{"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":"2023-04-21T19:49:02.835807Z","iopub.execute_input":"2023-04-21T19:49:02.836272Z","iopub.status.idle":"2023-04-21T19:49:02.851022Z","shell.execute_reply.started":"2023-04-21T19:49:02.836221Z","shell.execute_reply":"2023-04-21T19:49:02.849212Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load train terms\nShuld list all the proteins with a GO annotation","metadata":{}},{"cell_type":"code","source":"train_terms = pd.read_csv('/kaggle/input/cafa-5-protein-function-prediction/Train/train_terms.tsv',sep='\\t')\ntrain_terms.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T19:49:28.668238Z","iopub.execute_input":"2023-04-21T19:49:28.669357Z","iopub.status.idle":"2023-04-21T19:49:30.865755Z","shell.execute_reply.started":"2023-04-21T19:49:28.669306Z","shell.execute_reply":"2023-04-21T19:49:30.864493Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_terms_unique = set(train_terms['term'])","metadata":{"execution":{"iopub.status.busy":"2023-04-21T19:50:06.099399Z","iopub.execute_input":"2023-04-21T19:50:06.100288Z","iopub.status.idle":"2023-04-21T19:50:06.726031Z","shell.execute_reply.started":"2023-04-21T19:50:06.100241Z","shell.execute_reply":"2023-04-21T19:50:06.724529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load IA dataset\n\n1) It shuld list all the weights used by the scoring function\n\n2) does weights = 0 means no need to predict this term??","metadata":{}},{"cell_type":"code","source":"IA = pd.read_csv('/kaggle/input/cafa-5-protein-function-prediction/IA.txt',sep='\\t',header=None,index_col=None)\nIA.columns = ['term','score']\nprint(IA.shape)","metadata":{"execution":{"iopub.status.busy":"2023-04-21T19:52:20.289408Z","iopub.execute_input":"2023-04-21T19:52:20.289852Z","iopub.status.idle":"2023-04-21T19:52:20.340028Z","shell.execute_reply.started":"2023-04-21T19:52:20.289814Z","shell.execute_reply":"2023-04-21T19:52:20.338389Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Plot weights for protein in/out of train","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfig,ax=plt.subplots(figsize=(8,4))\nIA[~IA['term'].isin(train_terms_unique)].score.plot(kind='hist',histtype='step',ax=ax,label='no_data',density=True )\nIA[IA['term'].isin(train_terms_unique)].score.plot(kind='hist',histtype='step',ax=ax,label='in_train',density=True )\nplt.legend()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-04-21T19:57:43.452748Z","iopub.execute_input":"2023-04-21T19:57:43.454155Z","iopub.status.idle":"2023-04-21T19:57:43.688541Z","shell.execute_reply.started":"2023-04-21T19:57:43.454107Z","shell.execute_reply":"2023-04-21T19:57:43.687221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}