{
  "id": 98844,
  "title": "Leakage(about 8% current test dataset)",
  "url": "/competitions/aptos2019-blindness-detection/discussion/98844",
  "author_name": "",
  "post_date": "2019-07-06T23:06:56.279431600Z",
  "votes": 5,
  "comment_count": 1,
  "views": 0,
  "content": "<p>In my <a href=\"https://www.kaggle.com/miklgr500/leakage-detection-about-8-test-dataset\">new kernel with old aproch which based on autoencoder</a> is detected about 8% leakage. What are you think about it?</p>",
  "messages": [
    {
      "id": "569557",
      "postDate": "07/06/2019 23:06:56",
      "content": "<p>In my <a href=\"https://www.kaggle.com/miklgr500/leakage-detection-about-8-test-dataset\">new kernel with old aproch which based on autoencoder</a> is detected about 8% leakage. What are you think about it?</p>",
      "rawMarkdown": "In my [new kernel with old aproch which based on autoencoder](https://www.kaggle.com/miklgr500/leakage-detection-about-8-test-dataset) is detected about 8% leakage. What are you think about it?",
      "votes": null
    },
    {
      "id": "570044",
      "postDate": "07/07/2019 17:52:20",
      "content": "<p>Kernels will be re-run(or it re-run during submission, I still do not understood) with previously unseen test dataset, so if it is related for current test set only - it is not a big problem. But kernel is interesting, thanks for sharing this!</p>",
      "rawMarkdown": "Kernels will be re-run(or it re-run during submission, I still do not understood) with previously unseen test dataset, so if it is related for current test set only - it is not a big problem. But kernel is interesting, thanks for sharing this!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 570044,
      "author_name": "siarheifedartsou",
      "author_url": "",
      "post_date": "07/07/2019 17:52:20",
      "content": "<p>Kernels will be re-run(or it re-run during submission, I still do not understood) with previously unseen test dataset, so if it is related for current test set only - it is not a big problem. But kernel is interesting, thanks for sharing this!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "569557": "In my [new kernel with old aproch which based on autoencoder](https://www.kaggle.com/miklgr500/leakage-detection-about-8-test-dataset) is detected about 8% leakage. What are you think about it?",
    "570044": "Kernels will be re-run(or it re-run during submission, I still do not understood) with previously unseen test dataset, so if it is related for current test set only - it is not a big problem. But kernel is interesting, thanks for sharing this!"
  },
  "source": "meta"
}