{"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","execution":{"iopub.status.busy":"2022-10-01T01:40:06.594134Z","iopub.execute_input":"2022-10-01T01:40:06.595739Z","iopub.status.idle":"2022-10-01T01:40:06.631805Z","shell.execute_reply.started":"2022-10-01T01:40:06.595515Z","shell.execute_reply":"2022-10-01T01:40:06.630915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Convert to Parquet","metadata":{}},{"cell_type":"markdown","source":"Reading the original file and compressing it takes a while.","metadata":{}},{"cell_type":"code","source":"%%time\nfor i in range(10):\n    df = pd.read_csv(f'/kaggle/input/tabular-playground-series-oct-2022/train_{i}.csv')\n    df.to_parquet(f'train_{i}.parquet.gzip', compression='gzip')\n    print('Done with File', i)\n    \ndf = pd.read_csv(f'/kaggle/input/tabular-playground-series-oct-2022/test.csv')\ndf.to_parquet(f'test.parquet.gzip', compression='gzip')","metadata":{"execution":{"iopub.status.busy":"2022-10-01T01:58:51.303492Z","iopub.execute_input":"2022-10-01T01:58:51.311533Z","iopub.status.idle":"2022-10-01T01:59:09.678402Z","shell.execute_reply.started":"2022-10-01T01:58:51.311177Z","shell.execute_reply":"2022-10-01T01:59:09.677426Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Check Speedup","metadata":{}},{"cell_type":"markdown","source":"See the loading time difference between the original CSV and the compressed Parquet file.","metadata":{"execution":{"iopub.status.busy":"2022-10-01T01:56:15.459236Z","iopub.execute_input":"2022-10-01T01:56:15.459774Z","iopub.status.idle":"2022-10-01T01:56:15.469188Z","shell.execute_reply.started":"2022-10-01T01:56:15.459734Z","shell.execute_reply":"2022-10-01T01:56:15.466786Z"}}},{"cell_type":"code","source":"%%time\npd.read_csv('/kaggle/input/tabular-playground-series-oct-2022/train_0.csv')","metadata":{"execution":{"iopub.status.busy":"2022-10-01T01:59:45.503314Z","iopub.execute_input":"2022-10-01T01:59:45.503765Z","iopub.status.idle":"2022-10-01T02:00:06.721594Z","shell.execute_reply.started":"2022-10-01T01:59:45.503728Z","shell.execute_reply":"2022-10-01T02:00:06.720421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\npd.read_parquet('train_0.parquet.gzip')","metadata":{"execution":{"iopub.status.busy":"2022-10-01T01:56:21.070554Z","iopub.execute_input":"2022-10-01T01:56:21.071084Z","iopub.status.idle":"2022-10-01T01:56:24.415633Z","shell.execute_reply.started":"2022-10-01T01:56:21.071039Z","shell.execute_reply":"2022-10-01T01:56:24.414400Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"I have created a dataset linked to this notebook containing the compressed files; this will significantly improve loading times for the data.\n\nYou can use the compressed files without needing to run the code by using the following dataset: https://www.kaggle.com/datasets/reymaster/tps-oct-2022-compressed-parquet-files.","metadata":{}}]}