{"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\n#for 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":"# Install dask lib"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"#!pip install vaex\n!pip install \"dask[complete]\"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Read Full train data in dask dataframe"},{"metadata":{"trusted":true},"cell_type":"code","source":"import dask\nimport dask.dataframe as dd\n\n# It is just a logical read , nothing in memory at this moment\ndf = dd.read_csv('../input/riiid-test-answer-prediction/train.csv',low_memory=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# As a logical read only column info is there not about rows \ndf.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Delayed for rows just to \ndf.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# but you can read as you want \n# like simple dataframe\n# find more on dask site https://stories.dask.org/en/latest/\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loop over whole dataframe"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n# Loop over 1,000,000 ( 1 million )\n# look time taken\nfor index , data in df.iterrows():\n    #print(data)\n    #print(20*'--')\n    if index == 1000*1000 :\n        break\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\n# Find correct answer of each user \ndf.groupby(df.user_id).answered_correctly.sum().compute()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# From above output last user id is 2147482888     \n# lets check tail of dataframe\ndf.tail()","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}