{"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":"import numpy as np\nimport pandas as pd\nimport gresearch_crypto\nenv = gresearch_crypto.make_env()\niter_test = env.iter_test()","metadata":{"_uuid":"b7999a53-245f-4a2f-8d4d-585aed90e4a8","_cell_guid":"6a442687-aace-448c-9f27-c8d66e59d7c0","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-01-09T08:06:03.761715Z","iopub.execute_input":"2022-01-09T08:06:03.762514Z","iopub.status.idle":"2022-01-09T08:06:03.820971Z","shell.execute_reply.started":"2022-01-09T08:06:03.762407Z","shell.execute_reply":"2022-01-09T08:06:03.820185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"trainDF = pd.read_csv('/kaggle/input/g-research-crypto-forecasting/train.csv', \n                 usecols=['Target', 'Asset_ID','timestamp'], dtype={'Asset_ID': 'int8'})\ntrainDF['datetime'] = pd.to_datetime(trainDF['timestamp'], unit='s')\ntrainDF = trainDF.set_index('datetime').drop('timestamp', axis=1)\ntrainDF = trainDF[(trainDF.index.year == 2021) & (trainDF.index.month > 5)]\ndfs = {asset_id: trainDF[trainDF['Asset_ID'] == asset_id].resample('1min').interpolate().copy() for asset_id in trainDF['Asset_ID'].unique()}\ndel trainDF\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":{"_uuid":"08d0a93e-243a-4092-b215-03cfcbc89c7b","_cell_guid":"5f030a38-44f2-4443-ab1f-95106853f465","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-01-09T08:06:03.822726Z","iopub.execute_input":"2022-01-09T08:06:03.823477Z","iopub.status.idle":"2022-01-09T08:07:01.54525Z","shell.execute_reply.started":"2022-01-09T08:06:03.823425Z","shell.execute_reply":"2022-01-09T08:07:01.544634Z"},"trusted":true},"execution_count":null,"outputs":[]}]}