{"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 pandas as pd\nimport gc\nimport copy\nimport os\nimport sys\n\nfrom pathlib import Path\nfrom datetime import datetime, date, time, timedelta\nfrom dateutil import relativedelta\n\nimport pyarrow.parquet as pq\nimport pyarrow as pa","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n#https://stackoverflow.com/questions/25962114/how-do-i-read-a-large-csv-file-with-pandas\n\n\ndef process_big_csv(chunk, dest_file):\n    #---convert float64 to float32--------\n    float64_cols = chunk.select_dtypes(include=['float64']).columns.tolist()\n    chunk[float64_cols] = np.float32(chunk[float64_cols].values)\n    #---convert int64 to int32\n    int64_cols = chunk.select_dtypes(include=['int64']).columns.tolist()\n    chunk[int64_cols] = np.int32(chunk[int64_cols].values)\n    \n    #-- save to parquet file\n    table = pa.Table.from_pandas(chunk)\n    pq.write_table(table, dest_file, compression = 'GZIP')\n    \n    del table, chunk\n    gc.collect()\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nraw_file = '/kaggle/input/amex-default-prediction/train_labels.csv'\ndest_file = 'train_labels.parquet'\ndf = pd.read_csv(raw_file)\nprocess_big_csv(df, dest_file)\n\ndel df\ngc.collect()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nraw_file = '/kaggle/input/amex-default-prediction/sample_submission.csv'\ndest_file = 'sample_submission.parquet'\ndf = pd.read_csv(raw_file)\nprocess_big_csv(df, dest_file)\n\ndel df\ngc.collect()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nchunksize = 5e5 #500,000 500k samples per file\nprint('chunksize=', chunksize)\n\nraw_file = '/kaggle/input/amex-default-prediction/test_data.csv'\nwith pd.read_csv(raw_file, chunksize=chunksize) as reader:\n    for i, chunk in enumerate(reader):\n        dest_file = f'test_data_{i+1}.parquet'\n        process_big_csv(chunk, dest_file)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nchunksize = 5e5 #500,000. 500k samples per file\nprint('chunksize=', chunksize)\n\nraw_file = '/kaggle/input/amex-default-prediction/train_data.csv'\nwith pd.read_csv(raw_file, chunksize=chunksize) as reader:\n    for i, chunk in enumerate(reader):\n        dest_file = f'train_data_{i+1}.parquet'\n        process_big_csv(chunk, dest_file)","metadata":{},"execution_count":null,"outputs":[]}]}