{
  "id": 1124,
  "title": "user_id issue",
  "url": "/competitions/WhatDoYouKnow/discussion/1124",
  "author_name": "",
  "post_date": "2011-12-04T14:13:04.427Z",
  "votes": null,
  "comment_count": 1,
  "views": 1609,
  "content": "<p>&nbsp;</p>\r\n<p>The training and test files do not seem to be created according to the description in the Data section (&quot;The test/training split is derived by finding users who answered at least 6 questions, taking one of their answers (uniformly random, from their 6th\r\n question to their last), and inserting it into the test set.&nbsp; Any later answers by this user are removed, and any earlier answers are included in the training set&quot;), as looking into the test file, there are quite a number of user_ids that do not exist in the\r\n training.csv file (for example user_ids from 0 to 6). I did not yet check if for any user_id in the test file, that is represented in the training one, there are at least 5 answers in the training file.</p>\r\n<p>Any purpose for these extra user_ids? Should they just be discarded?</p>\r\n<p>Thanks</p>",
  "messages": [
    {
      "id": "6949",
      "postDate": "12/04/2011 14:13:04",
      "content": "<p>&nbsp;</p>\r\n<p>The training and test files do not seem to be created according to the description in the Data section (&quot;The test/training split is derived by finding users who answered at least 6 questions, taking one of their answers (uniformly random, from their 6th\r\n question to their last), and inserting it into the test set.&nbsp; Any later answers by this user are removed, and any earlier answers are included in the training set&quot;), as looking into the test file, there are quite a number of user_ids that do not exist in the\r\n training.csv file (for example user_ids from 0 to 6). I did not yet check if for any user_id in the test file, that is represented in the training one, there are at least 5 answers in the training file.</p>\r\n<p>Any purpose for these extra user_ids? Should they just be discarded?</p>\r\n<p>Thanks</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "6953",
      "postDate": "12/04/2011 22:02:02",
      "content": "<p>I am not able to recognize your problem.</p>\r\n<p>For example: user 0 can be found on line 2819423 and user 1 to 5 also occur more than 5 times in the training set.</p>\r\n<p>Hope this helps!&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 6953,
      "author_name": "dennisjaheruddin",
      "author_url": "",
      "post_date": "12/04/2011 22:02:02",
      "content": "<p>I am not able to recognize your problem.</p>\r\n<p>For example: user 0 can be found on line 2819423 and user 1 to 5 also occur more than 5 times in the training set.</p>\r\n<p>Hope this helps!&nbsp;</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "6949": "",
    "6953": ""
  },
  "source": "meta"
}