Can someone explain the technical details of how Kaggle runs the test dataset on the submitted code and how it knows which file to replace? Any insights would be greatly appreciated.
", "messages": [ { "id": "2152581", "postDate": "02/20/2023 22:16:18", "content": "Can someone explain the technical details of how Kaggle runs the test dataset on the submitted code and how it knows which file to replace? Any insights would be greatly appreciated.
", "rawMarkdown": "Can someone explain the technical details of how Kaggle runs the test dataset on the submitted code and how it knows which file to replace? Any insights would be greatly appreciated.", "votes": null }, { "id": "2153001", "postDate": "02/21/2023 06:16:33", "content": "I had basically asked the same question. When you press the submit button, your notebook will run in a hidden environment with hidden data. Otherwise it works the same way as when you run your notebook. The submission file will be \"submission.csv\" in your working directory. After your notebook had run in the hidden environment, a validation script will inspect and score your submission.
", "rawMarkdown": "I had basically asked the [same question](https://www.kaggle.com/competitions/icecube-neutrinos-in-deep-ice/discussion/355479). When you press the submit button, your notebook will run in a hidden environment with hidden data. Otherwise it works the same way as when you run your notebook. The submission file will be \"submission.csv\" in your working directory. After your notebook had run in the hidden environment, a validation script will inspect and score your submission.", "votes": null }, { "id": "2153506", "postDate": "02/21/2023 13:11:53", "content": "Some files of the competition's dataset are placeholders. These files are changed for the actual ones once you submit your notebook. That way your code is run the same way you intended but with different data. For example, the test data you see only has 3 samples, but when you make a submission this file is changed for the real hidden test data.
", "rawMarkdown": "Some files of the competition's dataset are placeholders. These files are changed for the actual ones once you submit your notebook. That way your code is run the same way you intended but with different data. For example, the test data you see only has 3 samples, but when you make a submission this file is changed for the real hidden test data.", "votes": null } ], "comments": [ { "id": 2153001, "author_name": "taqseorangpun", "author_url": "", "post_date": "02/21/2023 06:16:33", "content": "I had basically asked the same question. When you press the submit button, your notebook will run in a hidden environment with hidden data. Otherwise it works the same way as when you run your notebook. The submission file will be \"submission.csv\" in your working directory. After your notebook had run in the hidden environment, a validation script will inspect and score your submission.
", "votes": null, "replies": [] }, { "id": 2153506, "author_name": "alejopaullier", "author_url": "", "post_date": "02/21/2023 13:11:53", "content": "Some files of the competition's dataset are placeholders. These files are changed for the actual ones once you submit your notebook. That way your code is run the same way you intended but with different data. For example, the test data you see only has 3 samples, but when you make a submission this file is changed for the real hidden test data.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2152581": "Can someone explain the technical details of how Kaggle runs the test dataset on the submitted code and how it knows which file to replace? Any insights would be greatly appreciated.", "2153001": "I had basically asked the [same question](https://www.kaggle.com/competitions/icecube-neutrinos-in-deep-ice/discussion/355479). When you press the submit button, your notebook will run in a hidden environment with hidden data. Otherwise it works the same way as when you run your notebook. The submission file will be \"submission.csv\" in your working directory. After your notebook had run in the hidden environment, a validation script will inspect and score your submission.", "2153506": "Some files of the competition's dataset are placeholders. These files are changed for the actual ones once you submit your notebook. That way your code is run the same way you intended but with different data. For example, the test data you see only has 3 samples, but when you make a submission this file is changed for the real hidden test data." }, "source": "meta" }