{"cells":[{"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 5GB 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":{},"cell_type":"markdown","source":"## Loading large training file quickly"},{"metadata":{"trusted":true},"cell_type":"code","source":"import dask.dataframe as dd\ndf = dd.read_csv('/kaggle/input/riiid-test-answer-prediction/train.csv',low_memory=False,\n                dtype={'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                      }\n                )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.dtypes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install chart_studio\nimport plotly.express as px\nimport chart_studio.plotly as py\nimport plotly.graph_objs as go\nfrom plotly.offline import iplot\nimport cufflinks\ncufflinks.go_offline()\ncufflinks.set_config_file(world_readable=True, theme='pearl')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"content_acc = train.query('answered_correctly != -1').groupby('content_id')['answered_correctly'].mean().to_dict()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import riiideducation\n\n# You can only call make_env() once, so don't lose it!\nenv = riiideducation.make_env()\niter_test = env.iter_test()\n\ndef add_content_acc(x):\n    if x in content_acc.keys():\n        return content_acc[x]\n    else:\n        return 0.5\n\n\ntest = pd.read_csv(\"/kaggle/input/riiid-test-answer-prediction/example_test.csv\")\nfor (test, sample_prediction_df) in iter_test:\n    test['answered_correctly'] = test['content_id'].apply(add_content_acc).values\n    env.predict(test.loc[test['content_type_id'] == 0, ['row_id', 'answered_correctly']])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### some references were taken from Piantic...."}],"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}