{"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":"gpu","dataSources":[{"sourceId":56537,"databundleVersionId":8015876,"sourceType":"competition"},{"sourceId":8425368,"sourceType":"datasetVersion","datasetId":4865495}],"dockerImageVersionId":30699,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# LEAP Catboost Baseline\n\nCredits to:\n* [Giba Baseline XGBoost](https://www.kaggle.com/code/titericz/giba-baseline-xgboost)","metadata":{}},{"cell_type":"code","source":"import gc\nimport time\nimport cudf\nimport pickle\nimport numpy as np\nimport pandas as pd\nfrom glob import glob\nfrom tqdm import tqdm\nfrom catboost import CatBoostRegressor\nfrom sklearn.metrics import r2_score\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)\npd.options.display.max_columns = None\nimport matplotlib.pyplot as plt\n\n# All usable features\nfeatures = [\n    'state_t_0', 'state_t_1', 'state_t_2', 'state_t_3', 'state_t_4', 'state_t_5', 'state_t_6', 'state_t_7', 'state_t_8', 'state_t_9', 'state_t_10', 'state_t_11', 'state_t_12', 'state_t_13', 'state_t_14', 'state_t_15', 'state_t_16', 'state_t_17', 'state_t_18', 'state_t_19', 'state_t_20', 'state_t_21', 'state_t_22', 'state_t_23', 'state_t_24', 'state_t_25', 'state_t_26', 'state_t_27', 'state_t_28', 'state_t_29', 'state_t_30', 'state_t_31', 'state_t_32', 'state_t_33', 'state_t_34', 'state_t_35', 'state_t_36', 'state_t_37', 'state_t_38', 'state_t_39', 'state_t_40', 'state_t_41', 'state_t_42', 'state_t_43', 'state_t_44', 'state_t_45', 'state_t_46', 'state_t_47', 'state_t_48', 'state_t_49', 'state_t_50', 'state_t_51', 'state_t_52', 'state_t_53', 'state_t_54', 'state_t_55', 'state_t_56', 'state_t_57', 'state_t_58', 'state_t_59',\n    'state_q0001_0', 'state_q0001_1', 'state_q0001_2', 'state_q0001_3', 'state_q0001_4', 'state_q0001_5', 'state_q0001_6', 'state_q0001_7', 'state_q0001_8', 'state_q0001_9', 'state_q0001_10', 'state_q0001_11', 'state_q0001_12', 'state_q0001_13', 'state_q0001_14', 'state_q0001_15', 'state_q0001_16', 'state_q0001_17', 'state_q0001_18', 'state_q0001_19', 'state_q0001_20', 'state_q0001_21', 'state_q0001_22', 'state_q0001_23', 'state_q0001_24', 'state_q0001_25', 'state_q0001_26', 'state_q0001_27', 'state_q0001_28', 'state_q0001_29', 'state_q0001_30', 'state_q0001_31', 'state_q0001_32', 'state_q0001_33', 'state_q0001_34', 'state_q0001_35', 'state_q0001_36', 'state_q0001_37', 'state_q0001_38', 'state_q0001_39', 'state_q0001_40', 'state_q0001_41', 'state_q0001_42', 'state_q0001_43', 'state_q0001_44', 'state_q0001_45', 'state_q0001_46', 'state_q0001_47', 'state_q0001_48', 'state_q0001_49', 'state_q0001_50', 'state_q0001_51', 'state_q0001_52', 'state_q0001_53', 'state_q0001_54', 'state_q0001_55', 'state_q0001_56', 'state_q0001_57', 'state_q0001_58', 'state_q0001_59',\n    'state_q0002_0', 'state_q0002_1', 'state_q0002_2', 'state_q0002_3', 'state_q0002_4', 'state_q0002_5', 'state_q0002_6', 'state_q0002_7', 'state_q0002_8', 'state_q0002_9', 'state_q0002_10', 'state_q0002_11', 'state_q0002_12', 'state_q0002_13', 'state_q0002_14', 'state_q0002_15', 'state_q0002_16', 'state_q0002_17', 'state_q0002_18', 'state_q0002_19', 'state_q0002_20', 'state_q0002_21', 'state_q0002_22', 'state_q0002_23', 'state_q0002_24', 'state_q0002_25', 'state_q0002_26', 'state_q0002_27', 'state_q0002_28', 'state_q0002_29', 'state_q0002_30', 'state_q0002_31', 'state_q0002_32', 'state_q0002_33', 'state_q0002_34', 'state_q0002_35', 'state_q0002_36', 'state_q0002_37', 'state_q0002_38', 'state_q0002_39', 'state_q0002_40', 'state_q0002_41', 'state_q0002_42', 'state_q0002_43', 'state_q0002_44', 'state_q0002_45', 'state_q0002_46', 'state_q0002_47', 'state_q0002_48', 'state_q0002_49', 'state_q0002_50', 'state_q0002_51', 'state_q0002_52', 'state_q0002_53', 'state_q0002_54', 'state_q0002_55', 'state_q0002_56', 'state_q0002_57', 'state_q0002_58', 'state_q0002_59',\n    'state_q0003_0', 'state_q0003_1', 'state_q0003_2', 'state_q0003_3', 'state_q0003_4', 'state_q0003_5', 'state_q0003_6', 'state_q0003_7', 'state_q0003_8', 'state_q0003_9', 'state_q0003_10', 'state_q0003_11', 'state_q0003_12', 'state_q0003_13', 'state_q0003_14', 'state_q0003_15', 'state_q0003_16', 'state_q0003_17', 'state_q0003_18', 'state_q0003_19', 'state_q0003_20', 'state_q0003_21', 'state_q0003_22', 'state_q0003_23', 'state_q0003_24', 'state_q0003_25', 'state_q0003_26', 'state_q0003_27', 'state_q0003_28', 'state_q0003_29', 'state_q0003_30', 'state_q0003_31', 'state_q0003_32', 'state_q0003_33', 'state_q0003_34', 'state_q0003_35', 'state_q0003_36', 'state_q0003_37', 'state_q0003_38', 'state_q0003_39', 'state_q0003_40', 'state_q0003_41', 'state_q0003_42', 'state_q0003_43', 'state_q0003_44', 'state_q0003_45', 'state_q0003_46', 'state_q0003_47', 'state_q0003_48', 'state_q0003_49', 'state_q0003_50', 'state_q0003_51', 'state_q0003_52', 'state_q0003_53', 'state_q0003_54', 'state_q0003_55', 'state_q0003_56', 'state_q0003_57', 'state_q0003_58', 'state_q0003_59',\n    'state_u_0', 'state_u_1', 'state_u_2', 'state_u_3', 'state_u_4', 'state_u_5', 'state_u_6', 'state_u_7', 'state_u_8', 'state_u_9', 'state_u_10', 'state_u_11', 'state_u_12', 'state_u_13', 'state_u_14', 'state_u_15', 'state_u_16', 'state_u_17', 'state_u_18', 'state_u_19', 'state_u_20', 'state_u_21', 'state_u_22', 'state_u_23', 'state_u_24', 'state_u_25', 'state_u_26', 'state_u_27', 'state_u_28', 'state_u_29', 'state_u_30', 'state_u_31', 'state_u_32', 'state_u_33', 'state_u_34', 'state_u_35', 'state_u_36', 'state_u_37', 'state_u_38', 'state_u_39', 'state_u_40', 'state_u_41', 'state_u_42', 'state_u_43', 'state_u_44', 'state_u_45', 'state_u_46', 'state_u_47', 'state_u_48', 'state_u_49', 'state_u_50', 'state_u_51', 'state_u_52', 'state_u_53', 'state_u_54', 'state_u_55', 'state_u_56', 'state_u_57', 'state_u_58', 'state_u_59',\n    'state_v_0', 'state_v_1', 'state_v_2', 'state_v_3', 'state_v_4', 'state_v_5', 'state_v_6', 'state_v_7', 'state_v_8', 'state_v_9', 'state_v_10', 'state_v_11', 'state_v_12', 'state_v_13', 'state_v_14', 'state_v_15', 'state_v_16', 'state_v_17', 'state_v_18', 'state_v_19', 'state_v_20', 'state_v_21', 'state_v_22', 'state_v_23', 'state_v_24', 'state_v_25', 'state_v_26', 'state_v_27', 'state_v_28', 'state_v_29', 'state_v_30', 'state_v_31', 'state_v_32', 'state_v_33', 'state_v_34', 'state_v_35', 'state_v_36', 'state_v_37', 'state_v_38', 'state_v_39', 'state_v_40', 'state_v_41', 'state_v_42', 'state_v_43', 'state_v_44', 'state_v_45', 'state_v_46', 'state_v_47', 'state_v_48', 'state_v_49', 'state_v_50', 'state_v_51', 'state_v_52', 'state_v_53', 'state_v_54', 'state_v_55', 'state_v_56', 'state_v_57', 'state_v_58', 'state_v_59',\n    'state_ps', 'pbuf_SOLIN', 'pbuf_LHFLX', 'pbuf_SHFLX', 'pbuf_TAUX', 'pbuf_TAUY', 'pbuf_COSZRS', 'cam_in_ALDIF', 'cam_in_ALDIR', 'cam_in_ASDIF', 'cam_in_ASDIR', 'cam_in_LWUP', 'cam_in_ICEFRAC', 'cam_in_LANDFRAC', 'cam_in_OCNFRAC', 'cam_in_SNOWHLAND',\n    'pbuf_ozone_0', 'pbuf_ozone_1', 'pbuf_ozone_2', 'pbuf_ozone_3', 'pbuf_ozone_4', 'pbuf_ozone_5', 'pbuf_ozone_6', 'pbuf_ozone_7', 'pbuf_ozone_8', 'pbuf_ozone_9', 'pbuf_ozone_10', 'pbuf_ozone_11', 'pbuf_ozone_12', 'pbuf_ozone_13', 'pbuf_ozone_14', 'pbuf_ozone_15', 'pbuf_ozone_16', 'pbuf_ozone_17', 'pbuf_ozone_18', 'pbuf_ozone_19', 'pbuf_ozone_20', 'pbuf_ozone_21', 'pbuf_ozone_22', 'pbuf_ozone_23', 'pbuf_ozone_24', 'pbuf_ozone_25', 'pbuf_ozone_26', 'pbuf_ozone_27', 'pbuf_ozone_28', 'pbuf_ozone_29', 'pbuf_ozone_30', 'pbuf_ozone_31', 'pbuf_ozone_32', 'pbuf_ozone_33', 'pbuf_ozone_34', 'pbuf_ozone_35', 'pbuf_ozone_36', 'pbuf_ozone_37', 'pbuf_ozone_38', 'pbuf_ozone_39', 'pbuf_ozone_40', 'pbuf_ozone_41', 'pbuf_ozone_42', 'pbuf_ozone_43', 'pbuf_ozone_44', 'pbuf_ozone_45', 'pbuf_ozone_46', 'pbuf_ozone_47', 'pbuf_ozone_48', 'pbuf_ozone_49', 'pbuf_ozone_50', 'pbuf_ozone_51', 'pbuf_ozone_52', 'pbuf_ozone_53', 'pbuf_ozone_54', 'pbuf_ozone_55', 'pbuf_ozone_56', 'pbuf_ozone_57', 'pbuf_ozone_58', 'pbuf_ozone_59',\n    'pbuf_CH4_0', 'pbuf_CH4_1', 'pbuf_CH4_2', 'pbuf_CH4_3', 'pbuf_CH4_4', 'pbuf_CH4_5', 'pbuf_CH4_6', 'pbuf_CH4_7', 'pbuf_CH4_8', 'pbuf_CH4_9', 'pbuf_CH4_10', 'pbuf_CH4_11', 'pbuf_CH4_12', 'pbuf_CH4_13', 'pbuf_CH4_14', 'pbuf_CH4_15', 'pbuf_CH4_16', 'pbuf_CH4_17', 'pbuf_CH4_18', 'pbuf_CH4_19', 'pbuf_CH4_20', 'pbuf_CH4_21', 'pbuf_CH4_22', 'pbuf_CH4_23', 'pbuf_CH4_24', 'pbuf_CH4_25', 'pbuf_CH4_26',\n    'pbuf_N2O_0', 'pbuf_N2O_1', 'pbuf_N2O_2', 'pbuf_N2O_3', 'pbuf_N2O_4', 'pbuf_N2O_5', 'pbuf_N2O_6', 'pbuf_N2O_7', 'pbuf_N2O_8', 'pbuf_N2O_9', 'pbuf_N2O_10', 'pbuf_N2O_11', 'pbuf_N2O_12', 'pbuf_N2O_13', 'pbuf_N2O_14', 'pbuf_N2O_15', 'pbuf_N2O_16', 'pbuf_N2O_17', 'pbuf_N2O_18', 'pbuf_N2O_19', 'pbuf_N2O_20', 'pbuf_N2O_21', 'pbuf_N2O_22', 'pbuf_N2O_23', 'pbuf_N2O_24', 'pbuf_N2O_25', 'pbuf_N2O_26',\n]\n\n# Group of features\nfeatures0 = ['state_q0001_0', 'state_q0001_1', 'state_q0001_2', 'state_q0001_3', 'state_q0001_4', 'state_q0001_5', 'state_q0001_6', 'state_q0001_7', 'state_q0001_8', 'state_q0001_9', 'state_q0001_10', 'state_q0001_11', 'state_q0001_12', 'state_q0001_13', 'state_q0001_14', 'state_q0001_15', 'state_q0001_16', 'state_q0001_17', 'state_q0001_18', 'state_q0001_19', 'state_q0001_20', 'state_q0001_21', 'state_q0001_22', 'state_q0001_23', 'state_q0001_24', 'state_q0001_25', 'state_q0001_26', 'state_q0001_27', 'state_q0001_28', 'state_q0001_29', 'state_q0001_30', 'state_q0001_31', 'state_q0001_32', 'state_q0001_33', 'state_q0001_34', 'state_q0001_35', 'state_q0001_36', 'state_q0001_37', 'state_q0001_38', 'state_q0001_39', 'state_q0001_40', 'state_q0001_41', 'state_q0001_42', 'state_q0001_43', 'state_q0001_44', 'state_q0001_45', 'state_q0001_46', 'state_q0001_47', 'state_q0001_48', 'state_q0001_49', 'state_q0001_50', 'state_q0001_51', 'state_q0001_52', 'state_q0001_53', 'state_q0001_54', 'state_q0001_55', 'state_q0001_56', 'state_q0001_57', 'state_q0001_58', 'state_q0001_59',]\nfeatures1 = ['state_q0002_0', 'state_q0002_1', 'state_q0002_2', 'state_q0002_3', 'state_q0002_4', 'state_q0002_5', 'state_q0002_6', 'state_q0002_7', 'state_q0002_8', 'state_q0002_9', 'state_q0002_10', 'state_q0002_11', 'state_q0002_12', 'state_q0002_13', 'state_q0002_14', 'state_q0002_15', 'state_q0002_16', 'state_q0002_17', 'state_q0002_18', 'state_q0002_19', 'state_q0002_20', 'state_q0002_21', 'state_q0002_22', 'state_q0002_23', 'state_q0002_24', 'state_q0002_25', 'state_q0002_26', 'state_q0002_27', 'state_q0002_28', 'state_q0002_29', 'state_q0002_30', 'state_q0002_31', 'state_q0002_32', 'state_q0002_33', 'state_q0002_34', 'state_q0002_35', 'state_q0002_36', 'state_q0002_37', 'state_q0002_38', 'state_q0002_39', 'state_q0002_40', 'state_q0002_41', 'state_q0002_42', 'state_q0002_43', 'state_q0002_44', 'state_q0002_45', 'state_q0002_46', 'state_q0002_47', 'state_q0002_48', 'state_q0002_49', 'state_q0002_50', 'state_q0002_51', 'state_q0002_52', 'state_q0002_53', 'state_q0002_54', 'state_q0002_55', 'state_q0002_56', 'state_q0002_57', 'state_q0002_58', 'state_q0002_59',]\nfeatures2 = ['state_q0003_0', 'state_q0003_1', 'state_q0003_2', 'state_q0003_3', 'state_q0003_4', 'state_q0003_5', 'state_q0003_6', 'state_q0003_7', 'state_q0003_8', 'state_q0003_9', 'state_q0003_10', 'state_q0003_11', 'state_q0003_12', 'state_q0003_13', 'state_q0003_14', 'state_q0003_15', 'state_q0003_16', 'state_q0003_17', 'state_q0003_18', 'state_q0003_19', 'state_q0003_20', 'state_q0003_21', 'state_q0003_22', 'state_q0003_23', 'state_q0003_24', 'state_q0003_25', 'state_q0003_26', 'state_q0003_27', 'state_q0003_28', 'state_q0003_29', 'state_q0003_30', 'state_q0003_31', 'state_q0003_32', 'state_q0003_33', 'state_q0003_34', 'state_q0003_35', 'state_q0003_36', 'state_q0003_37', 'state_q0003_38', 'state_q0003_39', 'state_q0003_40', 'state_q0003_41', 'state_q0003_42', 'state_q0003_43', 'state_q0003_44', 'state_q0003_45', 'state_q0003_46', 'state_q0003_47', 'state_q0003_48', 'state_q0003_49', 'state_q0003_50', 'state_q0003_51', 'state_q0003_52', 'state_q0003_53', 'state_q0003_54', 'state_q0003_55', 'state_q0003_56', 'state_q0003_57', 'state_q0003_58', 'state_q0003_59',]\nfeatures3 = ['state_t_0', 'state_t_1', 'state_t_2', 'state_t_3', 'state_t_4', 'state_t_5', 'state_t_6', 'state_t_7', 'state_t_8', 'state_t_9', 'state_t_10', 'state_t_11', 'state_t_12', 'state_t_13', 'state_t_14', 'state_t_15', 'state_t_16', 'state_t_17', 'state_t_18', 'state_t_19', 'state_t_20', 'state_t_21', 'state_t_22', 'state_t_23', 'state_t_24', 'state_t_25', 'state_t_26', 'state_t_27', 'state_t_28', 'state_t_29', 'state_t_30', 'state_t_31', 'state_t_32', 'state_t_33', 'state_t_34', 'state_t_35', 'state_t_36', 'state_t_37', 'state_t_38', 'state_t_39', 'state_t_40', 'state_t_41', 'state_t_42', 'state_t_43', 'state_t_44', 'state_t_45', 'state_t_46', 'state_t_47', 'state_t_48', 'state_t_49', 'state_t_50', 'state_t_51', 'state_t_52', 'state_t_53', 'state_t_54', 'state_t_55', 'state_t_56', 'state_t_57', 'state_t_58', 'state_t_59',]\nfeatures4 = ['state_u_0', 'state_u_1', 'state_u_2', 'state_u_3', 'state_u_4', 'state_u_5', 'state_u_6', 'state_u_7', 'state_u_8', 'state_u_9', 'state_u_10', 'state_u_11', 'state_u_12', 'state_u_13', 'state_u_14', 'state_u_15', 'state_u_16', 'state_u_17', 'state_u_18', 'state_u_19', 'state_u_20', 'state_u_21', 'state_u_22', 'state_u_23', 'state_u_24', 'state_u_25', 'state_u_26', 'state_u_27', 'state_u_28', 'state_u_29', 'state_u_30', 'state_u_31', 'state_u_32', 'state_u_33', 'state_u_34', 'state_u_35', 'state_u_36', 'state_u_37', 'state_u_38', 'state_u_39', 'state_u_40', 'state_u_41', 'state_u_42', 'state_u_43', 'state_u_44', 'state_u_45', 'state_u_46', 'state_u_47', 'state_u_48', 'state_u_49', 'state_u_50', 'state_u_51', 'state_u_52', 'state_u_53', 'state_u_54', 'state_u_55', 'state_u_56', 'state_u_57', 'state_u_58', 'state_u_59',]\nfeatures5 = ['state_v_0', 'state_v_1', 'state_v_2', 'state_v_3', 'state_v_4', 'state_v_5', 'state_v_6', 'state_v_7', 'state_v_8', 'state_v_9', 'state_v_10', 'state_v_11', 'state_v_12', 'state_v_13', 'state_v_14', 'state_v_15', 'state_v_16', 'state_v_17', 'state_v_18', 'state_v_19', 'state_v_20', 'state_v_21', 'state_v_22', 'state_v_23', 'state_v_24', 'state_v_25', 'state_v_26', 'state_v_27', 'state_v_28', 'state_v_29', 'state_v_30', 'state_v_31', 'state_v_32', 'state_v_33', 'state_v_34', 'state_v_35', 'state_v_36', 'state_v_37', 'state_v_38', 'state_v_39', 'state_v_40', 'state_v_41', 'state_v_42', 'state_v_43', 'state_v_44', 'state_v_45', 'state_v_46', 'state_v_47', 'state_v_48', 'state_v_49', 'state_v_50', 'state_v_51', 'state_v_52', 'state_v_53', 'state_v_54', 'state_v_55', 'state_v_56', 'state_v_57', 'state_v_58', 'state_v_59',]\nfeatures6 = ['pbuf_ozone_0', 'pbuf_ozone_1', 'pbuf_ozone_2', 'pbuf_ozone_3', 'pbuf_ozone_4', 'pbuf_ozone_5', 'pbuf_ozone_6', 'pbuf_ozone_7', 'pbuf_ozone_8', 'pbuf_ozone_9', 'pbuf_ozone_10', 'pbuf_ozone_11', 'pbuf_ozone_12', 'pbuf_ozone_13', 'pbuf_ozone_14', 'pbuf_ozone_15', 'pbuf_ozone_16', 'pbuf_ozone_17', 'pbuf_ozone_18', 'pbuf_ozone_19', 'pbuf_ozone_20', 'pbuf_ozone_21', 'pbuf_ozone_22', 'pbuf_ozone_23', 'pbuf_ozone_24', 'pbuf_ozone_25', 'pbuf_ozone_26', 'pbuf_ozone_27', 'pbuf_ozone_28', 'pbuf_ozone_29', 'pbuf_ozone_30', 'pbuf_ozone_31', 'pbuf_ozone_32', 'pbuf_ozone_33', 'pbuf_ozone_34', 'pbuf_ozone_35', 'pbuf_ozone_36', 'pbuf_ozone_37', 'pbuf_ozone_38', 'pbuf_ozone_39', 'pbuf_ozone_40', 'pbuf_ozone_41', 'pbuf_ozone_42', 'pbuf_ozone_43', 'pbuf_ozone_44', 'pbuf_ozone_45', 'pbuf_ozone_46', 'pbuf_ozone_47', 'pbuf_ozone_48', 'pbuf_ozone_49', 'pbuf_ozone_50', 'pbuf_ozone_51', 'pbuf_ozone_52', 'pbuf_ozone_53', 'pbuf_ozone_54', 'pbuf_ozone_55', 'pbuf_ozone_56', 'pbuf_ozone_57', 'pbuf_ozone_58', 'pbuf_ozone_59',]\nfeatures7 = ['pbuf_CH4_0', 'pbuf_CH4_1', 'pbuf_CH4_2', 'pbuf_CH4_3', 'pbuf_CH4_4', 'pbuf_CH4_5', 'pbuf_CH4_6', 'pbuf_CH4_7', 'pbuf_CH4_8', 'pbuf_CH4_9', 'pbuf_CH4_10', 'pbuf_CH4_11', 'pbuf_CH4_12', 'pbuf_CH4_13', 'pbuf_CH4_14', 'pbuf_CH4_15', 'pbuf_CH4_16', 'pbuf_CH4_17', 'pbuf_CH4_18', 'pbuf_CH4_19', 'pbuf_CH4_20', 'pbuf_CH4_21', 'pbuf_CH4_22', 'pbuf_CH4_23', 'pbuf_CH4_24', 'pbuf_CH4_25', 'pbuf_CH4_26',]\nfeatures8 = ['pbuf_N2O_0', 'pbuf_N2O_1', 'pbuf_N2O_2', 'pbuf_N2O_3', 'pbuf_N2O_4', 'pbuf_N2O_5', 'pbuf_N2O_6', 'pbuf_N2O_7', 'pbuf_N2O_8', 'pbuf_N2O_9', 'pbuf_N2O_10', 'pbuf_N2O_11', 'pbuf_N2O_12', 'pbuf_N2O_13', 'pbuf_N2O_14', 'pbuf_N2O_15', 'pbuf_N2O_16', 'pbuf_N2O_17', 'pbuf_N2O_18', 'pbuf_N2O_19', 'pbuf_N2O_20', 'pbuf_N2O_21', 'pbuf_N2O_22', 'pbuf_N2O_23', 'pbuf_N2O_24', 'pbuf_N2O_25', 'pbuf_N2O_26',]\n\n# All the target variables\ntargets = [\n    'ptend_t_0', 'ptend_t_1', 'ptend_t_2', 'ptend_t_3', 'ptend_t_4', 'ptend_t_5', 'ptend_t_6', 'ptend_t_7', 'ptend_t_8', 'ptend_t_9', 'ptend_t_10', 'ptend_t_11', 'ptend_t_12', 'ptend_t_13', 'ptend_t_14', 'ptend_t_15', 'ptend_t_16', 'ptend_t_17', 'ptend_t_18', 'ptend_t_19', 'ptend_t_20', 'ptend_t_21', 'ptend_t_22', 'ptend_t_23', 'ptend_t_24', 'ptend_t_25', 'ptend_t_26', 'ptend_t_27', 'ptend_t_28', 'ptend_t_29', 'ptend_t_30', 'ptend_t_31', 'ptend_t_32', 'ptend_t_33', 'ptend_t_34', 'ptend_t_35', 'ptend_t_36', 'ptend_t_37', 'ptend_t_38', 'ptend_t_39', 'ptend_t_40', 'ptend_t_41', 'ptend_t_42', 'ptend_t_43', 'ptend_t_44', 'ptend_t_45', 'ptend_t_46', 'ptend_t_47', 'ptend_t_48', 'ptend_t_49', 'ptend_t_50', 'ptend_t_51', 'ptend_t_52', 'ptend_t_53', 'ptend_t_54', 'ptend_t_55', 'ptend_t_56', 'ptend_t_57', 'ptend_t_58', 'ptend_t_59',\n    'ptend_q0001_0', 'ptend_q0001_1', 'ptend_q0001_2', 'ptend_q0001_3', 'ptend_q0001_4', 'ptend_q0001_5', 'ptend_q0001_6', 'ptend_q0001_7', 'ptend_q0001_8', 'ptend_q0001_9', 'ptend_q0001_10', 'ptend_q0001_11', 'ptend_q0001_12', 'ptend_q0001_13', 'ptend_q0001_14', 'ptend_q0001_15', 'ptend_q0001_16', 'ptend_q0001_17', 'ptend_q0001_18', 'ptend_q0001_19', 'ptend_q0001_20', 'ptend_q0001_21', 'ptend_q0001_22', 'ptend_q0001_23', 'ptend_q0001_24', 'ptend_q0001_25', 'ptend_q0001_26', 'ptend_q0001_27', 'ptend_q0001_28', 'ptend_q0001_29', 'ptend_q0001_30', 'ptend_q0001_31', 'ptend_q0001_32', 'ptend_q0001_33', 'ptend_q0001_34', 'ptend_q0001_35', 'ptend_q0001_36', 'ptend_q0001_37', 'ptend_q0001_38', 'ptend_q0001_39', 'ptend_q0001_40', 'ptend_q0001_41', 'ptend_q0001_42', 'ptend_q0001_43', 'ptend_q0001_44', 'ptend_q0001_45', 'ptend_q0001_46', 'ptend_q0001_47', 'ptend_q0001_48', 'ptend_q0001_49', 'ptend_q0001_50', 'ptend_q0001_51', 'ptend_q0001_52', 'ptend_q0001_53', 'ptend_q0001_54', 'ptend_q0001_55', 'ptend_q0001_56', 'ptend_q0001_57', 'ptend_q0001_58', 'ptend_q0001_59',\n    'ptend_q0002_0', 'ptend_q0002_1', 'ptend_q0002_2', 'ptend_q0002_3', 'ptend_q0002_4', 'ptend_q0002_5', 'ptend_q0002_6', 'ptend_q0002_7', 'ptend_q0002_8', 'ptend_q0002_9', 'ptend_q0002_10', 'ptend_q0002_11', 'ptend_q0002_12', 'ptend_q0002_13', 'ptend_q0002_14', 'ptend_q0002_15', 'ptend_q0002_16', 'ptend_q0002_17', 'ptend_q0002_18', 'ptend_q0002_19', 'ptend_q0002_20', 'ptend_q0002_21', 'ptend_q0002_22', 'ptend_q0002_23', 'ptend_q0002_24', 'ptend_q0002_25', 'ptend_q0002_26', 'ptend_q0002_27', 'ptend_q0002_28', 'ptend_q0002_29', 'ptend_q0002_30', 'ptend_q0002_31', 'ptend_q0002_32', 'ptend_q0002_33', 'ptend_q0002_34', 'ptend_q0002_35', 'ptend_q0002_36', 'ptend_q0002_37', 'ptend_q0002_38', 'ptend_q0002_39', 'ptend_q0002_40', 'ptend_q0002_41', 'ptend_q0002_42', 'ptend_q0002_43', 'ptend_q0002_44', 'ptend_q0002_45', 'ptend_q0002_46', 'ptend_q0002_47', 'ptend_q0002_48', 'ptend_q0002_49', 'ptend_q0002_50', 'ptend_q0002_51', 'ptend_q0002_52', 'ptend_q0002_53', 'ptend_q0002_54', 'ptend_q0002_55', 'ptend_q0002_56', 'ptend_q0002_57', 'ptend_q0002_58', 'ptend_q0002_59',\n    'ptend_q0003_0', 'ptend_q0003_1', 'ptend_q0003_2', 'ptend_q0003_3', 'ptend_q0003_4', 'ptend_q0003_5', 'ptend_q0003_6', 'ptend_q0003_7', 'ptend_q0003_8', 'ptend_q0003_9', 'ptend_q0003_10', 'ptend_q0003_11', 'ptend_q0003_12', 'ptend_q0003_13', 'ptend_q0003_14', 'ptend_q0003_15', 'ptend_q0003_16', 'ptend_q0003_17', 'ptend_q0003_18', 'ptend_q0003_19', 'ptend_q0003_20', 'ptend_q0003_21', 'ptend_q0003_22', 'ptend_q0003_23', 'ptend_q0003_24', 'ptend_q0003_25', 'ptend_q0003_26', 'ptend_q0003_27', 'ptend_q0003_28', 'ptend_q0003_29', 'ptend_q0003_30', 'ptend_q0003_31', 'ptend_q0003_32', 'ptend_q0003_33', 'ptend_q0003_34', 'ptend_q0003_35', 'ptend_q0003_36', 'ptend_q0003_37', 'ptend_q0003_38', 'ptend_q0003_39', 'ptend_q0003_40', 'ptend_q0003_41', 'ptend_q0003_42', 'ptend_q0003_43', 'ptend_q0003_44', 'ptend_q0003_45', 'ptend_q0003_46', 'ptend_q0003_47', 'ptend_q0003_48', 'ptend_q0003_49', 'ptend_q0003_50', 'ptend_q0003_51', 'ptend_q0003_52', 'ptend_q0003_53', 'ptend_q0003_54', 'ptend_q0003_55', 'ptend_q0003_56', 'ptend_q0003_57', 'ptend_q0003_58', 'ptend_q0003_59',\n    'ptend_u_0', 'ptend_u_1', 'ptend_u_2', 'ptend_u_3', 'ptend_u_4', 'ptend_u_5', 'ptend_u_6', 'ptend_u_7', 'ptend_u_8', 'ptend_u_9', 'ptend_u_10', 'ptend_u_11', 'ptend_u_12', 'ptend_u_13', 'ptend_u_14', 'ptend_u_15', 'ptend_u_16', 'ptend_u_17', 'ptend_u_18', 'ptend_u_19', 'ptend_u_20', 'ptend_u_21', 'ptend_u_22', 'ptend_u_23', 'ptend_u_24', 'ptend_u_25', 'ptend_u_26', 'ptend_u_27', 'ptend_u_28', 'ptend_u_29', 'ptend_u_30', 'ptend_u_31', 'ptend_u_32', 'ptend_u_33', 'ptend_u_34', 'ptend_u_35', 'ptend_u_36', 'ptend_u_37', 'ptend_u_38', 'ptend_u_39', 'ptend_u_40', 'ptend_u_41', 'ptend_u_42', 'ptend_u_43', 'ptend_u_44', 'ptend_u_45', 'ptend_u_46', 'ptend_u_47', 'ptend_u_48', 'ptend_u_49', 'ptend_u_50', 'ptend_u_51', 'ptend_u_52', 'ptend_u_53', 'ptend_u_54', 'ptend_u_55', 'ptend_u_56', 'ptend_u_57', 'ptend_u_58', 'ptend_u_59',\n    'ptend_v_0', 'ptend_v_1', 'ptend_v_2', 'ptend_v_3', 'ptend_v_4', 'ptend_v_5', 'ptend_v_6', 'ptend_v_7', 'ptend_v_8', 'ptend_v_9', 'ptend_v_10', 'ptend_v_11', 'ptend_v_12', 'ptend_v_13', 'ptend_v_14', 'ptend_v_15', 'ptend_v_16', 'ptend_v_17', 'ptend_v_18', 'ptend_v_19', 'ptend_v_20', 'ptend_v_21', 'ptend_v_22', 'ptend_v_23', 'ptend_v_24', 'ptend_v_25', 'ptend_v_26', 'ptend_v_27', 'ptend_v_28', 'ptend_v_29', 'ptend_v_30', 'ptend_v_31', 'ptend_v_32', 'ptend_v_33', 'ptend_v_34', 'ptend_v_35', 'ptend_v_36', 'ptend_v_37', 'ptend_v_38', 'ptend_v_39', 'ptend_v_40', 'ptend_v_41', 'ptend_v_42', 'ptend_v_43', 'ptend_v_44', 'ptend_v_45', 'ptend_v_46', 'ptend_v_47', 'ptend_v_48', 'ptend_v_49', 'ptend_v_50', 'ptend_v_51', 'ptend_v_52', 'ptend_v_53', 'ptend_v_54', 'ptend_v_55', 'ptend_v_56', 'ptend_v_57', 'ptend_v_58', 'ptend_v_59',\n    'cam_out_NETSW', 'cam_out_FLWDS', 'cam_out_PRECSC', 'cam_out_PRECC', 'cam_out_SOLS', 'cam_out_SOLL', 'cam_out_SOLSD', 'cam_out_SOLLD',\n]\n\n\n# Compute target weights.\n# This is necessary to calculate the competition metric correctly.\nweights = pd.read_csv(\"/kaggle/input/leap-atmospheric-physics-ai-climsim/sample_submission.csv\", nrows=1)\ndel weights['sample_id']\nweights = weights.T\nweights = weights.to_dict()[0]\n\nprint(\"# Features:\", len(features))\nprint(\"# Targets Labels:\", len(targets))","metadata":{"execution":{"iopub.status.busy":"2024-05-20T18:41:34.94036Z","iopub.execute_input":"2024-05-20T18:41:34.940698Z","iopub.status.idle":"2024-05-20T18:41:35.025981Z","shell.execute_reply.started":"2024-05-20T18:41:34.940673Z","shell.execute_reply":"2024-05-20T18:41:35.025075Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Dataset: https://www.kaggle.com/datasets/titericz/leap-dataset-giba\n# This dataset was created using all train and test data.\n# Train is 10M samples and was split in 17 parquet files. Test is a single parquet file.\n\ntrain_files = sorted(glob(\"/kaggle/input/leap-dataset-giba/train_batch/*.parquet\"))\ntest_files = glob(\"/kaggle/input/leap-dataset-giba/test_batch/*.parquet\")\nlen(train_files), len(test_files)","metadata":{"execution":{"iopub.status.busy":"2024-05-20T18:18:00.065956Z","iopub.execute_input":"2024-05-20T18:18:00.066322Z","iopub.status.idle":"2024-05-20T18:18:00.090674Z","shell.execute_reply.started":"2024-05-20T18:18:00.066294Z","shell.execute_reply":"2024-05-20T18:18:00.089808Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load train, valid and test.","metadata":{}},{"cell_type":"code","source":"# Train on 2/17 of the full dataset\ntrain = pd.read_parquet(train_files[:4])\ngc.collect()\n\n# Validate on last parquet file (625000 samples)\nvalid = pd.read_parquet(train_files[-1])\ngc.collect()\n\ntest  = pd.read_parquet(test_files[0])\ngc.collect()\n\ntrain.shape, valid.shape, test.shape","metadata":{"execution":{"iopub.status.busy":"2024-05-20T18:18:23.160767Z","iopub.execute_input":"2024-05-20T18:18:23.161479Z","iopub.status.idle":"2024-05-20T18:19:25.919846Z","shell.execute_reply.started":"2024-05-20T18:18:23.161449Z","shell.execute_reply":"2024-05-20T18:19:25.918808Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training Loop - fit one by one","metadata":{}},{"cell_type":"code","source":"!mkdir models","metadata":{"execution":{"iopub.status.busy":"2024-05-20T18:40:01.199709Z","iopub.execute_input":"2024-05-20T18:40:01.200513Z","iopub.status.idle":"2024-05-20T18:40:02.618838Z","shell.execute_reply.started":"2024-05-20T18:40:01.20048Z","shell.execute_reply":"2024-05-20T18:40:02.617611Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"scores = []\nbegin = time.time()\nfor tnum, target in tqdm(enumerate(targets)):\n    if target not in train.columns:\n        test[target] = 0.\n        score = 1.0\n        scores.append(score)\n        mean_score = np.mean(scores)\n        print(f\"{tnum} r2(accum): {mean_score:.4f} / r2({target}): {score:.4f}\")\n        continue\n    M = train[target].mean()\n    if (train[target].nunique() != 1) and (train[target].abs().mean() > 1e-3):\n        model_path = f\"models/catboost_{target}.pkl\"\n        cat_params = {\n            'iterations': 2000, \n            'depth': 8, \n            'task_type' : \"GPU\",\n            'use_best_model': True,\n            'eval_metric': 'R2',\n            'early_stopping_rounds': 200,\n            'learning_rate': 0.05,\n            'border_count': 32,\n            'l2_leaf_reg': 3,\n            \"verbose\": 500\n        }\n        model = CatBoostRegressor(**cat_params)\n        model.fit(train[features], train[target], eval_set=(valid[features], valid[target])) \n        y_pred = model.predict(valid[features])\n        with open(model_path, \"wb\") as f:\n            pickle.dump(model, f)\n        score = r2_score(valid[target], y_pred, force_finite=True)\n        # If r2 is negative, just use mean(target)\n        if score <= 0:\n            score = r2_score(valid[target], np.zeros_like(valid[target]), force_finite=True)\n            test[target] = 0.\n        else:\n            test[target] = model.predict(test[features])\n        del model; gc.collect()\n    else:\n        score = r2_score(valid[target], np.zeros_like(valid[target]), force_finite=True)\n        test[target] = 0.\n    scores.append(score)\n    mean_score = np.mean(scores)\n    print(f\"{tnum} r2(accum): {mean_score:.4f} / r2({target}): {score:.4f}\")\n    elapsed_time = time.time() - begin\n    if elapsed_time > 8.9 * 3600:\n        break\nprint(f\"R2 score:{np.mean(scores)}\")","metadata":{"execution":{"iopub.status.busy":"2024-05-20T18:41:39.270168Z","iopub.execute_input":"2024-05-20T18:41:39.270834Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Clean up\ndel train, valid\ngc.collect()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Write submission file","metadata":{}},{"cell_type":"code","source":"submission = pd.read_csv(\"/kaggle/input/leap-atmospheric-physics-ai-climsim/sample_submission.csv\")\n\nfor col in tqdm(targets):\n    if weights[col] > 0:\n        submission[col] = test[col].values\n    else:\n        submission[col] = 0.\n        \nsubmission.to_csv('submission.csv', index=False)        \nsubmission.head()","metadata":{},"execution_count":null,"outputs":[]}]}