{"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","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport gresearch_crypto\nenv = gresearch_crypto.make_env()\niter_test = env.iter_test()\ndf = pd.read_csv('/kaggle/input/g-research-crypto-forecasting/train.csv', \n                 usecols=['Target', 'Asset_ID','timestamp'], dtype={'Asset_ID': 'int8'})\ndf['datetime'] = pd.to_datetime(df['timestamp'], unit='s')\ndf = df.set_index('datetime').drop('timestamp', axis=1)\ndf = df[(df.index.year == 2021) & (df.index.month > 5)].dropna(subset=[\"Target\"])\ndfs = {asset_id: df[df['Asset_ID'] == asset_id].copy() for asset_id in df['Asset_ID'].unique()}\ndel df\n\nfor df_test, df_pred in iter_test:\n    df_test['datetime'] = pd.to_datetime(df_test['timestamp'], unit='s')\n    for _, row in df_test.iterrows():\n        try:\n            df = dfs[row['Asset_ID']]\n            closest_train_sample = df.iloc[df.index.get_loc(row['datetime'], method='nearest')]\n            df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = closest_train_sample['Target']\n        except:\n            df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = 0\n    df_pred['Target'] = df_pred['Target'].fillna(0)\n    env.predict(df_pred)","metadata":{"execution":{"iopub.status.busy":"2021-11-16T19:10:17.068872Z","iopub.execute_input":"2021-11-16T19:10:17.069504Z","iopub.status.idle":"2021-11-16T19:11:03.108323Z","shell.execute_reply.started":"2021-11-16T19:10:17.069381Z","shell.execute_reply":"2021-11-16T19:11:03.107475Z"},"trusted":true},"execution_count":null,"outputs":[]}]}