{"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":"2023-06-23T09:52:37.897369Z","iopub.execute_input":"2023-06-23T09:52:37.897768Z","iopub.status.idle":"2023-06-23T09:52:37.914024Z","shell.execute_reply.started":"2023-06-23T09:52:37.897729Z","shell.execute_reply":"2023-06-23T09:52:37.912901Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nimport pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\n# Required for progressbar widget\nimport progressbar","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:52:50.638534Z","iopub.execute_input":"2023-06-23T09:52:50.638975Z","iopub.status.idle":"2023-06-23T09:52:50.645203Z","shell.execute_reply.started":"2023-06-23T09:52:50.638941Z","shell.execute_reply":"2023-06-23T09:52:50.643774Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Load DataSet**","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/cafa-5-protein-function-prediction/Train/train_terms.tsv\",sep=\"\\t\")\nprint(df.shape)","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:52:53.632775Z","iopub.execute_input":"2023-06-23T09:52:53.633204Z","iopub.status.idle":"2023-06-23T09:52:56.556312Z","shell.execute_reply.started":"2023-06-23T09:52:53.63317Z","shell.execute_reply":"2023-06-23T09:52:56.555211Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:52:59.446519Z","iopub.execute_input":"2023-06-23T09:52:59.446908Z","iopub.status.idle":"2023-06-23T09:52:59.459313Z","shell.execute_reply.started":"2023-06-23T09:52:59.446878Z","shell.execute_reply":"2023-06-23T09:52:59.458158Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df1 = pd.read_csv('/kaggle/input/cafa-5-protein-function-prediction/Train/train_taxonomy.tsv',sep=\"\\t\")\nprint(df1.shape)","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:53:01.385953Z","iopub.execute_input":"2023-06-23T09:53:01.386358Z","iopub.status.idle":"2023-06-23T09:53:01.501016Z","shell.execute_reply.started":"2023-06-23T09:53:01.386326Z","shell.execute_reply":"2023-06-23T09:53:01.499906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df1.head()","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:53:02.568533Z","iopub.execute_input":"2023-06-23T09:53:02.569961Z","iopub.status.idle":"2023-06-23T09:53:02.582039Z","shell.execute_reply.started":"2023-06-23T09:53:02.569907Z","shell.execute_reply":"2023-06-23T09:53:02.580477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df1[:5]","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:53:03.612479Z","iopub.execute_input":"2023-06-23T09:53:03.612972Z","iopub.status.idle":"2023-06-23T09:53:03.627892Z","shell.execute_reply.started":"2023-06-23T09:53:03.612927Z","shell.execute_reply":"2023-06-23T09:53:03.626865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n\ntrain_embeddings = np.load('/kaggle/input/cafa-5-protein-function-prediction/Train/train_taxonomy.tsv')\n\n# Create a list of column names using a list comprehension\ncolumn_names = [\"Column_\" + str(i) for i in range(1, train_embeddings.shape[1]+1)]\n\n# Create a DataFrame from the embeddings numpy array\ntrain_df = pd.DataFrame(train_embeddings, columns=column_names)\nprint(train_df.shape)\n","metadata":{"execution":{"iopub.status.busy":"2023-06-23T09:54:08.197686Z","iopub.execute_input":"2023-06-23T09:54:08.198234Z","iopub.status.idle":"2023-06-23T09:54:08.294408Z","shell.execute_reply.started":"2023-06-23T09:54:08.198194Z","shell.execute_reply":"2023-06-23T09:54:08.291015Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}