{"cells":[{"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\"\"\"\nbuilding = pd.read_csv('/kaggle/input/ashrae-energy-prediction/building_metadata.csv')\nsample = pd.read_csv('/kaggle/input/ashrae-energy-prediction/sample_submission.csv')\ntestW = pd.read_csv('/kaggle/input/ashrae-energy-prediction/weather_test.csv')\ntrain = pd.read_csv('/kaggle/input/ashrae-energy-prediction/train.csv')\ntest = pd.read_csv('/kaggle/input/ashrae-energy-prediction/test.csv')\ntrainW = pd.read_csv('/kaggle/input/ashrae-energy-prediction/weather_train.csv')\n\"\"\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from pandas.api.types import is_datetime64_any_dtype as is_datetime\n\ndef reduce_mem_usage(df, use_float16=False):\n    \"\"\" iterate through all the columns of a dataframe and modify the data type\n        to reduce memory usage.        \n    \"\"\"\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n    \n    for col in df.columns:\n        if is_datetime(df[col]):\n            # skip datetime type\n            continue\n        col_type = df[col].dtype\n        \n        if col_type != object:\n            c_min = df[col].min()\n            c_max = df[col].max()\n            if str(col_type)[:3] == 'int':\n                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n                    df[col] = df[col].astype(np.int8)\n                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n                    df[col] = df[col].astype(np.int16)\n                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n                    df[col] = df[col].astype(np.int32)\n                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n                    df[col] = df[col].astype(np.int64)  \n            else:\n                if use_float16 and c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n                    df[col] = df[col].astype(np.float16)\n                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n                    df[col] = df[col].astype(np.float32)\n                else:\n                    df[col] = df[col].astype(np.float64)\n        else:\n            df[col] = df[col].astype('category')\n\n    end_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n    \n    return df\n\n\ndef import_data(file):\n    \"\"\"create a dataframe and optimize its memory usage\"\"\"\n    df = pd.read_csv(file, parse_dates=True, keep_date_col=True)\n    df = reduce_mem_usage(df)\n    return df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\n# Read data...\nroot = '../input/ashrae-energy-prediction'\n\ntrain_df = pd.read_csv(os.path.join(root, 'train.csv'))\nweather_train_df = pd.read_csv(os.path.join(root, 'weather_train.csv'))\ntest_df = pd.read_csv(os.path.join(root, 'test.csv'))\nweather_test_df = pd.read_csv(os.path.join(root, 'weather_test.csv'))\nbuilding_meta_df = pd.read_csv(os.path.join(root, 'building_metadata.csv'))\nsample_submission = pd.read_csv(os.path.join(root, 'sample_submission.csv'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['timestamp'] = pd.to_datetime(train_df['timestamp'])\ntest_df['timestamp'] = pd.to_datetime(test_df['timestamp'])\nweather_train_df['timestamp'] = pd.to_datetime(weather_train_df['timestamp'])\nweather_test_df['timestamp'] = pd.to_datetime(weather_test_df['timestamp'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"reduce_mem_usage(train_df)\nreduce_mem_usage(test_df)\nreduce_mem_usage(building_meta_df)\nreduce_mem_usage(weather_train_df)\nreduce_mem_usage(weather_test_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ntrain_df.to_feather('train.feather')\ntest_df.to_feather('test.feather')\nweather_train_df.to_feather('weather_train.feather')\nweather_test_df.to_feather('weather_test.feather')\nbuilding_meta_df.to_feather('building_metadata.feather')\nsample_submission.to_feather('sample_submission.feather')","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":1}