{
  "id": 206132,
  "title": "Wait... Why do we have so many test files?",
  "url": "/competitions/rfcx-species-audio-detection/discussion/206132",
  "author_name": "",
  "post_date": "2020-12-23T11:08:28.861414700Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I've only done a few Kaggle competitions in anger so maybe I'm missing something here. Normally we only get a small handful of test cases just to verify our code works for submission. But there are lots here. Are these the ones used in LB evaluation?</p>",
  "messages": [
    {
      "id": "1123596",
      "postDate": "12/23/2020 11:08:28",
      "content": "<p>I've only done a few Kaggle competitions in anger so maybe I'm missing something here. Normally we only get a small handful of test cases just to verify our code works for submission. But there are lots here. Are these the ones used in LB evaluation?</p>",
      "rawMarkdown": "I've only done a few Kaggle competitions in anger so maybe I'm missing something here. Normally we only get a small handful of test cases just to verify our code works for submission. But there are lots here. Are these the ones used in LB evaluation?",
      "votes": null
    },
    {
      "id": "1123941",
      "postDate": "12/23/2020 15:47:46",
      "content": "<p>Hi Alexander,</p>\n<p>yes, the test files you see are all the ones that are used for the LB evaluation. But as the LB says:</p>\n<blockquote>\n  <p>This leaderboard is calculated with approximately 21% of the test data</p>\n</blockquote>\n<p>only a subset of them is used.</p>\n<p>Best,</p>\n<p>Guglielmo</p>",
      "rawMarkdown": "Hi Alexander,\n\nyes, the test files you see are all the ones that are used for the LB evaluation. But as the LB says:\n\n> This leaderboard is calculated with approximately 21% of the test data\n\nonly a subset of them is used.\n\nBest,\n\nGuglielmo",
      "votes": null
    },
    {
      "id": "1123974",
      "postDate": "12/23/2020 16:11:03",
      "content": "<p>Thanks Guglielmo!</p>",
      "rawMarkdown": "Thanks Guglielmo!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1123941,
      "author_name": "guglielmocamporese",
      "author_url": "",
      "post_date": "12/23/2020 15:47:46",
      "content": "<p>Hi Alexander,</p>\n<p>yes, the test files you see are all the ones that are used for the LB evaluation. But as the LB says:</p>\n<blockquote>\n  <p>This leaderboard is calculated with approximately 21% of the test data</p>\n</blockquote>\n<p>only a subset of them is used.</p>\n<p>Best,</p>\n<p>Guglielmo</p>",
      "votes": null,
      "replies": [
        {
          "id": 1123974,
          "author_name": "alexandersoare",
          "author_url": "",
          "post_date": "12/23/2020 16:11:03",
          "content": "<p>Thanks Guglielmo!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1123596": "I've only done a few Kaggle competitions in anger so maybe I'm missing something here. Normally we only get a small handful of test cases just to verify our code works for submission. But there are lots here. Are these the ones used in LB evaluation?",
    "1123941": "Hi Alexander,\n\nyes, the test files you see are all the ones that are used for the LB evaluation. But as the LB says:\n\n> This leaderboard is calculated with approximately 21% of the test data\n\nonly a subset of them is used.\n\nBest,\n\nGuglielmo",
    "1123974": "Thanks Guglielmo!"
  },
  "source": "meta"
}