{
  "id": 388886,
  "title": "Notebook Threw Exception. Fill na is the problem?",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/388886",
  "author_name": "",
  "post_date": "2023-02-20T00:44:54.050285Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi everyone,</p>\n<p>After many failed submissions in think I found a problem about the Notebook Throw Exception, which is very difficult to debug. I tested with all the train and all the test data and all the execution executed correctly, but when I submitted the solution I got \"Notebook Throw Exception\" and in the log there is no problem.</p>\n<p>I read <a href=\"https://www.kaggle.com/titericz\" target=\"_blank\">@titericz</a>'s comments <a href=\"https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/386370#2141613\" target=\"_blank\">here</a></p>\n<blockquote>\n  <p>I found one difference in submission compared with commit. The nan in submission variables is different from the nan in commit variables. Pandas can fix both nan in commit and submission using fillna. But numpy/python wasn't able to fill the nan in submission using nan_to_num function.</p>\n</blockquote>\n<p>After removing the fillna code and testing without model, create only the features the submission works. But I tested with <code>df = df.fill_na(...)</code> and I don't know if I have another problem with my code but the problem persists and I no longer have the daily commit.</p>",
  "messages": [
    {
      "id": "2151253",
      "postDate": "02/20/2023 00:44:54",
      "content": "<p>Hi everyone,</p>\n<p>After many failed submissions in think I found a problem about the Notebook Throw Exception, which is very difficult to debug. I tested with all the train and all the test data and all the execution executed correctly, but when I submitted the solution I got \"Notebook Throw Exception\" and in the log there is no problem.</p>\n<p>I read <a href=\"https://www.kaggle.com/titericz\" target=\"_blank\">@titericz</a>'s comments <a href=\"https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/386370#2141613\" target=\"_blank\">here</a></p>\n<blockquote>\n  <p>I found one difference in submission compared with commit. The nan in submission variables is different from the nan in commit variables. Pandas can fix both nan in commit and submission using fillna. But numpy/python wasn't able to fill the nan in submission using nan_to_num function.</p>\n</blockquote>\n<p>After removing the fillna code and testing without model, create only the features the submission works. But I tested with <code>df = df.fill_na(...)</code> and I don't know if I have another problem with my code but the problem persists and I no longer have the daily commit.</p>",
      "rawMarkdown": "Hi everyone,\n\nAfter many failed submissions in think I found a problem about the Notebook Throw Exception, which is very difficult to debug. I tested with all the train and all the test data and all the execution executed correctly, but when I submitted the solution I got \"Notebook Throw Exception\" and in the log there is no problem.\n\nI read @titericz's comments [here](https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/386370#2141613)\n\n>I found one difference in submission compared with commit. The nan in submission variables is different from the nan in commit variables. Pandas can fix both nan in commit and submission using fillna. But numpy/python wasn't able to fill the nan in submission using nan_to_num function.\n\nAfter removing the fillna code and testing without model, create only the features the submission works. But I tested with `df = df.fill_na(...)` and I don't know if I have another problem with my code but the problem persists and I no longer have the daily commit.",
      "votes": null
    },
    {
      "id": "2151989",
      "postDate": "02/20/2023 14:02:36",
      "content": "<p>Hi, <a href=\"https://www.kaggle.com/ceruttivini\" target=\"_blank\">@ceruttivini</a>!</p>\n<p>Try to test your feature engineering pipeline by using <a href=\"https://www.kaggle.com/code/zakopur0/psp-debug-inference\" target=\"_blank\">kernel</a> made by <a href=\"https://www.kaggle.com/zakopur0\" target=\"_blank\">@zakopur0</a>.</p>\n<p>It helped me to fix the error in my pipeline</p>",
      "rawMarkdown": "Hi, @ceruttivini!\n\nTry to test your feature engineering pipeline by using [kernel](https://www.kaggle.com/code/zakopur0/psp-debug-inference) made by @zakopur0.\n\nIt helped me to fix the error in my pipeline",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2151989,
      "author_name": "myppka",
      "author_url": "",
      "post_date": "02/20/2023 14:02:36",
      "content": "<p>Hi, <a href=\"https://www.kaggle.com/ceruttivini\" target=\"_blank\">@ceruttivini</a>!</p>\n<p>Try to test your feature engineering pipeline by using <a href=\"https://www.kaggle.com/code/zakopur0/psp-debug-inference\" target=\"_blank\">kernel</a> made by <a href=\"https://www.kaggle.com/zakopur0\" target=\"_blank\">@zakopur0</a>.</p>\n<p>It helped me to fix the error in my pipeline</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2151253": "Hi everyone,\n\nAfter many failed submissions in think I found a problem about the Notebook Throw Exception, which is very difficult to debug. I tested with all the train and all the test data and all the execution executed correctly, but when I submitted the solution I got \"Notebook Throw Exception\" and in the log there is no problem.\n\nI read @titericz's comments [here](https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/386370#2141613)\n\n>I found one difference in submission compared with commit. The nan in submission variables is different from the nan in commit variables. Pandas can fix both nan in commit and submission using fillna. But numpy/python wasn't able to fill the nan in submission using nan_to_num function.\n\nAfter removing the fillna code and testing without model, create only the features the submission works. But I tested with `df = df.fill_na(...)` and I don't know if I have another problem with my code but the problem persists and I no longer have the daily commit.",
    "2151989": "Hi, @ceruttivini!\n\nTry to test your feature engineering pipeline by using [kernel](https://www.kaggle.com/code/zakopur0/psp-debug-inference) made by @zakopur0.\n\nIt helped me to fix the error in my pipeline"
  },
  "source": "meta"
}