{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nfrom sklearn import model_selection","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv(\"../input/vinbigdata-chest-xray-abnormalities-detection/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.head(10)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df[\"kfold\"] = -1\ndf = df.sample(frac=1).reset_index(drop=True)\ny = df.class_id.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"kf = model_selection.GroupKFold(n_splits=5)\n\n# I group by image_id. Should we group by rad_id? 🤔\nfor f, (t_, v_) in enumerate(kf.split(X=df, y=y, groups=df.image_id.values)):\n    df.loc[v_, \"kfold\"] = f","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.to_csv(\"train_folds.csv\", index=False)","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}