{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"94ea1034-d175-cd55-e02d-ee46a72e8e70"},"outputs":[],"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport csv\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"f83358b4-bce4-55e0-eb50-02528282c890"},"outputs":[],"source":"import os\n\nmemory = 10 # stands for 10GB, write your memory here\nlimit = 114434838 / 10 * memory \n\nleak = {}\nfor c,row in enumerate(csv.DictReader(open('../input/promoted_content.csv'))):\n    if row['document_id'] != '':\n        leak[row['document_id']] = 1 \n"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"58c26483-0032-ee80-5c75-7ea3d3e91621"},"outputs":[],"source":"print(leak)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b0a76139-b882-8995-204c-60a0ab95035d"},"outputs":[],"source":""}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.5.2"}},"nbformat":4,"nbformat_minor":0}