{
  "id": 5792,
  "title": "Test set",
  "url": "/competitions/expedia-personalized-sort/discussion/5792",
  "author_name": "",
  "post_date": "2013-09-18T08:31:48.453Z",
  "votes": null,
  "comment_count": 1,
  "views": 970,
  "content": "<p>if I understand we must learn our model on the training set, and evaluate it on the test set. However, I would like to know how can do it if we have no information about booking_booll and &nbsp;click_bool in the test set, ie&nbsp;how to build in this case labels (grades) in the test set.</p>\n<p>thanks,</p>",
  "messages": [
    {
      "id": "31076",
      "postDate": "09/18/2013 08:31:48",
      "content": "<p>if I understand we must learn our model on the training set, and evaluate it on the test set. However, I would like to know how can do it if we have no information about booking_booll and &nbsp;click_bool in the test set, ie&nbsp;how to build in this case labels (grades) in the test set.</p>\n<p>thanks,</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "31078",
      "postDate": "09/18/2013 11:48:10",
      "content": "<p>The benchmark code simply removes these columns (Line 11-16).</p>\n<p>https://github.com/benhamner/ExpediaPersonalizedSortCompetition/blob/master/PythonBenchmark/train.py</p>\n<p>(I think there's no way around this, because they're missing in the test set)</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 31078,
      "author_name": "mattvonrohr",
      "author_url": "",
      "post_date": "09/18/2013 11:48:10",
      "content": "<p>The benchmark code simply removes these columns (Line 11-16).</p>\n<p>https://github.com/benhamner/ExpediaPersonalizedSortCompetition/blob/master/PythonBenchmark/train.py</p>\n<p>(I think there's no way around this, because they're missing in the test set)</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "31076": "",
    "31078": ""
  },
  "source": "meta"
}