{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from sklearn.model_selection import GroupKFold \nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"COMP_PATH = '../input/ranzcr-clip-catheter-line-classification/'\n\nN_SPLITS = 5","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv(COMP_PATH+'train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"targets = ['ETT - Abnormal', 'ETT - Borderline',\n       'ETT - Normal', 'NGT - Abnormal', 'NGT - Borderline',\n       'NGT - Incompletely Imaged', 'NGT - Normal', 'CVC - Abnormal',\n       'CVC - Borderline', 'CVC - Normal', 'Swan Ganz Catheter Present']","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"gkf =  GroupKFold(n_splits = N_SPLITS)\n\ndf_train[\"fold\"] = -1\n\ndf_train = df_train.sample(frac=1).reset_index(drop=True)\n\nresult = []   \nfor fold, (train_idx, val_idx) in enumerate(gkf.split(df_train, df_train[targets], df_train['PatientID'])):\n    print(len(train_idx), len(val_idx))\n    df_train.loc[val_idx, 'fold'] = fold","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = plt.figure(figsize=(16, 6))\n\nax = sns.countplot(df_train['fold'])\n\nax.tick_params(axis='x', labelsize=20)\nax.tick_params(axis='y', labelsize=20)\nax.set_xticklabels([f'{value} ({count:,})' for value, count in df_train['fold'].value_counts().sort_index().to_dict().items()])\nax.set_xlabel('Folds', size=20, labelpad=20)\nax.set_ylabel('Samples', size=20, labelpad=20)\n\nplt.title(f'Training Set Number of Samples in Folds', size=20, pad=20)\n\nplt.show()\nsplits = df_train.groupby('fold').sum()[targets] \\\n        .reset_index(drop=True) \\\n        .T \\\n        .rename(columns={fold - 1: fold for fold in sorted(df_train['fold'].unique())}) \\\n        .reset_index() \\\n        .rename(columns={'index': 'Target'})\n\nsplits = pd.melt(splits, id_vars=['Target'], value_name='Count')\nsplits['Total'] = splits.groupby('Target')['Count'].transform('sum')\nsplits = splits.sort_values(by=['Total', 'Target'], ascending=False).reset_index(drop=True)\nsplits['variable'] = 'Fold ' + splits['variable'].astype(str)\n\nfig = plt.figure(figsize=(16, 8), dpi=100)\n\nsns.barplot(x=splits['Count'],\n            y=splits['Target'],\n            hue=splits['variable'])\n\nplt.xlabel('')\nplt.ylabel('')\nplt.tick_params(axis='x', labelsize=15)\nplt.tick_params(axis='y', labelsize=15)\nplt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0, prop={'size': 20})\nplt.title('Multi Label Stratified GroupKFold Target Counts', size=18, pad=18)\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.to_csv(f'train_{N_SPLITS}_kfolds.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}