{"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_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\nimport os\nfor 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","execution":{"iopub.status.busy":"2023-04-21T18:42:42.341544Z","iopub.execute_input":"2023-04-21T18:42:42.341972Z","iopub.status.idle":"2023-04-21T18:42:42.38831Z","shell.execute_reply.started":"2023-04-21T18:42:42.341936Z","shell.execute_reply":"2023-04-21T18:42:42.386834Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_file =\"/kaggle/input/cafa-5-protein-function-prediction/Train/train_terms.tsv\"\ndata = pd.read_csv(data_file,sep=\"\\t\",usecols=[\"EntryID\",\"term\"]).drop_duplicates()\ntrain_entries = set(data['EntryID'].unique())","metadata":{"execution":{"iopub.status.busy":"2023-04-21T18:43:15.614655Z","iopub.execute_input":"2023-04-21T18:43:15.615016Z","iopub.status.idle":"2023-04-21T18:43:20.608625Z","shell.execute_reply.started":"2023-04-21T18:43:15.614988Z","shell.execute_reply":"2023-04-21T18:43:20.607698Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(train_entries)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T18:43:22.322718Z","iopub.execute_input":"2023-04-21T18:43:22.324289Z","iopub.status.idle":"2023-04-21T18:43:22.332319Z","shell.execute_reply.started":"2023-04-21T18:43:22.324233Z","shell.execute_reply":"2023-04-21T18:43:22.331113Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_sub = pd.read_csv(\"/kaggle/input/cafa-5-protein-function-prediction/sample_submission.tsv\",sep=\"\\t\",header=None).drop_duplicates()\ndata_sub.columns = [\"EntryID\",\"term\",'score']\ntest_entries = set(data_sub['EntryID'].unique())\nlen(test_entries)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T18:45:59.943752Z","iopub.execute_input":"2023-04-21T18:45:59.944137Z","iopub.status.idle":"2023-04-21T18:46:00.173363Z","shell.execute_reply.started":"2023-04-21T18:45:59.944094Z","shell.execute_reply":"2023-04-21T18:46:00.172237Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(test_entries & train_entries)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T18:46:00.176107Z","iopub.execute_input":"2023-04-21T18:46:00.177525Z","iopub.status.idle":"2023-04-21T18:46:00.199355Z","shell.execute_reply.started":"2023-04-21T18:46:00.17745Z","shell.execute_reply":"2023-04-21T18:46:00.197927Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}