{"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_minor":4,"nbformat":4,"cells":[{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd \nprint('successfull')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dtypes = {\"session_id\" : 'int64',\n          \"index\" : np.int16,\n          \"elapsed_time\" : np.int32,\n          \"event_name\" : 'category', \n          \"name\" : 'category',\n          \"level\" : np.int8,\n          \"page\" : np.float16,\n          \"room_coor_x\" : np.float16,\n          \"room_coor_y\" : np.float16,\n          \"screen_coor_x\" : np.float16,\n          \"screen_coor_y\" : np.float16,\n          \"hover_duration\" : np.float32,\n          \"text\" : 'category',\n          \"fqid\" : 'category',\n          \"room_fqid\" : 'category',\n          \"text_fqid\" : 'category',\n          \"fullscreen\" : np.int8,\n          \"hq\" : np.int8,\n          \"music\" : np.int8,\n          \"level_group\" : 'category'\n         }\n\nuse_col = ['session_id', 'index', 'elapsed_time', 'event_name', 'name', 'level', 'page', 'room_coor_x', 'room_coor_y', \n           'screen_coor_x', 'screen_coor_y', 'hover_duration', 'text', 'fqid', 'room_fqid', 'text_fqid', 'level_group']\ndf = pd.read_csv('/kaggle/input/predict-student-performance-from-game-play/train.csv', dtype = dtypes, usecols = use_col)\nprint(format(df.shape))","metadata":{},"execution_count":null,"outputs":[]}]}