{
  "id": 516357,
  "title": "Submission Scoring Error",
  "url": "/competitions/rsna-2024-lumbar-spine-degenerative-classification/discussion/516357",
  "author_name": "",
  "post_date": "2024-07-02T08:31:59.614786600Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I have a problem with scoring submission. Generating \"submission.csv\" file is successful, but when it calculates score, it's false. Do you have any solutions to address this issue, or faced the same problem? Please let me know!!!</p>\n<p>Here is logs:</p>\n<p>20.5s    8   /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass <code>--Exporter.preprocessors item</code> … multiple times to add items to a list.<br>\n20.5s    9     warn(<br>\n20.5s    10  [NbConvertApp] WARNING | Config option <code>kernel_spec_manager_class</code> not recognized by <code>NbConvertApp</code>.<br>\n20.6s    11  [NbConvertApp] Converting notebook <strong>notebook</strong>.ipynb to notebook<br>\n21.0s    12  [NbConvertApp] Writing 45887 bytes to <strong>notebook</strong>.ipynb<br>\n22.6s    13  /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass <code>--Exporter.preprocessors item</code> … multiple times to add items to a list.<br>\n22.6s    14    warn(<br>\n22.6s    15  [NbConvertApp] WARNING | Config option <code>kernel_spec_manager_class</code> not recognized by <code>NbConvertApp</code>.<br>\n22.6s    16  [NbConvertApp] Converting notebook <strong>notebook</strong>.ipynb to html<br>\n23.6s    17  [NbConvertApp] Writing 399240 bytes to <strong>results</strong>.html</p>\n<p>Here is my submission.csv file</p>",
  "messages": [
    {
      "id": "2900381",
      "postDate": "07/02/2024 08:31:59",
      "content": "<p>I have a problem with scoring submission. Generating \"submission.csv\" file is successful, but when it calculates score, it's false. Do you have any solutions to address this issue, or faced the same problem? Please let me know!!!</p>\n<p>Here is logs:</p>\n<p>20.5s    8   /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass <code>--Exporter.preprocessors item</code> … multiple times to add items to a list.<br>\n20.5s    9     warn(<br>\n20.5s    10  [NbConvertApp] WARNING | Config option <code>kernel_spec_manager_class</code> not recognized by <code>NbConvertApp</code>.<br>\n20.6s    11  [NbConvertApp] Converting notebook <strong>notebook</strong>.ipynb to notebook<br>\n21.0s    12  [NbConvertApp] Writing 45887 bytes to <strong>notebook</strong>.ipynb<br>\n22.6s    13  /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass <code>--Exporter.preprocessors item</code> … multiple times to add items to a list.<br>\n22.6s    14    warn(<br>\n22.6s    15  [NbConvertApp] WARNING | Config option <code>kernel_spec_manager_class</code> not recognized by <code>NbConvertApp</code>.<br>\n22.6s    16  [NbConvertApp] Converting notebook <strong>notebook</strong>.ipynb to html<br>\n23.6s    17  [NbConvertApp] Writing 399240 bytes to <strong>results</strong>.html</p>\n<p>Here is my submission.csv file</p>",
      "rawMarkdown": "I have a problem with scoring submission. Generating \"submission.csv\" file is successful, but when it calculates score, it's false. Do you have any solutions to address this issue, or faced the same problem? Please let me know!!!\n\nHere is logs:\n\n20.5s\t8\t/opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n20.5s\t9\t  warn(\n20.5s\t10\t[NbConvertApp] WARNING | Config option `kernel_spec_manager_class` not recognized by `NbConvertApp`.\n20.6s\t11\t[NbConvertApp] Converting notebook __notebook__.ipynb to notebook\n21.0s\t12\t[NbConvertApp] Writing 45887 bytes to __notebook__.ipynb\n22.6s\t13\t/opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n22.6s\t14\t  warn(\n22.6s\t15\t[NbConvertApp] WARNING | Config option `kernel_spec_manager_class` not recognized by `NbConvertApp`.\n22.6s\t16\t[NbConvertApp] Converting notebook __notebook__.ipynb to html\n23.6s\t17\t[NbConvertApp] Writing 399240 bytes to __results__.html\n\n\nHere is my submission.csv file",
      "votes": null
    },
    {
      "id": "2900988",
      "postDate": "07/02/2024 15:39:51",
      "content": "<p>I want to confirm that you are aware of the hidden test cases. That is, the 25 rows in the public sample submission will turn into (Number of studies in <code>test_images</code> folder) * 25.<br>\nFrom the screenshot you gave, the way you are saving it is correct. After creating the final submission dataframe but before saving it, assert the following:</p>\n<ol>\n<li>The dataframe has no NaN values.</li>\n<li>All row_ids in <code>sample_submission.csv</code> are present in your final dataframe and that there are no additional row_ids. That is, <code>set(ss_df.row_id.to_list())==set(my_df.row_id.to_list())</code> where <code>my_df</code> is your final submission dataframe.</li>\n</ol>\n<p>If the \"Submission Scoring Error\" changes to \"Notebook Throw an Exception\" then you know that some problem exists in your code creating the final submission.</p>\n<p>Also, logs above will be present for all notebooks you save as it is just the logs generated when converting IPYNB file to HTML.</p>",
      "rawMarkdown": "I want to confirm that you are aware of the hidden test cases. That is, the 25 rows in the public sample submission will turn into (Number of studies in `test_images` folder) * 25.\nFrom the screenshot you gave, the way you are saving it is correct. After creating the final submission dataframe but before saving it, assert the following:\n1. The dataframe has no NaN values.\n1. All row_ids in `sample_submission.csv` are present in your final dataframe and that there are no additional row_ids. That is, `set(ss_df.row_id.to_list())==set(my_df.row_id.to_list())` where `my_df` is your final submission dataframe.\n\nIf the \"Submission Scoring Error\" changes to \"Notebook Throw an Exception\" then you know that some problem exists in your code creating the final submission.\n\nAlso, logs above will be present for all notebooks you save as it is just the logs generated when converting IPYNB file to HTML.",
      "votes": null
    },
    {
      "id": "2917606",
      "postDate": "07/11/2024 17:37:32",
      "content": "<p>Hi ,</p>\n<p>Most likely your code is failing in loop that generates whole output for all study_ids in hidden test set.</p>\n<p><a href=\"https://www.kaggle.com/sohier\" target=\"_blank\">@sohier</a> <br>\nI would request organizers to give at least 2 sample study_id folders so that iterative code is validated.</p>",
      "rawMarkdown": "Hi ,\n\nMost likely your code is failing in loop that generates whole output for all study_ids in hidden test set.\n\n@sohier \nI would request organizers to give at least 2 sample study_id folders so that iterative code is validated.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2900988,
      "author_name": "coderrkj",
      "author_url": "",
      "post_date": "07/02/2024 15:39:51",
      "content": "<p>I want to confirm that you are aware of the hidden test cases. That is, the 25 rows in the public sample submission will turn into (Number of studies in <code>test_images</code> folder) * 25.<br>\nFrom the screenshot you gave, the way you are saving it is correct. After creating the final submission dataframe but before saving it, assert the following:</p>\n<ol>\n<li>The dataframe has no NaN values.</li>\n<li>All row_ids in <code>sample_submission.csv</code> are present in your final dataframe and that there are no additional row_ids. That is, <code>set(ss_df.row_id.to_list())==set(my_df.row_id.to_list())</code> where <code>my_df</code> is your final submission dataframe.</li>\n</ol>\n<p>If the \"Submission Scoring Error\" changes to \"Notebook Throw an Exception\" then you know that some problem exists in your code creating the final submission.</p>\n<p>Also, logs above will be present for all notebooks you save as it is just the logs generated when converting IPYNB file to HTML.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2917606,
      "author_name": "rohitchaudhari25",
      "author_url": "",
      "post_date": "07/11/2024 17:37:32",
      "content": "<p>Hi ,</p>\n<p>Most likely your code is failing in loop that generates whole output for all study_ids in hidden test set.</p>\n<p><a href=\"https://www.kaggle.com/sohier\" target=\"_blank\">@sohier</a> <br>\nI would request organizers to give at least 2 sample study_id folders so that iterative code is validated.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2900381": "I have a problem with scoring submission. Generating \"submission.csv\" file is successful, but when it calculates score, it's false. Do you have any solutions to address this issue, or faced the same problem? Please let me know!!!\n\nHere is logs:\n\n20.5s\t8\t/opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n20.5s\t9\t  warn(\n20.5s\t10\t[NbConvertApp] WARNING | Config option `kernel_spec_manager_class` not recognized by `NbConvertApp`.\n20.6s\t11\t[NbConvertApp] Converting notebook __notebook__.ipynb to notebook\n21.0s\t12\t[NbConvertApp] Writing 45887 bytes to __notebook__.ipynb\n22.6s\t13\t/opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n22.6s\t14\t  warn(\n22.6s\t15\t[NbConvertApp] WARNING | Config option `kernel_spec_manager_class` not recognized by `NbConvertApp`.\n22.6s\t16\t[NbConvertApp] Converting notebook __notebook__.ipynb to html\n23.6s\t17\t[NbConvertApp] Writing 399240 bytes to __results__.html\n\n\nHere is my submission.csv file",
    "2900988": "I want to confirm that you are aware of the hidden test cases. That is, the 25 rows in the public sample submission will turn into (Number of studies in `test_images` folder) * 25.\nFrom the screenshot you gave, the way you are saving it is correct. After creating the final submission dataframe but before saving it, assert the following:\n1. The dataframe has no NaN values.\n1. All row_ids in `sample_submission.csv` are present in your final dataframe and that there are no additional row_ids. That is, `set(ss_df.row_id.to_list())==set(my_df.row_id.to_list())` where `my_df` is your final submission dataframe.\n\nIf the \"Submission Scoring Error\" changes to \"Notebook Throw an Exception\" then you know that some problem exists in your code creating the final submission.\n\nAlso, logs above will be present for all notebooks you save as it is just the logs generated when converting IPYNB file to HTML.",
    "2917606": "Hi ,\n\nMost likely your code is failing in loop that generates whole output for all study_ids in hidden test set.\n\n@sohier \nI would request organizers to give at least 2 sample study_id folders so that iterative code is validated."
  },
  "source": "meta"
}