{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"## Version 1:\n## int 32 for user id\n## Simple Mean of answered Correctly for Each  User Id","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Description :\n1. In this notebook I have tried First Submission of My Competition .\n2. Rather than simply Taking Mean of Content Ids , I am trying to take mean of User Ids and Based on their number of correct answers we are predicting ! \n3. This is obiviously not a good solution as it causes target leakage describe [here](https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/189437)\n4. More to add is Rolling Average and Bayesian Averages ! "},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import riiideducation\nimport dask.dataframe as dd\n\nenv = riiideducation.make_env()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"user_acc = dd.read_csv('/kaggle/input/riiid-test-answer-prediction/train.csv', \n                usecols=[2,7], dtype={'user_id': 'int32','answered_correctly':'int8'}\n              ).query('answered_correctly != -1').groupby('user_id')['answered_correctly'].mean().compute().to_dict()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def add_user_acc(x):\n    if x in user_acc.keys():\n        return user_acc[x]\n    else:\n        return 0.5\n\niter_test = env.iter_test()\nbatch = 0 \nfor (test_df, sample_prediction_df) in iter_test:\n    test_df['answered_correctly'] = test_df['user_id'].apply(add_user_acc).values\n    env.predict(test_df.loc[test_df['content_type_id'] == 0, ['row_id', 'answered_correctly']])\n    print(\"Batch Done : \" , batch)\n    batch += 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}