{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Riiids Educational Dataset to Pickle Format\n\nThis notebook simply transforms the input datasets into Pickle format. This format is read much faster than using pandas.read_csv and can save you some time in your tests. There might be other similar notebooks around. However, I decided to create mine.\n\nI hope you find it useful."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"INPUT_FOLDER='/kaggle/input/riiid-test-answer-prediction'\nOUTPUT_FOLDER='/kaggle/working'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"%%time\nprint('Reading the train dataset, this takes around 5 minutes...')\ntrain_df = pd.read_csv(\n    INPUT_FOLDER+'/train.csv',\n        dtype={\n            'row_id': 'int64', \n            'timestamp': 'int64', \n            'user_id': 'int32', \n            'content_id': 'int16', \n            'content_type_id': 'int8',\n            'task_container_id': 'int16', \n            'user_answer': 'int8', \n            'answered_correctly': 'int8', \n            'prior_question_elapsed_time': 'float32', \n            'prior_question_had_explanation': 'boolean'\n        }\n    )\nprint('Done.')\nprint('Save to disk...')\ntrain_df.to_pickle(OUTPUT_FOLDER+'/riiid_train.pkl.gzip')\nprint('Done')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"To load the pandas dataframe simply run..."},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nloaded_train_df = pd.read_pickle(OUTPUT_FOLDER+'/riiid_train.pkl.gzip')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loaded_train_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loaded_train_df.describe()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Probably you may want to use the train dataset without lectures. Simply, process and save a copy."},{"metadata":{"trusted":true},"cell_type":"code","source":"# That was just for demonstration, remove it\ndel loaded_train_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nprint('Remove lectures from the dataset')\ntrain_df=train_df[train_df.content_type_id==0]\nprint('Done')\nprint('Save to disk...')\ntrain_df.to_pickle(OUTPUT_FOLDER+'/riiid_train_no_lectures.pkl.gzip')\nprint('Done')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nprint('Reading questions...')\nquestions_df = pd.read_csv(INPUT_FOLDER+'/questions.csv')\nquestions_df.to_pickle(OUTPUT_FOLDER+'/questions.pkl.gzip')\nprint('Done.')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nprint('Reading lectures...')\nlectures_df = pd.read_csv(INPUT_FOLDER+'/lectures.csv')\nlectures_df.to_pickle(OUTPUT_FOLDER+'/lectures.pkl.gzip')\nprint('Done')","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}