{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":112509,"databundleVersionId":14254895,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":13636070,"sourceType":"datasetVersion","datasetId":8667402},{"sourceId":13900620,"sourceType":"datasetVersion","datasetId":8856212},{"sourceId":14018229,"sourceType":"datasetVersion","datasetId":8929818},{"sourceId":14479049,"sourceType":"datasetVersion","datasetId":9219682},{"sourceId":288467413,"sourceType":"kernelVersion"},{"sourceId":290627241,"sourceType":"kernelVersion"},{"sourceId":4537,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":3329,"modelId":986},{"sourceId":268942,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":230141,"modelId":251887},{"sourceId":663314,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":471723,"modelId":487624},{"sourceId":4535,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":3327,"modelId":986},{"sourceId":686541,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":507446,"modelId":522154},{"sourceId":711299,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":540408,"modelId":553604}],"dockerImageVersionId":31193,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### This is my last public solution in this competition. Firsly, I would like to wish everyone a happy new year in 2026, and I would like to thank these people very much: Zhuang Jia(jiazhuang), Chika Komari(gothamjocker), CigarCat(takahitomizunobyts), samu2505(samu2505), Mattia Angeli(mattiaangeli), Kh0a(llkh0a). Thank you for your dedication in this competition, you have done a really great job! I strongly advise you to look at their work because they have different approaches to solving this problem.\n\n### I would also like to express my deep gratitude to the users, thank you for supporting me and improving yourself. I think it's clear how I +- built the pipeline and made improvements. further improvements will be much more difficult to achieve. 😄 Good luck with your work!\n\n### Time inference pipeline 7.45 +- hours","metadata":{}},{"cell_type":"code","source":"!python /kaggle/input/5-ensemble-csiro/inference1.py\n!python /kaggle/input/5-ensemble-csiro/inference2.py\n!python /kaggle/input/5-ensemble-csiro/inference3.py\n!python /kaggle/input/5-ensemble-csiro/inference4.py\n!python /kaggle/input/5-ensemble-csiro/inference5.py","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\nsubmission1 = pd.read_csv('submission1.csv')\nsubmission2 = pd.read_csv('submission2.csv')\nsubmission3 = pd.read_csv('submission3.csv')\nsubmission4 = pd.read_csv('submission4.csv')\nsubmission5 = pd.read_csv('submission5.csv')\n\nsubmission1 = submission1.rename(columns={'target': 'target_1'})\nsubmission2 = submission2.rename(columns={'target': 'target_2'})\nsubmission3 = submission3.rename(columns={'target': 'target_3'})\nsubmission4 = submission4.rename(columns={'target': 'target_4'})\nsubmission5 = submission5.rename(columns={'target': 'target_5'})\n\nmerged = pd.merge(submission1, submission2, on='sample_id')\nmerged = pd.merge(merged, submission3, on='sample_id')\nmerged = pd.merge(merged, submission4, on='sample_id')\nmerged = pd.merge(merged, submission5, on='sample_id')\n\nweight1, weight2, weight3, weight4, weight5 = 0.19, 0.27, 0.22, 0.22, 0.10\nmerged['target'] = (merged['target_1'] * weight1 + \n                    merged['target_2'] * weight2 + \n                    merged['target_3'] * weight3 +\n                    merged['target_4'] * weight4 +\n                    merged['target_5'] * weight5)\n\nsubmission = merged[['sample_id', 'target']]\nsubmission.to_csv('submission.csv', index=False)\nprint(submission.head())","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}