{
  "id": 6261,
  "title": "What are some ways that you have tried to convert the data for this competition into standard train_X, train_Y and test_X format so that it can be fed to ML libraries to predict test_Y?",
  "url": "/competitions/accelerometer-biometric-competition/discussion/6261",
  "author_name": "",
  "post_date": "2013-11-09T02:52:45.630Z",
  "votes": null,
  "comment_count": 1,
  "views": 1474,
  "content": "<p>What are some ways that you have tried to convert the data for this competition into standard train_X, train_Y and test_X format so that it can be fed to ML libraries to predict test_Y?</p>",
  "messages": [
    {
      "id": "33453",
      "postDate": "11/09/2013 02:52:45",
      "content": "<p>What are some ways that you have tried to convert the data for this competition into standard train_X, train_Y and test_X format so that it can be fed to ML libraries to predict test_Y?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "33480",
      "postDate": "11/09/2013 19:32:42",
      "content": "<p>Well, there seems to be leakage issues with this competition, and the host has acknowledged this, choosing to go on anyway, prizes and all. So I'm guessing there are quite a number of entries that try to exploit these issues, rather than employ ML approaches.</p>\n<p>That being said, I tried to mimic the evaluation process. I divided the train set into 300 points each within every device label, transformed them into a single data point, then applied the same transform on the test set. I'm playing with various models and ensembles on these transformed sets.</p>\n<p>&nbsp;</p>\n<p>&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 33480,
      "author_name": "barisumog",
      "author_url": "",
      "post_date": "11/09/2013 19:32:42",
      "content": "<p>Well, there seems to be leakage issues with this competition, and the host has acknowledged this, choosing to go on anyway, prizes and all. So I'm guessing there are quite a number of entries that try to exploit these issues, rather than employ ML approaches.</p>\n<p>That being said, I tried to mimic the evaluation process. I divided the train set into 300 points each within every device label, transformed them into a single data point, then applied the same transform on the test set. I'm playing with various models and ensembles on these transformed sets.</p>\n<p>&nbsp;</p>\n<p>&nbsp;</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "33453": "",
    "33480": ""
  },
  "source": "meta"
}