Trial 763 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:10,207] Trial 764 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:10,407] Trial 765 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:10,616] Trial 766 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:10,817] Trial 767 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:11,016] Trial 768 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:14,961] Trial 769 finished with value: 0.598360655737705 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013660494777564106, 'subsample': 0.6048522126281642, 'colsample_bytree': 0.9074566673584397, 'reg_alpha': 1.4581269454268684e-09, 'reg_lambda': 3.4555665950209042, 'num_boost_rounds': 1444}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:07:15,184] Trial 770 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:15,403] Trial 771 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:15,738] Trial 772 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:19,517] Trial 773 finished with value: 0.5988020176544767 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014972782615490278, 'subsample': 0.6052195110964004, 'colsample_bytree': 0.8972370772184562, 'reg_alpha': 2.3183573782023303e-09, 'reg_lambda': 3.5140821297723646, 'num_boost_rounds': 1418}. Best is trial 730 with value: 0.6001261034047919.\n[I 2024-05-31 21:07:19,715] Trial 774 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:19,927] Trial 775 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:23,755] Trial 776 finished with value: 0.6034047919293821 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014670740897988646, 'subsample': 0.6058441199265151, 'colsample_bytree': 0.8947859572212196, 'reg_alpha': 6.263662860381885e-10, 'reg_lambda': 4.475180736243736, 'num_boost_rounds': 1420}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:23,965] Trial 777 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:24,224] Trial 778 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:28,314] Trial 779 finished with value: 0.5950189155107188 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014707955746582858, 'subsample': 0.6178593055982929, 'colsample_bytree': 0.8943807304075944, 'reg_alpha': 1.0949842159952205e-10, 'reg_lambda': 6.991594137039345, 'num_boost_rounds': 1418}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:28,564] Trial 780 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:28,761] Trial 781 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:28,961] Trial 782 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:32,649] Trial 783 finished with value: 0.5994325346784364 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014423236039102152, 'subsample': 0.6080336183369166, 'colsample_bytree': 0.8940907100135301, 'reg_alpha': 1.1401142496364185e-10, 'reg_lambda': 4.970055742727749, 'num_boost_rounds': 1354}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:32,861] Trial 784 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:33,064] Trial 785 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:33,273] Trial 786 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:33,482] Trial 787 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:33,683] Trial 788 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:33,892] Trial 789 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:34,098] Trial 790 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:39,001] Trial 791 finished with value: 0.5968474148802018 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0016201852081880253, 'subsample': 0.6096829119000513, 'colsample_bytree': 0.8932265893159287, 'reg_alpha': 4.296021664534036e-10, 'reg_lambda': 3.1006554841606095, 'num_boost_rounds': 1392}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:39,205] Trial 792 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:39,398] Trial 793 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:43,078] Trial 794 finished with value: 0.6005044136191678 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0015749649349081733, 'subsample': 0.6055419213627501, 'colsample_bytree': 0.8952745104307225, 'reg_alpha': 3.4122059381415517e-10, 'reg_lambda': 4.240388903664488, 'num_boost_rounds': 1348}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:43,284] Trial 795 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:43,488] Trial 796 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:43,683] Trial 797 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:43,876] Trial 798 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:44,070] Trial 799 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:44,342] Trial 800 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:44,559] Trial 801 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:44,755] Trial 802 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:44,954] Trial 803 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:48,728] Trial 804 finished with value: 0.5977931904161412 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001440320055630269, 'subsample': 0.6075392733918726, 'colsample_bytree': 0.9062346390728206, 'reg_alpha': 4.5577880890885703e-10, 'reg_lambda': 5.5794331192296625, 'num_boost_rounds': 1429}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:48,924] Trial 805 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:49,133] Trial 806 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:49,334] Trial 807 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:49,537] Trial 808 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:53,106] Trial 809 finished with value: 0.5987389659520808 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0016316854506457136, 'subsample': 0.6076977174120063, 'colsample_bytree': 0.9050738123563755, 'reg_alpha': 8.706754372563225e-10, 'reg_lambda': 6.650543022567537, 'num_boost_rounds': 1381}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:53,305] Trial 810 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:56,902] Trial 811 finished with value: 0.6002522068095839 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0017985236347361146, 'subsample': 0.6085403401751909, 'colsample_bytree': 0.9086229843043302, 'reg_alpha': 9.81570771921281e-10, 'reg_lambda': 4.781916453301688, 'num_boost_rounds': 1346}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:07:57,109] Trial 812 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:57,311] Trial 813 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:57,506] Trial 814 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:57,706] Trial 815 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:57,923] Trial 816 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:58,117] Trial 817 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:58,307] Trial 818 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:58,515] Trial 819 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:58,721] Trial 820 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:58,920] Trial 821 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:59,114] Trial 822 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:59,320] Trial 823 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:59,515] Trial 824 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:59,720] Trial 825 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:07:59,920] Trial 826 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:00,118] Trial 827 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:00,322] Trial 828 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:00,527] Trial 829 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:00,728] Trial 830 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:00,924] Trial 831 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:04,725] Trial 832 finished with value: 0.5928751576292561 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0017086587736130912, 'subsample': 0.6185353707543622, 'colsample_bytree': 0.9116432130187394, 'reg_alpha': 8.681565940733783e-10, 'reg_lambda': 2.258878193531207, 'num_boost_rounds': 1457}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:04,940] Trial 833 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:05,146] Trial 834 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:05,376] Trial 835 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:05,677] Trial 836 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:05,911] Trial 837 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:09,568] Trial 838 finished with value: 0.5867591424968475 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013058542579093143, 'subsample': 0.6078911404118413, 'colsample_bytree': 0.8912146803778455, 'reg_alpha': 9.336715871281635e-10, 'reg_lambda': 2.2834023480790178, 'num_boost_rounds': 944}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:09,776] Trial 839 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:13,694] Trial 840 finished with value: 0.48417402269861287 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.09035960653212344, 'subsample': 0.6171628438242731, 'colsample_bytree': 0.8721820744590862, 'reg_alpha': 3.9353061844382486e-10, 'reg_lambda': 7.299570886939422, 'num_boost_rounds': 1432}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:13,907] Trial 841 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:14,123] Trial 842 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:15,534] Trial 843 finished with value: 0.5815889029003782 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001289489496162379, 'subsample': 0.6206430708584184, 'colsample_bytree': 0.8952779609996032, 'reg_alpha': 0.0013193759677981429, 'reg_lambda': 3.5440095530081996, 'num_boost_rounds': 456}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:15,750] Trial 844 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:15,948] Trial 845 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:16,148] Trial 846 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:16,366] Trial 847 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:16,746] Trial 848 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:16,992] Trial 849 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:17,370] Trial 850 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:17,579] Trial 851 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:21,278] Trial 852 pruned. Trial was pruned at iteration 1336.\n[I 2024-05-31 21:08:21,487] Trial 853 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:21,707] Trial 854 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:21,910] Trial 855 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:22,127] Trial 856 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:22,421] Trial 857 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:26,323] Trial 858 finished with value: 0.592875157629256 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0017759892578479222, 'subsample': 0.6213275547916776, 'colsample_bytree': 0.9088192031645843, 'reg_alpha': 2.3893899765164137e-09, 'reg_lambda': 3.5033917472450695, 'num_boost_rounds': 1427}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:26,551] Trial 859 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:26,758] Trial 860 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:26,959] Trial 861 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:27,171] Trial 862 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:27,376] Trial 863 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:27,579] Trial 864 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:27,793] Trial 865 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:28,013] Trial 866 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:28,233] Trial 867 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:28,437] Trial 868 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:32,320] Trial 869 finished with value: 0.5964060529634301 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012512991979108559, 'subsample': 0.6109075336857784, 'colsample_bytree': 0.9192782857308638, 'reg_alpha': 1.6686588225125454e-09, 'reg_lambda': 2.9654080580421103, 'num_boost_rounds': 1478}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:32,536] Trial 870 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:32,737] Trial 871 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:32,936] Trial 872 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:33,145] Trial 873 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:33,463] Trial 874 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:33,682] Trial 875 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:37,446] Trial 876 finished with value: 0.5979823455233292 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001327189592358229, 'subsample': 0.6009012649934693, 'colsample_bytree': 0.9220322843913409, 'reg_alpha': 9.085770258218999e-10, 'reg_lambda': 3.075483493862786, 'num_boost_rounds': 1402}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:37,648] Trial 877 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:37,848] Trial 878 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:38,051] Trial 879 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:38,261] Trial 880 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:38,464] Trial 881 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:38,662] Trial 882 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:38,878] Trial 883 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:39,075] Trial 884 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:44,200] Trial 885 finished with value: 0.6014501891551073 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012295169456455516, 'subsample': 0.6046642211961041, 'colsample_bytree': 0.9275388041473576, 'reg_alpha': 1.7565205435811329e-09, 'reg_lambda': 5.024043889796191, 'num_boost_rounds': 1424}. Best is trial 776 with value: 0.6034047919293821.\n[I 2024-05-31 21:08:44,409] Trial 886 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:44,620] Trial 887 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:44,836] Trial 888 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:48,551] Trial 889 finished with value: 0.6034678436317781 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013120481578682735, 'subsample': 0.6044948329796078, 'colsample_bytree': 0.9195111693986473, 'reg_alpha': 5.117534385516801e-10, 'reg_lambda': 4.92575951515746, 'num_boost_rounds': 1374}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:08:48,757] Trial 890 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:48,957] Trial 891 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:49,157] Trial 892 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:49,376] Trial 893 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:49,577] Trial 894 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:49,774] Trial 895 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:49,976] Trial 896 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:50,193] Trial 897 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:50,399] Trial 898 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:50,605] Trial 899 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:50,821] Trial 900 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:51,025] Trial 901 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:51,228] Trial 902 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:58,043] Trial 903 pruned. Trial was pruned at iteration 1173.\n[I 2024-05-31 21:08:58,258] Trial 904 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:58,489] Trial 905 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:58,725] Trial 906 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:58,932] Trial 907 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:59,139] Trial 908 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:59,348] Trial 909 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:59,566] Trial 910 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:59,777] Trial 911 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:08:59,992] Trial 912 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:00,198] Trial 913 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:00,403] Trial 914 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:04,336] Trial 915 finished with value: 0.5925598991172762 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014888010880583413, 'subsample': 0.6221483843489416, 'colsample_bytree': 0.8931942253920617, 'reg_alpha': 8.058263873422858e-10, 'reg_lambda': 1.171352271459073, 'num_boost_rounds': 1415}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:04,555] Trial 916 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:08,207] Trial 917 finished with value: 0.5258511979823456 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.03908811645079037, 'subsample': 0.5983847547125261, 'colsample_bytree': 0.9156677530358758, 'reg_alpha': 2.0355952647836416e-09, 'reg_lambda': 2.185373585599543, 'num_boost_rounds': 1359}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:13,324] Trial 918 finished with value: 0.5917402269861286 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0015891803228322496, 'subsample': 0.6151067663840238, 'colsample_bytree': 0.9393484164512408, 'reg_alpha': 7.591682488663783e-05, 'reg_lambda': 3.5448865858141883, 'num_boost_rounds': 1401}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:13,530] Trial 919 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:13,745] Trial 920 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:13,947] Trial 921 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:14,170] Trial 922 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:14,377] Trial 923 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:14,589] Trial 924 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:18,516] Trial 925 finished with value: 0.596343001261034 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001550920309646323, 'subsample': 0.6023563413678811, 'colsample_bytree': 0.9099631119505461, 'reg_alpha': 1.603133627405556e-09, 'reg_lambda': 1.1330525737930026, 'num_boost_rounds': 1459}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:18,725] Trial 926 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:18,941] Trial 927 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:19,155] Trial 928 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:19,381] Trial 929 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:19,594] Trial 930 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:23,346] Trial 931 finished with value: 0.5998738965952081 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013988901797905974, 'subsample': 0.6037967845974528, 'colsample_bytree': 0.9058287758435872, 'reg_alpha': 1.8137862538219393e-09, 'reg_lambda': 3.956886478070126, 'num_boost_rounds': 1428}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:23,692] Trial 932 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:23,906] Trial 933 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:24,236] Trial 934 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:24,449] Trial 935 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:24,665] Trial 936 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:24,876] Trial 937 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:25,093] Trial 938 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:25,321] Trial 939 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:25,542] Trial 940 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:25,759] Trial 941 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:29,877] Trial 942 finished with value: 0.5985498108448928 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013252069105086904, 'subsample': 0.6047070135816565, 'colsample_bytree': 0.9746229916998508, 'reg_alpha': 1.3277191479467965e-09, 'reg_lambda': 1.8486982992851335, 'num_boost_rounds': 1434}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:30,089] Trial 943 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:33,972] Trial 944 finished with value: 0.5970365699873896 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0013244297009297147, 'subsample': 0.603237016253796, 'colsample_bytree': 0.9685397060163816, 'reg_alpha': 1.0816824149728844e-09, 'reg_lambda': 2.006062177258115, 'num_boost_rounds': 1407}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:34,188] Trial 945 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:34,410] Trial 946 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:34,619] Trial 947 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:34,833] Trial 948 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:35,042] Trial 949 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:35,287] Trial 950 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:35,498] Trial 951 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:35,715] Trial 952 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:35,975] Trial 953 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:36,199] Trial 954 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:36,415] Trial 955 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:36,637] Trial 956 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:37,033] Trial 957 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:37,255] Trial 958 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:37,483] Trial 959 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:37,691] Trial 960 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:37,908] Trial 961 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:38,120] Trial 962 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:42,045] Trial 963 finished with value: 0.5977301387137454 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0015254164375093477, 'subsample': 0.6100634137184543, 'colsample_bytree': 0.9602543224753628, 'reg_alpha': 3.340316826476365e-10, 'reg_lambda': 2.855734368530157, 'num_boost_rounds': 1436}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:42,255] Trial 964 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:42,469] Trial 965 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:42,994] Trial 966 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:43,638] Trial 967 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:43,860] Trial 968 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:44,072] Trial 969 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:44,285] Trial 970 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:44,592] Trial 971 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:44,812] Trial 972 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:45,035] Trial 973 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:45,306] Trial 974 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:45,522] Trial 975 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:45,742] Trial 976 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:45,952] Trial 977 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:46,160] Trial 978 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:46,373] Trial 979 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:46,617] Trial 980 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:46,834] Trial 981 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:47,050] Trial 982 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:47,263] Trial 983 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:47,494] Trial 984 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:47,778] Trial 985 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:51,488] Trial 986 finished with value: 0.5950819672131149 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0014457456237916163, 'subsample': 0.6101544013776168, 'colsample_bytree': 0.95178731033514, 'reg_alpha': 6.436775909406948e-10, 'reg_lambda': 2.432670187572633, 'num_boost_rounds': 1316}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:51,712] Trial 987 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:51,936] Trial 988 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:52,151] Trial 989 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:52,370] Trial 990 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:56,708] Trial 991 finished with value: 0.5977931904161411 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.001247647344993039, 'subsample': 0.6022450673684764, 'colsample_bytree': 0.9460178075219824, 'reg_alpha': 5.847749923710279e-10, 'reg_lambda': 1.9341929586605153, 'num_boost_rounds': 1500}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:09:56,926] Trial 992 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:57,152] Trial 993 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:57,377] Trial 994 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:09:57,602] Trial 995 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:10:01,738] Trial 996 finished with value: 0.5985498108448928 and parameters: {'lags': 2, 'max_depth': 3, 'learning_rate': 0.0012649206230807562, 'subsample': 0.5983651887539425, 'colsample_bytree': 0.9689084332480751, 'reg_alpha': 7.732905241887149e-10, 'reg_lambda': 2.647408903134117, 'num_boost_rounds': 1451}. Best is trial 889 with value: 0.6034678436317781.\n[I 2024-05-31 21:10:01,964] Trial 997 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:10:02,189] Trial 998 pruned. Trial was pruned at iteration 0.\n[I 2024-05-31 21:10:02,408] Trial 999 pruned. Trial was pruned at iteration 0.\n", "output_type": "stream" }, { "name": "stdout", "text": "Number of finished trials: 1000\n", "output_type": "stream" } ] }, { "cell_type": "code", "source": [ "lags = best_params['lags']\n", "best_params.pop('lags')\n", "\n", "og_cols = df.columns.tolist()\n", "og_cols.remove('clabel')\n", "lag_transformer = LagFeatures(periods=[x for x in range(1, lags + 1)])\n", "lagged_df = lag_transformer.fit_transform(df)\n", "lagged_df = lagged_df.dropna().drop(columns=og_cols)\n", "X = lagged_df.drop(columns=['clabel'])\n", "y = lagged_df.clabel\n", "X_train, X_test, y_train, y_test = tts_last_n(X, y, 252)\n", "\n", "dtrain = xgb.DMatrix(X_train, y_train)\n", "dtest = xgb.DMatrix(X_test, y_test)\n", "model = xgb.train(best_params, dtrain, num_boost_round=n_rounds)\n", "importance_dict = model.get_score(importance_type='weight')\n", "sorted_importance = sorted(importance_dict.items(), key=lambda item: item[1], reverse=True)\n", "preds = model.predict(dtest)\n", "print(roc_auc_score(y_test, preds))\n", "# Print the sorted key-value pairs\n", "for feature, importance in sorted_importance:\n", " print(f\"{feature}: {importance}\")" ], "metadata": { "execution": { "iopub.status.busy": "2024-05-31T21:19:21.655876Z", "iopub.execute_input": "2024-05-31T21:19:21.656758Z", "iopub.status.idle": "2024-05-31T21:19:23.506865Z", "shell.execute_reply.started": "2024-05-31T21:19:21.656724Z", "shell.execute_reply": "2024-05-31T21:19:23.506100Z" }, "trusted": true }, "execution_count": 10, "outputs": [ { "name": "stdout", "text": "0.48865927419354843\nrsi_ema_lag_1: 939.0\nblob_pol_lag_1: 806.0\nfinbert_pos_lag_1: 471.0\nvader_pos_lag_2: 451.0\nreturn_lag_2: 434.0\nvolume_lag_2: 425.0\nfinbert_neg_lag_2: 424.0\nvader_pos_lag_1: 420.0\nfinbert_neu_lag_2: 409.0\nvader_neu_lag_2: 375.0\nfinbert_pos_lag_2: 374.0\nblob_pol_lag_2: 352.0\nfinbert_neg_lag_1: 326.0\nrsi_ema_lag_2: 323.0\nreturn_lag_1: 276.0\nvolume_lag_1: 269.0\newmstd_20_lag_1: 269.0\nvader_neg_lag_1: 251.0\nfinbert_neu_lag_1: 232.0\nvader_neu_lag_1: 231.0\newmstd_20_lag_2: 227.0\nvader_neg_lag_2: 208.0\nmacd_lag_1: 158.0\nmacd_lag_2: 130.0\newma_20_lag_1: 86.0\newma_60_lag_1: 81.0\nopen_lag_1: 62.0\newma_60_lag_2: 58.0\newma_20_lag_2: 52.0\nadj_close_lag_1: 51.0\nlow_lag_1: 46.0\nlog1p_return_lag_2: 39.0\nhigh_lag_1: 35.0\nopen_lag_2: 31.0\nlog1p_return_lag_1: 28.0\nhigh_lag_2: 27.0\nlow_lag_2: 27.0\nadj_close_lag_2: 12.0\nclabel_lag_2: 1.0\n", "output_type": "stream" } ] }, { "cell_type": "code", "source": [ "for t, p in zip(y_test, preds):\n", " print(f'{t} {p}')" ], "metadata": { "execution": { "iopub.status.busy": "2024-05-31T21:41:12.598224Z", "iopub.execute_input": "2024-05-31T21:41:12.598630Z", "iopub.status.idle": "2024-05-31T21:41:12.605828Z", "shell.execute_reply.started": "2024-05-31T21:41:12.598599Z", "shell.execute_reply": "2024-05-31T21:41:12.604960Z" }, "trusted": true }, "execution_count": 11, "outputs": [ { "name": "stdout", "text": "1 0.47065234184265137\n0 0.5189043879508972\n0 0.5076619386672974\n0 0.48384585976600647\n0 0.5388537645339966\n0 0.5509284734725952\n1 0.5151180028915405\n1 0.5534857511520386\n1 0.4054875373840332\n1 0.4701915681362152\n0 0.5148618221282959\n0 0.4551321566104889\n1 0.4997105002403259\n0 0.4810556471347809\n0 0.4865526854991913\n1 0.5004813075065613\n0 0.4908014237880707\n1 0.4836479723453522\n1 0.46918246150016785\n1 0.500747561454773\n1 0.5154166221618652\n1 0.43352195620536804\n0 0.46490201354026794\n0 0.462611585855484\n1 0.4923120141029358\n0 0.5109392404556274\n1 0.47008228302001953\n1 0.4728529453277588\n0 0.4631299674510956\n0 0.529362678527832\n0 0.5050005912780762\n1 0.537726879119873\n0 0.48994436860084534\n1 0.5050482153892517\n1 0.48590901494026184\n1 0.4701353907585144\n0 0.4754470884799957\n0 0.4751470983028412\n1 0.45190364122390747\n0 0.4852973222732544\n1 0.4466356337070465\n0 0.4667574465274811\n1 0.4997677803039551\n0 0.4420485198497772\n1 0.43025025725364685\n1 0.49303945899009705\n0 0.5147255659103394\n1 0.4567466080188751\n1 0.5958914756774902\n0 0.540429949760437\n0 0.4961487948894501\n1 0.4940754771232605\n1 0.5193387269973755\n0 0.5584979057312012\n1 0.48244500160217285\n1 0.5757376551628113\n0 0.5642377138137817\n0 0.544733464717865\n1 0.504325270652771\n0 0.5480174422264099\n0 0.508025050163269\n0 0.5207054018974304\n0 0.4867977499961853\n0 0.48764535784721375\n1 0.5617823004722595\n0 0.46066057682037354\n1 0.4414660930633545\n1 0.4434305429458618\n1 0.5059064626693726\n0 0.5021345019340515\n1 0.5002156496047974\n0 0.4953109920024872\n0 0.491411417722702\n1 0.4861580729484558\n0 0.49113911390304565\n0 0.45481181144714355\n0 0.5113703608512878\n1 0.4809853732585907\n0 0.4544568955898285\n0 0.48428788781166077\n0 0.489268034696579\n1 0.49735119938850403\n0 0.46754828095436096\n0 0.47513848543167114\n0 0.5572832822799683\n1 0.5439212918281555\n0 0.5165201425552368\n0 0.54869145154953\n1 0.5799077749252319\n0 0.5485747456550598\n1 0.5041449666023254\n0 0.5154220461845398\n0 0.4960781931877136\n1 0.5335249304771423\n0 0.4817487299442291\n0 0.4205290377140045\n1 0.5234341025352478\n0 0.5378763675689697\n0 0.5435639023780823\n0 0.5469034910202026\n1 0.5526469349861145\n1 0.5548135042190552\n1 0.5143516063690186\n0 0.47294989228248596\n1 0.5217337012290955\n0 0.49552032351493835\n0 0.5405517816543579\n1 0.49391600489616394\n0 0.4523322880268097\n1 0.5361831784248352\n0 0.4804140627384186\n1 0.4658789038658142\n0 0.4934852719306946\n1 0.5001546740531921\n1 0.5091626644134521\n0 0.45075279474258423\n0 0.4847452640533447\n1 0.4994242787361145\n1 0.43192651867866516\n0 0.48334333300590515\n1 0.4974867105484009\n0 0.4972633421421051\n0 0.4927198588848114\n0 0.48605018854141235\n1 0.4400656819343567\n1 0.4809432327747345\n1 0.4807473123073578\n0 0.4884348213672638\n0 0.46917715668678284\n1 0.4556770622730255\n0 0.47248515486717224\n1 0.4882658123970032\n1 0.4774240553379059\n1 0.4887571930885315\n0 0.45209571719169617\n1 0.4710647463798523\n1 0.5690885782241821\n1 0.517767071723938\n1 0.5319639444351196\n0 0.5109938979148865\n0 0.5724546909332275\n1 0.4844364523887634\n1 0.4665590226650238\n1 0.49168914556503296\n1 0.5343847274780273\n1 0.5238745212554932\n1 0.5044466257095337\n0 0.5480439066886902\n1 0.5333994030952454\n0 0.48692163825035095\n1 0.5749618411064148\n0 0.5269419550895691\n0 0.5347323417663574\n0 0.5376496911048889\n1 0.49861636757850647\n1 0.5354914665222168\n0 0.503760039806366\n1 0.565818190574646\n1 0.5425437092781067\n0 0.5251337885856628\n1 0.5272447466850281\n0 0.5440842509269714\n1 0.49124225974082947\n1 0.4675951898097992\n1 0.4457981586456299\n1 0.5107477903366089\n1 0.5088239908218384\n0 0.5554713010787964\n0 0.4663885831832886\n0 0.4789040684700012\n1 0.45231565833091736\n0 0.48625585436820984\n0 0.48490068316459656\n0 0.4898800551891327\n0 0.5479289889335632\n0 0.5659279227256775\n0 0.5519580245018005\n0 0.5364710688591003\n0 0.5654364824295044\n1 0.553878128528595\n0 0.5671566128730774\n0 0.5541385412216187\n0 0.541589617729187\n1 0.5239233374595642\n1 0.5650263428688049\n0 0.5607441663742065\n0 0.5247649550437927\n1 0.5656642317771912\n1 0.528219997882843\n0 0.5034701824188232\n1 0.475536584854126\n0 0.5046051144599915\n1 0.5072952508926392\n1 0.4998229742050171\n1 0.4977791905403137\n1 0.5171829462051392\n1 0.5493860244750977\n0 0.5516682863235474\n0 0.5427684783935547\n0 0.5961533188819885\n0 0.5022115707397461\n1 0.4511396586894989\n1 0.472433477640152\n1 0.5280117392539978\n0 0.45754730701446533\n1 0.4865305423736572\n0 0.4874947667121887\n0 0.4736732840538025\n1 0.523613691329956\n0 0.4802992641925812\n1 0.5042921900749207\n0 0.4755711853504181\n0 0.5771065354347229\n1 0.5184980034828186\n0 0.4790145456790924\n1 0.4997763931751251\n0 0.4914988875389099\n0 0.5368571877479553\n1 0.5347521901130676\n1 0.478729248046875\n1 0.4469251334667206\n1 0.4958845376968384\n0 0.4855208694934845\n1 0.4915098249912262\n1 0.46627742052078247\n1 0.4257979989051819\n1 0.5024654269218445\n1 0.4686288833618164\n0 0.5485775470733643\n1 0.5089522004127502\n0 0.5187005996704102\n1 0.6063231229782104\n1 0.592868983745575\n1 0.5652821660041809\n0 0.538360595703125\n0 0.5750173926353455\n0 0.5028910040855408\n0 0.45578017830848694\n1 0.5260308980941772\n1 0.5510714054107666\n0 0.5459314584732056\n1 0.5311086177825928\n0 0.5916005373001099\n1 0.5452562570571899\n1 0.5638125538825989\n1 0.5824530124664307\n1 0.5545468926429749\n1 0.5545260906219482\n0 0.5720897316932678\n0 0.5709519982337952\n1 0.5844793319702148\n1 0.5402488112449646\n", "output_type": "stream" } ] }, { "cell_type": "code", "source": [ "import matplotlib.pyplot as plt\n", "from sklearn.metrics import RocCurveDisplay\n", "\n", "# Plot the ROC curve using RocCurveDisplay\n", "RocCurveDisplay.from_predictions(y_test, preds)\n", "plt.title('Receiver Operating Characteristic')\n", "plt.show()\n" ], "metadata": { "execution": { "iopub.status.busy": "2024-05-31T21:46:49.455021Z", "iopub.execute_input": "2024-05-31T21:46:49.455439Z", "iopub.status.idle": "2024-05-31T21:46:49.754903Z", "shell.execute_reply.started": "2024-05-31T21:46:49.455403Z", "shell.execute_reply": "2024-05-31T21:46:49.753921Z" }, "trusted": true }, "execution_count": 12, "outputs": [ { "output_type": "display_data", "data": { "text/plain": "
", "image/png": "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" }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "X_train, X_test, y_train, y_test = tts_last_n(X, y, 252)\n", "X_opt, X_val, y_opt, y_val = tts_last_n(X_train, y_train, 252)\n", "dopt = xgb.DMatrix(X_opt, y_opt)\n", "dval = xgb.DMatrix(X_val, y_val)\n", "\n", "bst = xgb.train(params=best_params,\n", " dtrain=dopt,\n", " evals=[(dval, 'validation')],\n", " num_boost_round=n_rounds,\n", " verbose_eval=False)\n", "y_pred = bst.predict(dval)\n", "roc_auc_score(y_val, y_pred)" ], "metadata": { "execution": { "iopub.status.busy": "2024-05-31T21:51:59.298798Z", "iopub.execute_input": "2024-05-31T21:51:59.299437Z", "iopub.status.idle": "2024-05-31T21:52:01.610412Z", "shell.execute_reply.started": "2024-05-31T21:51:59.299403Z", "shell.execute_reply": "2024-05-31T21:52:01.609598Z" }, "trusted": true }, "execution_count": 13, "outputs": [ { "execution_count": 13, "output_type": "execute_result", "data": { "text/plain": "0.6034678436317781" }, "metadata": {} } ] } ] }