{"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom glob import glob\nfrom time import time\nfrom tqdm import tqdm\nfrom skimage import io\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install /kaggle/input/fastparquet/python_snappy-0.5.4-cp36-cp36m-linux_x86_64.whl\n!pip install /kaggle/input/fastparquet/thrift-0.13.0-cp36-cp36m-linux_x86_64.whl\n!pip install /kaggle/input/fastparquet/fastparquet-0.3.2-cp36-cp36m-linux_x86_64.whl","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"filepaths = glob('/kaggle/input/bengaliai/256_train/256/*.png')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(filepaths)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Loading from .png**, thanks to Peter. https://www.kaggle.com/c/bengaliai-cv19/discussion/122467"},{"metadata":{"trusted":true},"cell_type":"code","source":"for path in tqdm(filepaths):\n    img = io.imread(path)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Loading from .parquet**"},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in tqdm(range(4)):\n    df = pd.read_parquet('/kaggle/input/bengaliai-cv19/train_image_data_{}.parquet'.format(i))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Loading from .parquet with fastparquet**, thanks to Vladislav https://www.kaggle.com/vladislavleketush/fast-parquet-loading-example"},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in tqdm(range(4)):\n    df = pd.read_parquet('/kaggle/input/bengaliai-cv19/train_image_data_{}.parquet'.format(i), engine='fastparquet')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Loading from .feather**, thanks to corochann https://www.kaggle.com/corochann/bangali-ai-super-fast-data-loading-with-feather"},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in tqdm(range(4)):\n    df = pd.read_feather('/kaggle/input/bengaliaicv19feather/train_image_data_{}.feather'.format(i))","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":1}