{"cells":[{"metadata":{},"cell_type":"markdown","source":"The purpose of this notebook is to share a useful way for the interpretation of timestamp. The final result is 2 new columns, one called month and the other one day. These 2 columns report for each user_id the month and the day of the intereation with the App. In this way a cluster analysis could be performed."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/riiid-test-answer-prediction/train.csv', nrows=1000000)\nlectures = pd.read_csv('../input/riiid-test-answer-prediction/lectures.csv')\nquestions = pd.read_csv('../input/riiid-test-answer-prediction/questions.csv')\nexample_test = pd.read_csv('../input/riiid-test-answer-prediction/example_test.csv')\nexample_sample_submission = pd.read_csv('../input/riiid-test-answer-prediction/example_sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from datetime import datetime\ntrain_df['timestamp'] = pd.to_datetime(train_df['timestamp'], unit='ms',origin='2017-1-1')\ntrain_df['month']=(train_df.timestamp.dt.month)\ntrain_df['day']=(train_df.timestamp.dt.day)\ntrain_df=train_df.drop(columns=['timestamp'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['task_container_id'] = (\n    train_df\n    .groupby('user_id')['task_container_id']\n    .transform(lambda x : pd.factorize(x)[0])\n    .astype('int16')\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = train_df.sort_values(by=['user_id','row_id'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df","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}