{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":70367,"databundleVersionId":9188054,"sourceType":"competition"}],"dockerImageVersionId":30761,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Created by <a href=\"https://github.com/yunsuxiaozi/\">yunsuxiaozi </a> 2024/09/05\n\n#### The <a href=\"https://www.kaggle.com/competitions/isic-2024-challenge/\">ISIC2024</a> next door is coming to an end, and we are also about to welcome the 'Shakeup'. The amount of data in this competition is very small, will it also be a very shaky competition?\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"import pandas as pd#导入csv文件的库\nimport numpy as np#矩阵运算与科学计算的库\nimport warnings#避免一些可以忽略的报错\nwarnings.filterwarnings('ignore')#filterwarnings()方法是用于设置警告过滤器的方法，它可以控制警告信息的输出方式和级别。\n\n\ntrain=pd.read_csv(\"/kaggle/input/ariel-data-challenge-2024/train_adc_info.csv\")\ntrain_label=pd.read_csv(\"/kaggle/input/ariel-data-challenge-2024/train_labels.csv\")\ntrain=train.merge(train_label,on='planet_id',how='left')\n\ntest=pd.read_csv(\"/kaggle/input/ariel-data-challenge-2024/test_adc_info.csv\")\n\nprint(f\"len(train):{len(train)},len(train_label):{len(train_label)},len(test):{len(test)}\")\n\n#star是0或者1\ntrain['star']=(train['star']==1).astype(np.int8)\ntest['star']=(test['star']==1).astype(np.int8)\n\ntrain.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#1~283\ntargets=[f'wl_{i+1}' for i in range(283)]\ndf=train.groupby(['star'])[targets].mean().reset_index()\ndf.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test=test.merge(df,on='star',how='left')\nfor i in range(283):\n    test[f'sigma_{i+1}']=test[f'wl_{i+1}']\ntest.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission=test[['planet_id']+[f'wl_{i+1}' for i in range(283)]+[f'sigma_{i+1}' for i in range(283)]]\n#这是为了以防万一,如果有缺失值,填充为0.002,如果有小于0的数,填充为1e-20\nsubmission=submission.fillna(0.002)\nsubmission=submission.clip(1e-20)\nsubmission.to_csv(\"submission.csv\",index=None)\nsubmission.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}