{"cells":[{"metadata":{},"cell_type":"markdown","source":"# What's your CV method?\n- I observed the oof using k-fold, and found that the increase in the number of folds increases the oof_rmse, but the public LB decreases.\n\n- LGBM parmeter(For the fold-12, n_estimators= 1000 learning_rate=0.1 was used as a limited time)\n        n_estimators=6000,\n        learning_rate=0.05,\n        feature_fraction=0.7,\n        subsample=0.4,\n        num_leaves=40,\n        metric='rmse'\n\n\n\n- All variables are the same."},{"metadata":{},"cell_type":"markdown","source":"# OOF_RMSE AND Public LB\nThe more the fold number increases, the lower the oof_rmse and the more public lb increases.\n- [2-fold](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22526687)   \noof_rmse : 1.42 Public LB : 1.11\n- [3-fold](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22513136)   \noof_rmse : 1.35 Public LB : 1.12\n- [4-fold](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22340799)   \noof_rmse : 1.27 Public LB : 1.16\n- [5-fold](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22371767)   \noof_rmse : 1.23 Public LB : 1.17\n- [6-fold](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22371793)   \noof_rmse : 1.20 Public LB : 1.18\n- [12-fold](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22371727)   \noof_rmse : 1.10 Public LB : 1.20"},{"metadata":{},"cell_type":"markdown","source":"# Why is this happening?\nBecause of simple k-fold, I think it will be learned and evaluated by roughly monthly.\n\n        Example(4-fold)\n        fold0 - January ~ March \n        fold1 - April ~ June \n        fold2 - July ~ September\n        fold3 - October ~ December"},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":false},"cell_type":"code","source":"## Function to reduce the DF size\ndef reduce_mem_usage(df, verbose=True):\n    numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n    start_mem = df.memory_usage().sum() / 1024**2    \n    for col in df.columns:\n        col_type = df[col].dtypes\n        if col_type in numerics:\n            c_min = df[col].min()\n            c_max = df[col].max()\n            if str(col_type)[:3] == 'int':\n                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n                    df[col] = df[col].astype(np.int8)\n                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n                    df[col] = df[col].astype(np.int16)\n                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n                    df[col] = df[col].astype(np.int32)\n                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n                    df[col] = df[col].astype(np.int64)  \n            else:\n                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n                    df[col] = df[col].astype(np.float16)\n                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n                    df[col] = df[col].astype(np.float32)\n                else:\n                    df[col] = df[col].astype(np.float64)    \n    end_mem = df.memory_usage().sum() / 1024**2\n    if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem))\n    return df","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-input":true,"_kg_hide-output":true,"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":false},"cell_type":"code","source":"import pandas as pd \nimport numpy as np\nfrom sklearn.model_selection import KFold\nimport matplotlib.pyplot as plt\nimport os\nimport gc\n\ndirectory = '/kaggle/input/ashrae-energy-prediction'\nos.listdir(directory)\ndf_train = pd.read_csv(directory+'/train.csv')\ndf_train  = reduce_mem_usage(df_train)\ndf_train[\"timestamp\"] = pd.to_datetime(df_train[\"timestamp\"])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# k-fold val_set_range"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"folds = [4, 2, 12]\nfor folds in folds:\n    fold = KFold(n_splits=folds, shuffle=False, random_state=42)\n    print('-'*50)\n    print(folds,'-fold')\n    for fold_, (trn_idx, val_idx)  in enumerate(fold.split(df_train, df_train['meter_reading'])):\n        tr_x, tr_y = df_train.iloc[trn_idx], df_train['meter_reading'][trn_idx]\n        vl_x, vl_y = df_train.iloc[val_idx], df_train['meter_reading'][val_idx]\n        print('fold :', fold_)\n        print('val_set_range : ',vl_x['timestamp'].min(), vl_x['timestamp'].max())    \ndel tr_x, tr_y, vl_x, vl_y","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Mean Meter reading"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"# Reference - https://www.kaggle.com/nroman/eda-for-ashrae\nfig, axes = plt.subplots(1, 1, figsize=(14, 6), dpi=100)\ndf_train[['timestamp', 'meter_reading']].set_index('timestamp').resample('M').mean()['meter_reading'].plot(ax=axes, label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\ndf_train[['timestamp', 'meter_reading']].set_index('timestamp').resample('H').mean()['meter_reading'].plot(ax=axes, label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\ndf_train[['timestamp', 'meter_reading']].set_index('timestamp').resample('D').mean()['meter_reading'].plot(ax=axes, label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\naxes.set_title('Mean Meter reading by hour and day, month', fontsize=16);\naxes.legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Mean Meter reading by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"df_train['meter'] = df_train['meter'].map({0: 'electricity', 1: 'chilledwater', 2: 'steam', 3: 'hotwater'})\ncol = ['electricity', 'chilledwater', 'steam', 'hotwater']\nfig, axes = plt.subplots(4, 1, figsize=(14, 30), dpi=100)\nfor i, col in enumerate(col):\n    train = df_train[df_train['meter']==col].copy()\n    train[['timestamp', 'meter_reading']].set_index('timestamp').resample('M').mean()['meter_reading'].plot(ax=axes[i], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'meter_reading']].set_index('timestamp').resample('H').mean()['meter_reading'].plot(ax=axes[i], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'meter_reading']].set_index('timestamp').resample('D').mean()['meter_reading'].plot(ax=axes[i], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i].set_title(col +' Mean Meter reading by hour and day, month', fontsize=16);\n    axes[i].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 2-fold predict plot"},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":false,"trusted":false},"cell_type":"code","source":"del df_train\ndel train\n\ndf_test = pd.read_csv(directory+'/test.csv')\ndf_test = df_test['meter']\n\ngc.collect()\n\nfold2 = pd.read_csv('/kaggle/input/2fold/submission.csv')\nfold2  = reduce_mem_usage(fold2)\nfold2[\"timestamp\"] = pd.to_datetime(fold2[\"timestamp\"])\nfold2 = pd.concat([fold2,df_test],axis=1)\nfold2['meter'] = fold2['meter'].map({0: 'electricity', 1: 'chilledwater', 2: 'steam', 3: 'hotwater'})\nfold2.head()\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"column = ['fold0_meter_reading', 'fold1_meter_reading','fold_mean_meter_reading']\nfig, axes = plt.subplots(3, 1, figsize=(14, 18), dpi=100)\nfor i, col in enumerate(column):\n    fold2[['timestamp', col]].set_index('timestamp').resample('M').mean()[col].plot(ax=axes[i], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    fold2[['timestamp', col]].set_index('timestamp').resample('H').mean()[col].plot(ax=axes[i], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    fold2[['timestamp', col]].set_index('timestamp').resample('D').mean()[col].plot(ax=axes[i], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold0_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"column = ['electricity', 'chilledwater', 'steam', 'hotwater']\nfig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold2[fold2['meter']==col].copy()\n    train[['timestamp', 'fold0_meter_reading']].set_index('timestamp').resample('M').mean()['fold0_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold0_meter_reading']].set_index('timestamp').resample('H').mean()['fold0_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold0_meter_reading']].set_index('timestamp').resample('D').mean()['fold0_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold1_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold2[fold2['meter']==col].copy()\n    train[['timestamp', 'fold1_meter_reading']].set_index('timestamp').resample('M').mean()['fold1_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold1_meter_reading']].set_index('timestamp').resample('H').mean()['fold1_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold1_meter_reading']].set_index('timestamp').resample('D').mean()['fold1_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold_mean_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold2[fold2['meter']==col].copy()\n    train[['timestamp', 'fold_mean_meter_reading']].set_index('timestamp').resample('M').mean()['fold_mean_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold_mean_meter_reading']].set_index('timestamp').resample('H').mean()['fold_mean_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold_mean_meter_reading']].set_index('timestamp').resample('D').mean()['fold_mean_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 4-fold predict plot"},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":false,"trusted":false},"cell_type":"code","source":"del fold2\ndel train\ngc.collect()\n\nfold4 = pd.read_csv('/kaggle/input/4fold/submission.csv')\nfold4  = reduce_mem_usage(fold4)\nfold4[\"timestamp\"] = pd.to_datetime(fold4[\"timestamp\"])\nfold4.head()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"column = ['fold0_meter_reading', 'fold1_meter_reading','fold2_meter_reading', 'fold3_meter_reading','fold_mean_meter_reading']\nfig, axes = plt.subplots(5, 1, figsize=(14, 30), dpi=100)\nfor i, col in enumerate(column):\n    fold4[['timestamp', col]].set_index('timestamp').resample('M').mean()[col].plot(ax=axes[i], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    fold4[['timestamp', col]].set_index('timestamp').resample('H').mean()[col].plot(ax=axes[i], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    fold4[['timestamp', col]].set_index('timestamp').resample('D').mean()[col].plot(ax=axes[i], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i].legend();\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold0_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fold4 = pd.concat([fold4,df_test],axis=1)\nfold4['meter'] = fold4['meter'].map({0: 'electricity', 1: 'chilledwater', 2: 'steam', 3: 'hotwater'})\ncolumn = ['electricity', 'chilledwater', 'steam', 'hotwater']\nfig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold4[fold4['meter']==col].copy()\n    train[['timestamp', 'fold0_meter_reading']].set_index('timestamp').resample('M').mean()['fold0_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold0_meter_reading']].set_index('timestamp').resample('H').mean()['fold0_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold0_meter_reading']].set_index('timestamp').resample('D').mean()['fold0_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold1_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold4[fold4['meter']==col].copy()\n    train[['timestamp', 'fold1_meter_reading']].set_index('timestamp').resample('M').mean()['fold1_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold1_meter_reading']].set_index('timestamp').resample('H').mean()['fold1_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold1_meter_reading']].set_index('timestamp').resample('D').mean()['fold1_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold2_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold4[fold4['meter']==col].copy()\n    train[['timestamp', 'fold2_meter_reading']].set_index('timestamp').resample('M').mean()['fold2_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold2_meter_reading']].set_index('timestamp').resample('H').mean()['fold2_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold2_meter_reading']].set_index('timestamp').resample('D').mean()['fold2_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold3_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold4[fold4['meter']==col].copy()\n    train[['timestamp', 'fold3_meter_reading']].set_index('timestamp').resample('M').mean()['fold3_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold3_meter_reading']].set_index('timestamp').resample('H').mean()['fold3_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold3_meter_reading']].set_index('timestamp').resample('D').mean()['fold3_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## fold_mean_predict by meter"},{"metadata":{"_kg_hide-input":true,"trusted":false},"cell_type":"code","source":"fig, axes = plt.subplots(2, 2, figsize=(20, 12), dpi=100)\nfor i, col in enumerate(column):\n    train = fold4[fold4['meter']==col].copy()\n    train[['timestamp', 'fold_mean_meter_reading']].set_index('timestamp').resample('M').mean()['fold_mean_meter_reading'].plot(ax=axes[i%2][i//2], label='By month', alpha=1).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold_mean_meter_reading']].set_index('timestamp').resample('H').mean()['fold_mean_meter_reading'].plot(ax=axes[i%2][i//2], label='By hour', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    train[['timestamp', 'fold_mean_meter_reading']].set_index('timestamp').resample('D').mean()['fold_mean_meter_reading'].plot(ax=axes[i%2][i//2], label='By day', alpha=0.7).set_ylabel('Meter reading', fontsize=14);\n    axes[i%2][i//2].set_title(col + 'by hour and day, month', fontsize=16);\n    axes[i%2][i//2].legend();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# thinking\nat the above picture January to March is a moderate MMR(Mean Meter Reading) but a very high MMR from March to July, then July to Desember shows almost zero, although it is increasing at November\n\n- 2-Fold recorded the highest public lb(1.11); fold0 train until June before MMR falls, and fold1 train after that, then averages two results I don't know exactly, but I think this training affected model performance\n\n- i'll test 2-fold at a reduced timestamp.\n\n- Depending on the variable, the method of cross-validation can also be affected.\n\n- Predictive Mean meter reading is too low for training Mean meter reading because The mean meter reading by meter type has a large difference in value. Therefore, I think that if you perform proper k-fold verification by meter, you will get a good score."},{"metadata":{},"cell_type":"markdown","source":"# Reference\n- https://www.kaggle.com/nroman/eda-for-ashrae\n- https://www.kaggle.com/ryches/simple-lgbm-solution\n- https://www.kaggle.com/c/ashrae-energy-prediction/discussion/113286#latest-654648\n"},{"metadata":{},"cell_type":"markdown","source":"\n# I'll try\nI'm going to try various cross-validations and upload them to the kernel. If you have idea, please mention it\n- additional variable\n- k-fold per site_ID, meter, Buiding_id\n- 2-fold at a reduced timestamp\n\n"},{"metadata":{},"cell_type":"markdown","source":"# Try\n- [4-kfold by site ID](https://www.kaggle.com/kimtaegwan/lgbm-baseline-what-s-your-cv-method?scriptVersionId=22377656) Public LB : 2.50\n- [GROUP(Month) K-Fold](https://www.kaggle.com/kimtaegwan/what-s-your-cv-method?scriptVersionId=22905017) Public LB :1.10\n- train_test_spilt \n      test_size:0.5(Public LB :1.23)\n      test_size:0.1(Public LB :1.22)"},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"2de0ac8c87c24d49bec4f88117063e12":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":"initial"}},"39909fceb1a04d67987c529e133647b5":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"IntProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"IntProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"100%","description_tooltip":null,"layout":"IPY_MODEL_708784a3692b458e8d6bf4a3dae59a31","max":50,"min":0,"orientation":"horizontal","style":"IPY_MODEL_2de0ac8c87c24d49bec4f88117063e12","value":50}},"708784a3692b458e8d6bf4a3dae59a31":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"793a7513a04c491994afde7c0ad62cc8":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"871e9cc012eb4a469b2255261eb067cc":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8cef185aace44a54a64ea8dcead953af":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a5e6903c43ff4088b6860eebca282824":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_8cef185aace44a54a64ea8dcead953af","placeholder":"​","style":"IPY_MODEL_793a7513a04c491994afde7c0ad62cc8","value":" 50/50 [1:40:21&lt;00:00, 120.43s/it]"}},"e0ed1cbebd434d4f924f1b7305928938":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_39909fceb1a04d67987c529e133647b5","IPY_MODEL_a5e6903c43ff4088b6860eebca282824"],"layout":"IPY_MODEL_871e9cc012eb4a469b2255261eb067cc"}}},"version_major":2,"version_minor":0}}},"nbformat":4,"nbformat_minor":1}