{"cells":[{"metadata":{},"cell_type":"markdown","source":"## In this notebook we have generated pickles files from train parquet files\n## It is referred from youtube [video](http://www.youtube.com/watch?v=8J5Q4mEzRtY&list=PL98nY_tJQXZntH5WUtKB0bghZeKVIJHJc) by Abhishek Thakur."},{"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\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"! pip install iterative-stratification","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport os\nimport numpy as np\nimport joblib\nimport glob\nfrom tqdm import tqdm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dirname = '/kaggle/input/bengaliai-cv19/'\ndf = pd.read_csv(os.path.join(dirname, 'train.csv'))\ndf.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We have total 4 train parquet files with 200840 image details. So instead of loading them into dataframe we will store each image data in pickle files. Using this pickle files will help us to speed up the processing of images."},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir '/kaggle/working/image_pickles'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_image_pickle():\n    parquetFiles = glob.glob(os.path.join(dirname, 'train_*.parquet'))\n    for fl in parquetFiles:\n        tempDf = pd.read_parquet(fl)\n        imgIds = tempDf.image_id.values\n        tempDf = tempDf.drop('image_id',axis = 1)\n        img_values = tempDf.values\n        for i, img_id in tqdm(enumerate(imgIds), total = len(imgIds)):\n            joblib.dump(img_values[i,:], f\"/kaggle/working/image_pickles/{img_id}.pkl\")\n\n# Convert all images to pickle files to process faster\nget_image_pickle()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls '/kaggle/working/image_pickles'","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}