{
  "id": 390648,
  "title": "Submission scoring error",
  "url": "/competitions/icecube-neutrinos-in-deep-ice/discussion/390648",
  "author_name": "",
  "post_date": "2023-02-26T14:44:06.790900700Z",
  "votes": null,
  "comment_count": 6,
  "views": 0,
  "content": "<p>Hello!</p>\n<p>Has anyone encountered weird submission scoring errors?</p>\n<p>I don't get it what's wrong with it?</p>\n<p>The error reads:<br>\n<em>Your notebook generated a submission file with incorrect format. Some examples causing this are: wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.</em></p>\n<p>Here is the test notebook:<br>\n<a href=\"https://www.kaggle.com/code/mmakhyanov/test-submission\" target=\"_blank\">https://www.kaggle.com/code/mmakhyanov/test-submission</a></p>\n<p>submission file attached</p>",
  "messages": [
    {
      "id": "2160289",
      "postDate": "02/26/2023 14:44:06",
      "content": "<p>Hello!</p>\n<p>Has anyone encountered weird submission scoring errors?</p>\n<p>I don't get it what's wrong with it?</p>\n<p>The error reads:<br>\n<em>Your notebook generated a submission file with incorrect format. Some examples causing this are: wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.</em></p>\n<p>Here is the test notebook:<br>\n<a href=\"https://www.kaggle.com/code/mmakhyanov/test-submission\" target=\"_blank\">https://www.kaggle.com/code/mmakhyanov/test-submission</a></p>\n<p>submission file attached</p>",
      "rawMarkdown": "Hello!\n\nHas anyone encountered weird submission scoring errors?\n\nI don't get it what's wrong with it?\n\nThe error reads:\n*Your notebook generated a submission file with incorrect format. Some examples causing this are: wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.*\n\n\nHere is the test notebook:\nhttps://www.kaggle.com/code/mmakhyanov/test-submission\n\nsubmission file attached",
      "votes": null
    },
    {
      "id": "2160311",
      "postDate": "02/26/2023 15:01:39",
      "content": "<p>Hello, i checked your notebook.<br>\nYou are predicting only 3 rows.</p>\n<p>The problem is that the submissions are scored on a bigger test set which has the same structure of the file <br>\nbatch_661.parquet provided in the test folder.</p>\n<p>The submission.csv should have the predictions for each event in the hidden test set. <br>\nOtherwise you will get an error telling you that your submission has the wrong number of rows/columns. </p>\n<p>I suggest you to check some of the notebooks that are currently shared by other participants to understand better how to create a submission.</p>",
      "rawMarkdown": "Hello, i checked your notebook.\nYou are predicting only 3 rows.\n \nThe problem is that the submissions are scored on a bigger test set which has the same structure of the file \nbatch_661.parquet provided in the test folder.\n\nThe submission.csv should have the predictions for each event in the hidden test set. \nOtherwise you will get an error telling you that your submission has the wrong number of rows/columns. \n\nI suggest you to check some of the notebooks that are currently shared by other participants to understand better how to create a submission.",
      "votes": null
    },
    {
      "id": "2160314",
      "postDate": "02/26/2023 15:03:50",
      "content": "<p>great! thanks a lot, it makes sense since I tried to debug my other submission and couldn't understand what gone wrong</p>",
      "rawMarkdown": "great! thanks a lot, it makes sense since I tried to debug my other submission and couldn't understand what gone wrong",
      "votes": null
    },
    {
      "id": "2200188",
      "postDate": "03/28/2023 11:00:19",
      "content": "<p><a href=\"https://www.kaggle.com/mmakhyanov\" target=\"_blank\">@mmakhyanov</a> can you please guide how are you submitting the code? I am getting \"submission scoring errors\" and could not understand why.</p>\n<p>This is how I am defining the path of files:</p>\n<p>sensor_coords_file_path = r\"/kaggle/input/icecube-neutrinos-in-deep-ice\"<br>\nsensors_geometry_filename = \"sensor_geometry.csv\"<br>\nSENSOR_GEOMETRY = Path(sensor_coords_file_path, sensors_geometry_filename)</p>\n<p>meta_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice\"<br>\nmeta_filename = \"test_meta.parquet\"<br>\nMETA_FILE = Path(meta_file_path, meta_filename)</p>\n<p>batch_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice/test\"<br>\nbatch_filename_syntax = \"batch_{}.parquet\"</p>\n<p>Getting batch_ids from test_meta file using \"batch_ids = meta_file_df[\"batch_id\"].unique()\"<br>\nThen using loop for each batch_id:<br>\nfor i, batch_id in enumerate(batch_ids):<br>\nAnd defining batch_filename as \"batch_filename = Path(batch_file_path,<br>\n                                                       batch_filename_syntax.format(batch_id))\"</p>\n<p>Using the data I am predicting zenith and azimuth angles and storing in respective lists, along with event_id. Then I am using following code to generate csv file:</p>\n<p>submission_df = pd.DataFrame({\"event_id\": sub_event,<br>\n                              \"azimuth\": sub_az,<br>\n                              \"zenith\": sub_ze})<br>\nsubmission_df = submission_df.sort_values(by = ['event_id'])<br>\nsubmission_df.to_csv(submission_filename, index = False)</p>\n<p>Attached submission file that is generated using test_meta provided</p>\n<p>Thanks for your time</p>",
      "rawMarkdown": "mmakhyanov can you please guide how are you submitting the code? I am getting \"submission scoring errors\" and could not understand why.\n\nThis is how I am defining the path of files:\n\nsensor_coords_file_path = r\"/kaggle/input/icecube-neutrinos-in-deep-ice\"\nsensors_geometry_filename = \"sensor_geometry.csv\"\nSENSOR_GEOMETRY = Path(sensor_coords_file_path, sensors_geometry_filename)\n\nmeta_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice\"\nmeta_filename = \"test_meta.parquet\"\nMETA_FILE = Path(meta_file_path, meta_filename)\n\nbatch_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice/test\"\nbatch_filename_syntax = \"batch_{}.parquet\"\n\n\nGetting batch_ids from test_meta file using \"batch_ids = meta_file_df[\"batch_id\"].unique()\"\nThen using loop for each batch_id:\nfor i, batch_id in enumerate(batch_ids):\nAnd defining batch_filename as \"batch_filename = Path(batch_file_path,\n                                                       batch_filename_syntax.format(batch_id))\"\n\nUsing the data I am predicting zenith and azimuth angles and storing in respective lists, along with event_id. Then I am using following code to generate csv file:\n\nsubmission_df = pd.DataFrame({\"event_id\": sub_event,\n                              \"azimuth\": sub_az,\n                              \"zenith\": sub_ze})\nsubmission_df = submission_df.sort_values(by = ['event_id'])\nsubmission_df.to_csv(submission_filename, index = False)\n\nAttached submission file that is generated using test_meta provided\n\n\nThanks for your time",
      "votes": null
    },
    {
      "id": "2209153",
      "postDate": "04/04/2023 13:54:38",
      "content": "<p>thx, also meet the the same situation</p>",
      "rawMarkdown": "thx, also meet the the same situation",
      "votes": null
    },
    {
      "id": "2224995",
      "postDate": "04/17/2023 20:06:52",
      "content": "<p>The test set provided contains only 3 events, I don't get it. Could someone help please ?</p>",
      "rawMarkdown": "The test set provided contains only 3 events, I don't get it. Could someone help please ?",
      "votes": null
    },
    {
      "id": "2225160",
      "postDate": "04/18/2023 00:26:38",
      "content": "<p>The test set will be replaced by a hidden test set on submission.</p>",
      "rawMarkdown": "The test set will be replaced by a hidden test set on submission.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2160311,
      "author_name": "pietromaldini1",
      "author_url": "",
      "post_date": "02/26/2023 15:01:39",
      "content": "<p>Hello, i checked your notebook.<br>\nYou are predicting only 3 rows.</p>\n<p>The problem is that the submissions are scored on a bigger test set which has the same structure of the file <br>\nbatch_661.parquet provided in the test folder.</p>\n<p>The submission.csv should have the predictions for each event in the hidden test set. <br>\nOtherwise you will get an error telling you that your submission has the wrong number of rows/columns. </p>\n<p>I suggest you to check some of the notebooks that are currently shared by other participants to understand better how to create a submission.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2160314,
          "author_name": "mmakhyanov",
          "author_url": "",
          "post_date": "02/26/2023 15:03:50",
          "content": "<p>great! thanks a lot, it makes sense since I tried to debug my other submission and couldn't understand what gone wrong</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 2209153,
          "author_name": "liuxin22",
          "author_url": "",
          "post_date": "04/04/2023 13:54:38",
          "content": "<p>thx, also meet the the same situation</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 2224995,
          "author_name": "mlportal",
          "author_url": "",
          "post_date": "04/17/2023 20:06:52",
          "content": "<p>The test set provided contains only 3 events, I don't get it. Could someone help please ?</p>",
          "votes": null,
          "replies": [
            {
              "id": 2225160,
              "author_name": "taqseorangpun",
              "author_url": "",
              "post_date": "04/18/2023 00:26:38",
              "content": "<p>The test set will be replaced by a hidden test set on submission.</p>",
              "votes": null,
              "replies": []
            }
          ]
        }
      ]
    },
    {
      "id": 2200188,
      "author_name": "talhakarimtk",
      "author_url": "",
      "post_date": "03/28/2023 11:00:19",
      "content": "<p><a href=\"https://www.kaggle.com/mmakhyanov\" target=\"_blank\">@mmakhyanov</a> can you please guide how are you submitting the code? I am getting \"submission scoring errors\" and could not understand why.</p>\n<p>This is how I am defining the path of files:</p>\n<p>sensor_coords_file_path = r\"/kaggle/input/icecube-neutrinos-in-deep-ice\"<br>\nsensors_geometry_filename = \"sensor_geometry.csv\"<br>\nSENSOR_GEOMETRY = Path(sensor_coords_file_path, sensors_geometry_filename)</p>\n<p>meta_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice\"<br>\nmeta_filename = \"test_meta.parquet\"<br>\nMETA_FILE = Path(meta_file_path, meta_filename)</p>\n<p>batch_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice/test\"<br>\nbatch_filename_syntax = \"batch_{}.parquet\"</p>\n<p>Getting batch_ids from test_meta file using \"batch_ids = meta_file_df[\"batch_id\"].unique()\"<br>\nThen using loop for each batch_id:<br>\nfor i, batch_id in enumerate(batch_ids):<br>\nAnd defining batch_filename as \"batch_filename = Path(batch_file_path,<br>\n                                                       batch_filename_syntax.format(batch_id))\"</p>\n<p>Using the data I am predicting zenith and azimuth angles and storing in respective lists, along with event_id. Then I am using following code to generate csv file:</p>\n<p>submission_df = pd.DataFrame({\"event_id\": sub_event,<br>\n                              \"azimuth\": sub_az,<br>\n                              \"zenith\": sub_ze})<br>\nsubmission_df = submission_df.sort_values(by = ['event_id'])<br>\nsubmission_df.to_csv(submission_filename, index = False)</p>\n<p>Attached submission file that is generated using test_meta provided</p>\n<p>Thanks for your time</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2160289": "Hello!\n\nHas anyone encountered weird submission scoring errors?\n\nI don't get it what's wrong with it?\n\nThe error reads:\n*Your notebook generated a submission file with incorrect format. Some examples causing this are: wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.*\n\n\nHere is the test notebook:\nhttps://www.kaggle.com/code/mmakhyanov/test-submission\n\nsubmission file attached",
    "2160311": "Hello, i checked your notebook.\nYou are predicting only 3 rows.\n \nThe problem is that the submissions are scored on a bigger test set which has the same structure of the file \nbatch_661.parquet provided in the test folder.\n\nThe submission.csv should have the predictions for each event in the hidden test set. \nOtherwise you will get an error telling you that your submission has the wrong number of rows/columns. \n\nI suggest you to check some of the notebooks that are currently shared by other participants to understand better how to create a submission.",
    "2160314": "great! thanks a lot, it makes sense since I tried to debug my other submission and couldn't understand what gone wrong",
    "2200188": "mmakhyanov can you please guide how are you submitting the code? I am getting \"submission scoring errors\" and could not understand why.\n\nThis is how I am defining the path of files:\n\nsensor_coords_file_path = r\"/kaggle/input/icecube-neutrinos-in-deep-ice\"\nsensors_geometry_filename = \"sensor_geometry.csv\"\nSENSOR_GEOMETRY = Path(sensor_coords_file_path, sensors_geometry_filename)\n\nmeta_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice\"\nmeta_filename = \"test_meta.parquet\"\nMETA_FILE = Path(meta_file_path, meta_filename)\n\nbatch_file_path = \"/kaggle/input/icecube-neutrinos-in-deep-ice/test\"\nbatch_filename_syntax = \"batch_{}.parquet\"\n\n\nGetting batch_ids from test_meta file using \"batch_ids = meta_file_df[\"batch_id\"].unique()\"\nThen using loop for each batch_id:\nfor i, batch_id in enumerate(batch_ids):\nAnd defining batch_filename as \"batch_filename = Path(batch_file_path,\n                                                       batch_filename_syntax.format(batch_id))\"\n\nUsing the data I am predicting zenith and azimuth angles and storing in respective lists, along with event_id. Then I am using following code to generate csv file:\n\nsubmission_df = pd.DataFrame({\"event_id\": sub_event,\n                              \"azimuth\": sub_az,\n                              \"zenith\": sub_ze})\nsubmission_df = submission_df.sort_values(by = ['event_id'])\nsubmission_df.to_csv(submission_filename, index = False)\n\nAttached submission file that is generated using test_meta provided\n\n\nThanks for your time",
    "2209153": "thx, also meet the the same situation",
    "2224995": "The test set provided contains only 3 events, I don't get it. Could someone help please ?",
    "2225160": "The test set will be replaced by a hidden test set on submission."
  },
  "source": "meta"
}