{"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":"2023-02-14T11:52:15.898337Z","iopub.execute_input":"2023-02-14T11:52:15.898797Z","iopub.status.idle":"2023-02-14T11:52:15.937281Z","shell.execute_reply.started":"2023-02-14T11:52:15.898675Z","shell.execute_reply":"2023-02-14T11:52:15.936600Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport gc","metadata":{"execution":{"iopub.status.busy":"2023-02-14T11:52:20.419020Z","iopub.execute_input":"2023-02-14T11:52:20.419462Z","iopub.status.idle":"2023-02-14T11:52:20.423178Z","shell.execute_reply.started":"2023-02-14T11:52:20.419431Z","shell.execute_reply":"2023-02-14T11:52:20.422497Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ntrain_data = pd.DataFrame()\nwith pd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv', chunksize=10**5) as reader:\n    for counter, chunk in enumerate(reader):\n        for column in chunk.columns:\n            if str(chunk[column].dtype) == \"float64\":\n                chunk[column] = chunk[column].astype(np.float32)\n            if str(chunk[column].dtype) == \"int64\":\n                chunk[column] = chunk[column].astype(np.int32)\n        train_data = pd.concat([train_data, chunk])\n        gc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-02-14T11:52:23.762462Z","iopub.execute_input":"2023-02-14T11:52:23.762818Z","iopub.status.idle":"2023-02-14T12:04:28.740526Z","shell.execute_reply.started":"2023-02-14T11:52:23.762785Z","shell.execute_reply":"2023-02-14T12:04:28.739587Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.to_pickle(\"train_data.pkl\")","metadata":{"execution":{"iopub.status.busy":"2023-02-14T12:06:11.929668Z","iopub.execute_input":"2023-02-14T12:06:11.930088Z","iopub.status.idle":"2023-02-14T12:06:29.507505Z","shell.execute_reply.started":"2023-02-14T12:06:11.930049Z","shell.execute_reply":"2023-02-14T12:06:29.506628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels = pd.read_csv(\"/kaggle/input/amex-default-prediction/train_labels.csv\")\ntrain_labels.to_pickle(\"train_labels.pkl\")","metadata":{"execution":{"iopub.status.busy":"2023-02-14T12:11:41.978078Z","iopub.execute_input":"2023-02-14T12:11:41.978449Z","iopub.status.idle":"2023-02-14T12:11:43.380643Z","shell.execute_reply.started":"2023-02-14T12:11:41.978413Z","shell.execute_reply":"2023-02-14T12:11:43.379620Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}