{
  "id": 393182,
  "title": "Need one clarification regarding level_group in the iter_test",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/393182",
  "author_name": "",
  "post_date": "2023-03-08T11:07:20.353485400Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi! I want to know that when we are looping over <code>iter_test</code>, we get <code>sample_submission</code> and <code>test</code>. In the <code>test</code> data frame, for the <code>level_group</code> column, will there be only one type of group in each iteration? I mean whether it will be only all <code>0-4</code> rows or all <code>5-13</code> rows or all <code>14-22</code> rows. Or, the different combinations can be present in the final <code>test_data</code> <code>level_group</code> column. Can someone clarify this? Thanks. <br>\nBecause I see many notebooks only take the first value <code>level_group.unique()</code>.</p>",
  "messages": [
    {
      "id": "2173402",
      "postDate": "03/08/2023 11:07:20",
      "content": "<p>Hi! I want to know that when we are looping over <code>iter_test</code>, we get <code>sample_submission</code> and <code>test</code>. In the <code>test</code> data frame, for the <code>level_group</code> column, will there be only one type of group in each iteration? I mean whether it will be only all <code>0-4</code> rows or all <code>5-13</code> rows or all <code>14-22</code> rows. Or, the different combinations can be present in the final <code>test_data</code> <code>level_group</code> column. Can someone clarify this? Thanks. <br>\nBecause I see many notebooks only take the first value <code>level_group.unique()</code>.</p>",
      "rawMarkdown": "Hi! I want to know that when we are looping over `iter_test`, we get `sample_submission` and `test`. In the `test` data frame, for the `level_group` column, will there be only one type of group in each iteration? I mean whether it will be only all `0-4` rows or all `5-13` rows or all `14-22` rows. Or, the different combinations can be present in the final `test_data` `level_group` column. Can someone clarify this? Thanks. \nBecause I see many notebooks only take the first value `level_group.unique()`.",
      "votes": null
    },
    {
      "id": "2173457",
      "postDate": "03/08/2023 12:20:11",
      "content": "<p>you can refer to</p>\n<p><a href=\"https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/388479#2153727\" target=\"_blank\">https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/388479#2153727</a></p>\n<blockquote>\n  <p>The fix was ensuring that the ordering of the incoming data was correct - 0-4, 5-12, 13-22. This is the way the data is presented; you use the 0-4 data to predict question correctness at the end of that segment, and so on.</p>\n</blockquote>\n<p><code>grp = test.level_group.values[0]</code> is representative for whole iter</p>",
      "rawMarkdown": "you can refer to\n\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/388479#2153727\n\n>  The fix was ensuring that the ordering of the incoming data was correct - 0-4, 5-12, 13-22. This is the way the data is presented; you use the 0-4 data to predict question correctness at the end of that segment, and so on.\n\n`grp = test.level_group.values[0]` is representative for whole iter",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2173457,
      "author_name": "steubk",
      "author_url": "",
      "post_date": "03/08/2023 12:20:11",
      "content": "<p>you can refer to</p>\n<p><a href=\"https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/388479#2153727\" target=\"_blank\">https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/388479#2153727</a></p>\n<blockquote>\n  <p>The fix was ensuring that the ordering of the incoming data was correct - 0-4, 5-12, 13-22. This is the way the data is presented; you use the 0-4 data to predict question correctness at the end of that segment, and so on.</p>\n</blockquote>\n<p><code>grp = test.level_group.values[0]</code> is representative for whole iter</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2173402": "Hi! I want to know that when we are looping over `iter_test`, we get `sample_submission` and `test`. In the `test` data frame, for the `level_group` column, will there be only one type of group in each iteration? I mean whether it will be only all `0-4` rows or all `5-13` rows or all `14-22` rows. Or, the different combinations can be present in the final `test_data` `level_group` column. Can someone clarify this? Thanks. \nBecause I see many notebooks only take the first value `level_group.unique()`.",
    "2173457": "you can refer to\n\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/388479#2153727\n\n>  The fix was ensuring that the ordering of the incoming data was correct - 0-4, 5-12, 13-22. This is the way the data is presented; you use the 0-4 data to predict question correctness at the end of that segment, and so on.\n\n`grp = test.level_group.values[0]` is representative for whole iter"
  },
  "source": "meta"
}