{
  "id": 200016,
  "title": "train.csv file lacking some features/columns present in the test file",
  "url": "/competitions/riiid-test-answer-prediction/discussion/200016",
  "author_name": "",
  "post_date": "2020-11-28T11:17:19.486851400Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Anyone with the idea on how to get the group_num and other features/columns in the example_test.csv file which were not included in the train.csv</p>",
  "messages": [
    {
      "id": "1094165",
      "postDate": "11/28/2020 11:17:19",
      "content": "<p>Anyone with the idea on how to get the group_num and other features/columns in the example_test.csv file which were not included in the train.csv</p>",
      "rawMarkdown": "Anyone with the idea on how to get the group_num and other features/columns in the example_test.csv file which were not included in the train.csv",
      "votes": null
    },
    {
      "id": "1094202",
      "postDate": "11/28/2020 12:01:35",
      "content": "<p>Divide your validation data into batches and give the batches consecutive <code>group_num</code>:s.  IIRC, someone posted a submission API simulator that I would assume does it for you.</p>",
      "rawMarkdown": "Divide your validation data into batches and give the batches consecutive `group_num`:s.  IIRC, someone posted a submission API simulator that I would assume does it for you.",
      "votes": null
    },
    {
      "id": "1095234",
      "postDate": "11/29/2020 11:42:35",
      "content": "<p>The group number has no meaning for the train dataset, I don't think it should be used as a feature.</p>",
      "rawMarkdown": "The group number has no meaning for the train dataset, I don't think it should be used as a feature.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1094202,
      "author_name": "christoffer",
      "author_url": "",
      "post_date": "11/28/2020 12:01:35",
      "content": "<p>Divide your validation data into batches and give the batches consecutive <code>group_num</code>:s.  IIRC, someone posted a submission API simulator that I would assume does it for you.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1095234,
      "author_name": "rodolphelampe",
      "author_url": "",
      "post_date": "11/29/2020 11:42:35",
      "content": "<p>The group number has no meaning for the train dataset, I don't think it should be used as a feature.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1094165": "Anyone with the idea on how to get the group_num and other features/columns in the example_test.csv file which were not included in the train.csv",
    "1094202": "Divide your validation data into batches and give the batches consecutive `group_num`:s.  IIRC, someone posted a submission API simulator that I would assume does it for you.",
    "1095234": "The group number has no meaning for the train dataset, I don't think it should be used as a feature."
  },
  "source": "meta"
}