{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81000,"databundleVersionId":8812083,"sourceType":"competition"}],"dockerImageVersionId":30732,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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)\nimport seaborn as sns # plotting\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":"2024-06-11T15:30:09.124987Z","iopub.execute_input":"2024-06-11T15:30:09.125497Z","iopub.status.idle":"2024-06-11T15:30:10.298763Z","shell.execute_reply.started":"2024-06-11T15:30:09.125450Z","shell.execute_reply":"2024-06-11T15:30:10.297430Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def load_data(crop: str, mode: str=\"train\"):\n    # note that years represent an offset from model spinup;\n    # soil co2 dataset has real year;\n    # 0-30 are days before sowing, 31-238 are days after sowing\n    #tasmax = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/tasmax_{crop}_{mode}.parquet\")\n    #tasmin = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/tasmin_{crop}_{mode}.parquet\")\n    #pr = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/pr_{crop}_{mode}.parquet\")\n    #rsds = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/rsds_{crop}_{mode}.parquet\")\n    soil_co2 = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/soil_co2_{crop}_{mode}.parquet\")\n    target = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/{mode}_solutions_{crop}.parquet\")\n    return {\n        #'tasmax': tasmax,\n        #'tasmin': tasmin,\n        #'pr': pr,\n        #'rsds': rsds,\n        'soil_co2': soil_co2,\n        'target': target,\n    }","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:30:10.300720Z","iopub.execute_input":"2024-06-11T15:30:10.301832Z","iopub.status.idle":"2024-06-11T15:30:10.310263Z","shell.execute_reply.started":"2024-06-11T15:30:10.301782Z","shell.execute_reply":"2024-06-11T15:30:10.309008Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"maize_train = load_data(\"maize\", \"train\")\nmaize_train.keys()","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:30:10.313787Z","iopub.execute_input":"2024-06-11T15:30:10.314888Z","iopub.status.idle":"2024-06-11T15:30:10.432880Z","shell.execute_reply.started":"2024-06-11T15:30:10.314840Z","shell.execute_reply":"2024-06-11T15:30:10.431475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"wheat_train = load_data(\"wheat\", \"train\")\nwheat_train.keys()","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:30:10.434497Z","iopub.execute_input":"2024-06-11T15:30:10.434955Z","iopub.status.idle":"2024-06-11T15:30:10.509966Z","shell.execute_reply.started":"2024-06-11T15:30:10.434903Z","shell.execute_reply":"2024-06-11T15:30:10.508660Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# calculate mean maize yield at each grid cell\nmean_maize_per_gridcell = maize_train['soil_co2'].join(maize_train['target']).groupby(\n    ['lon','lat'])['yield'].mean()","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:30:11.868503Z","iopub.execute_input":"2024-06-11T15:30:11.869013Z","iopub.status.idle":"2024-06-11T15:30:11.948689Z","shell.execute_reply.started":"2024-06-11T15:30:11.868975Z","shell.execute_reply":"2024-06-11T15:30:11.947249Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# calculate mean wheat yield at each grid cell\nmean_wheat_per_gridcell = wheat_train['soil_co2'].join(wheat_train['target']).groupby(\n    ['lon','lat'])['yield'].mean()","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:30:19.493699Z","iopub.execute_input":"2024-06-11T15:30:19.494121Z","iopub.status.idle":"2024-06-11T15:30:19.545059Z","shell.execute_reply.started":"2024-06-11T15:30:19.494087Z","shell.execute_reply":"2024-06-11T15:30:19.543782Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"soil_co2_maize_test = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/soil_co2_maize_test.parquet\")","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:31:44.883801Z","iopub.execute_input":"2024-06-11T15:31:44.884246Z","iopub.status.idle":"2024-06-11T15:31:44.979465Z","shell.execute_reply.started":"2024-06-11T15:31:44.884209Z","shell.execute_reply":"2024-06-11T15:31:44.978227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# join with IDs of datapoints to be predicted\nmaize_predictions = pd.merge(soil_co2_maize_test.reset_index(), \n                             mean_maize_per_gridcell.reset_index(), \n                             how='left', on=['lat','lon']).set_index('ID')[['yield']]","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:33:48.007834Z","iopub.execute_input":"2024-06-11T15:33:48.008452Z","iopub.status.idle":"2024-06-11T15:33:48.170531Z","shell.execute_reply.started":"2024-06-11T15:33:48.008401Z","shell.execute_reply":"2024-06-11T15:33:48.168989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"soil_co2_wheat_test = pd.read_parquet(f\"/kaggle/input/the-future-crop-challenge/soil_co2_wheat_test.parquet\")","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:34:22.321914Z","iopub.execute_input":"2024-06-11T15:34:22.322344Z","iopub.status.idle":"2024-06-11T15:34:22.438354Z","shell.execute_reply.started":"2024-06-11T15:34:22.322307Z","shell.execute_reply":"2024-06-11T15:34:22.436983Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# join with IDs of datapoints to be predicted\nwheat_predictions = pd.merge(soil_co2_wheat_test.reset_index(), \n                             mean_wheat_per_gridcell.reset_index(), \n                             how='left', on=['lat','lon']).set_index('ID')[['yield']]","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:34:23.413928Z","iopub.execute_input":"2024-06-11T15:34:23.414350Z","iopub.status.idle":"2024-06-11T15:34:23.536330Z","shell.execute_reply.started":"2024-06-11T15:34:23.414315Z","shell.execute_reply":"2024-06-11T15:34:23.535226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pd.concat([maize_predictions, wheat_predictions]).to_csv('submission.csv', index_label='ID')","metadata":{"execution":{"iopub.status.busy":"2024-06-11T15:36:33.686214Z","iopub.execute_input":"2024-06-11T15:36:33.687282Z","iopub.status.idle":"2024-06-11T15:36:37.595907Z","shell.execute_reply.started":"2024-06-11T15:36:33.687241Z","shell.execute_reply":"2024-06-11T15:36:37.594829Z"},"trusted":true},"execution_count":null,"outputs":[]}]}