{
  "id": 380321,
  "title": "Notebook threw exception",
  "url": "/competitions/icecube-neutrinos-in-deep-ice/discussion/380321",
  "author_name": "",
  "post_date": "2023-01-22T20:02:05.887330600Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi, i'm new in kaggle competition. I have successfully commit my notebook, it shows that it already successfully ran. But, in the submission tab it shows that notebook threw exception, how can I fix it?</p>",
  "messages": [
    {
      "id": "2111343",
      "postDate": "01/22/2023 20:02:05",
      "content": "<p>Hi, i'm new in kaggle competition. I have successfully commit my notebook, it shows that it already successfully ran. But, in the submission tab it shows that notebook threw exception, how can I fix it?</p>",
      "rawMarkdown": "Hi, i'm new in kaggle competition. I have successfully commit my notebook, it shows that it already successfully ran. But, in the submission tab it shows that notebook threw exception, how can I fix it?",
      "votes": null
    },
    {
      "id": "2111360",
      "postDate": "01/22/2023 20:22:44",
      "content": "<p>There is a bug in your code, and you will have to find it the hard way. Try running your algorithm on a local validation scheme (i.e., train data) with at least two batches, including calculating the score with <a href=\"https://www.kaggle.com/code/sohier/mean-angular-error\" target=\"_blank\">their function</a>. This should help you find the problem. You can check <a href=\"https://www.kaggle.com/code/shlomoron/icecube-eda-pca-baseline-cv-1-28-lb-1-274\" target=\"_blank\">me notebook</a> to see how to perform validation, although I did not perform it on whole two batches, so you will have to implement this part yourself. Note that you have to assume (I think) that the test data include more than one batch, and you also have to take into account memory bounds, i.e. making sure that you don't load too many batches at the same time.</p>",
      "rawMarkdown": "There is a bug in your code, and you will have to find it the hard way. Try running your algorithm on a local validation scheme (i.e., train data) with at least two batches, including calculating the score with [their function](https://www.kaggle.com/code/sohier/mean-angular-error). This should help you find the problem. You can check [me notebook](https://www.kaggle.com/code/shlomoron/icecube-eda-pca-baseline-cv-1-28-lb-1-274) to see how to perform validation, although I did not perform it on whole two batches, so you will have to implement this part yourself. Note that you have to assume (I think) that the test data include more than one batch, and you also have to take into account memory bounds, i.e. making sure that you don't load too many batches at the same time.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2111360,
      "author_name": "shlomoron",
      "author_url": "",
      "post_date": "01/22/2023 20:22:44",
      "content": "<p>There is a bug in your code, and you will have to find it the hard way. Try running your algorithm on a local validation scheme (i.e., train data) with at least two batches, including calculating the score with <a href=\"https://www.kaggle.com/code/sohier/mean-angular-error\" target=\"_blank\">their function</a>. This should help you find the problem. You can check <a href=\"https://www.kaggle.com/code/shlomoron/icecube-eda-pca-baseline-cv-1-28-lb-1-274\" target=\"_blank\">me notebook</a> to see how to perform validation, although I did not perform it on whole two batches, so you will have to implement this part yourself. Note that you have to assume (I think) that the test data include more than one batch, and you also have to take into account memory bounds, i.e. making sure that you don't load too many batches at the same time.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2111343": "Hi, i'm new in kaggle competition. I have successfully commit my notebook, it shows that it already successfully ran. But, in the submission tab it shows that notebook threw exception, how can I fix it?",
    "2111360": "There is a bug in your code, and you will have to find it the hard way. Try running your algorithm on a local validation scheme (i.e., train data) with at least two batches, including calculating the score with [their function](https://www.kaggle.com/code/sohier/mean-angular-error). This should help you find the problem. You can check [me notebook](https://www.kaggle.com/code/shlomoron/icecube-eda-pca-baseline-cv-1-28-lb-1-274) to see how to perform validation, although I did not perform it on whole two batches, so you will have to implement this part yourself. Note that you have to assume (I think) that the test data include more than one batch, and you also have to take into account memory bounds, i.e. making sure that you don't load too many batches at the same time."
  },
  "source": "meta"
}