{"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":"markdown","source":"# Use Feather to compress csv file ","metadata":{}},{"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":"2022-10-01T13:36:33.444628Z","iopub.execute_input":"2022-10-01T13:36:33.445051Z","iopub.status.idle":"2022-10-01T13:36:33.455921Z","shell.execute_reply.started":"2022-10-01T13:36:33.445010Z","shell.execute_reply":"2022-10-01T13:36:33.454606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dir =  \"/kaggle/input/tabular-playground-series-oct-2022/\"","metadata":{"execution":{"iopub.status.busy":"2022-10-01T12:19:40.144135Z","iopub.execute_input":"2022-10-01T12:19:40.144572Z","iopub.status.idle":"2022-10-01T12:19:40.150620Z","shell.execute_reply.started":"2022-10-01T12:19:40.144513Z","shell.execute_reply":"2022-10-01T12:19:40.149351Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Use given data types to load csv, this help to reduce datafrme size significantly","metadata":{}},{"cell_type":"code","source":"%%time\ndtypes_df = pd.read_csv(dir+'train_dtypes.csv')\ndtypes = {k: v for (k, v) in zip(dtypes_df.column, dtypes_df.dtype)}\nfor i in range(10):\n    print(f\"Processing {i+1}th file...\")\n    df = pd.read_csv(dir+f'train_{i}.csv', dtype=dtypes)\n    df.to_feather(f\"train_{i}.feather\")\n    ","metadata":{"execution":{"iopub.status.busy":"2022-10-01T12:27:28.745934Z","iopub.execute_input":"2022-10-01T12:27:28.746427Z","iopub.status.idle":"2022-10-01T12:32:56.581476Z","shell.execute_reply.started":"2022-10-01T12:27:28.746392Z","shell.execute_reply":"2022-10-01T12:32:56.580239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Read all training feather files","metadata":{}},{"cell_type":"code","source":"%%time\ntrain = pd.DataFrame()\nfor i in range(10):\n    df = pd.read_feather(f'train_{i}.feather')\n","metadata":{"execution":{"iopub.status.busy":"2022-10-01T13:36:41.176561Z","iopub.execute_input":"2022-10-01T13:36:41.177312Z","iopub.status.idle":"2022-10-01T13:37:04.642042Z","shell.execute_reply.started":"2022-10-01T13:36:41.177274Z","shell.execute_reply":"2022-10-01T13:37:04.640174Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Check 0th train file","metadata":{}},{"cell_type":"code","source":"%%time\n#load with feather data\ntrain_0 = pd.read_feather('train_0.feather')\ntrain_0.head()\n","metadata":{"execution":{"iopub.status.busy":"2022-10-01T12:22:41.937668Z","iopub.execute_input":"2022-10-01T12:22:41.938866Z","iopub.status.idle":"2022-10-01T12:22:43.212676Z","shell.execute_reply.started":"2022-10-01T12:22:41.938827Z","shell.execute_reply":"2022-10-01T12:22:43.211407Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Thank you\n[Check this notebook for feather](https://www.kaggle.com/code/gazu468/feather-to-compress-your-data-8x-faster/notebook)","metadata":{}}]}