{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nfrom sklearn.preprocessing import LabelEncoder","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# settings\n\nnfolds = 10\n\ndata_folder = '../input/rsna-str-pulmonary-embolism-detection/'\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# data\ntrain = pd.read_csv(data_folder + 'train.csv')\ntest = pd.read_csv(data_folder + 'test.csv')\n\nxfolds = train[['StudyInstanceUID', 'SeriesInstanceUID']].copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# non-overlapping folds\nle = LabelEncoder()\nx = le.fit_transform(xfolds['StudyInstanceUID'])\nxfolds['fold_st'] = x%nfolds\n\nx = le.fit_transform(xfolds['SeriesInstanceUID'])\nxfolds['fold_sr'] = x%nfolds\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xfolds.to_csv('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}