{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"45829a78-9ac5-64ab-a725-24b6a5a8e472"},"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)\n\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\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\np = sns.color_palette()\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"f2571706-e8b7-341d-0e1a-d5f923046f49"},"outputs":[],"source":"df_train = pd.read_csv('../input/clicks_train.csv')\ndf_test = pd.read_csv('../input/clicks_test.csv')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"a6daa770-5928-c92f-a147-20e32335e098"},"outputs":[],"source":"sizes_train = df_train.groupby('display_id')['ad_id'].count().value_counts()\nsizes_test = df_test.groupby('display_id')['ad_id'].count().value_counts()\nsizes_train = sizes_train / np.sum(sizes_train)\nsizes_test = sizes_test / np.sum(sizes_test)\n\nplt.figure(figsize=(12,4))\nsns.barplot(sizes_train.index, sizes_train.values, alpha=0.8, color=p[0], label='train')\nsns.barplot(sizes_test.index, sizes_test.values, alpha=0.6, color=p[1], label='test')\nplt.legend()\nplt.xlabel('Number of Ads in display', fontsize=12)\nplt.ylabel('Proportion of set', fontsize=12)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"3034d6d1-b163-c0e4-e03d-1d3391aab4b8"},"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}