{"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":"2021-06-01T01:49:47.370141Z","iopub.execute_input":"2021-06-01T01:49:47.370582Z","iopub.status.idle":"2021-06-01T01:49:47.384523Z","shell.execute_reply.started":"2021-06-01T01:49:47.370487Z","shell.execute_reply":"2021-06-01T01:49:47.383484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_metadata = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/building_metadata.csv\") \ndf_train_bd = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/train.csv\")\ndf_test_bd = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/test.csv\")\ndf_train_wt = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/weather_train.csv\")\ndf_test_wt = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/weather_test.csv\")\n","metadata":{"execution":{"iopub.status.busy":"2021-06-01T01:49:47.763927Z","iopub.execute_input":"2021-06-01T01:49:47.764245Z","iopub.status.idle":"2021-06-01T01:50:26.903341Z","shell.execute_reply.started":"2021-06-01T01:49:47.764213Z","shell.execute_reply":"2021-06-01T01:50:26.902382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# データを眺めてみる\n\n#### pandasを活用  \n#### df.info, df.columns, df.unique...etc\n","metadata":{}},{"cell_type":"code","source":"print(\"info = \")\ndf_train_bd.info()\nprint(\"rows = \", len(df_train_bd))\nprint(\"columns = \", len(df_train_bd.columns))\nprint(df_train_bd.shape)\nprint(df_train_wt.shape)","metadata":{"execution":{"iopub.status.busy":"2021-06-01T01:50:26.904761Z","iopub.execute_input":"2021-06-01T01:50:26.905113Z","iopub.status.idle":"2021-06-01T01:50:26.929454Z","shell.execute_reply.started":"2021-06-01T01:50:26.905072Z","shell.execute_reply":"2021-06-01T01:50:26.928358Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(df_train_bd.columns)","metadata":{"execution":{"iopub.status.busy":"2021-06-01T01:50:26.932255Z","iopub.execute_input":"2021-06-01T01:50:26.932722Z","iopub.status.idle":"2021-06-01T01:50:26.942946Z","shell.execute_reply.started":"2021-06-01T01:50:26.932676Z","shell.execute_reply":"2021-06-01T01:50:26.941695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.sort(df_train_bd[\"building_id\"].unique())","metadata":{"execution":{"iopub.status.busy":"2021-06-01T01:50:26.944916Z","iopub.execute_input":"2021-06-01T01:50:26.945344Z","iopub.status.idle":"2021-06-01T01:50:27.062158Z","shell.execute_reply.started":"2021-06-01T01:50:26.9453Z","shell.execute_reply":"2021-06-01T01:50:27.061204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train_pre = pd.merge(\n    df_train_bd, df_metadata, on = [\"building_id\"])\ndf_train = pd.merge(df_train_pre, df_train_wt, on = [\"site_id\", \"timestamp\"])\nprint(df_train.shape)","metadata":{"execution":{"iopub.status.busy":"2021-06-01T01:50:27.063508Z","iopub.execute_input":"2021-06-01T01:50:27.063875Z","iopub.status.idle":"2021-06-01T01:50:36.595666Z","shell.execute_reply.started":"2021-06-01T01:50:27.063837Z","shell.execute_reply":"2021-06-01T01:50:36.594775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.head(10)","metadata":{"execution":{"iopub.status.busy":"2021-06-01T01:50:36.599493Z","iopub.execute_input":"2021-06-01T01:50:36.601395Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}