{"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"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":10418,"databundleVersionId":862236,"sourceType":"competition"},{"sourceId":23823,"databundleVersionId":1920183,"sourceType":"competition"}],"dockerImageVersionId":30066,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\n# import os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ls -lh ../input","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_2020 = pd.read_csv('../input/hpa-single-cell-image-classification/train.csv')\ntrain_2018 = pd.read_csv('../input/human-protein-atlas-image-classification/train.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_2020","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_2018","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_2018.rename(columns={'Id':'ID'}, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_merged = train_2020.merge(train_2018, on='ID', how='inner')\ntrain_merged","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"label_2020 = pd.DataFrame()\ntmp = train_merged['Label'].map(lambda x: list(map(int, x.split('|'))))\nfor i in range(19):\n    label_2020[i] = tmp.map(lambda x: i in x) * 1\n\nlabel_2020","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"label_2018 = pd.DataFrame()\ntmp = train_merged['Target'].map(lambda x: list(map(int, x.split())))\nfor i in range(19):\n    label_2018[i] = tmp.map(lambda x: i in x) * 1\n\nlabel_2018","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"label_2020[label_2018[0] == 1].mean()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_merged[(label_2018[0] == 1) & (label_2020[0] == 0)]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_merged[(label_2018[0] == 0) & (label_2020[0] == 1)]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}