{
  "id": 10119,
  "title": "Submission",
  "url": "/competitions/seizure-prediction/discussion/10119",
  "author_name": "",
  "post_date": "2014-08-26T18:36:11.357Z",
  "votes": null,
  "comment_count": 6,
  "views": 1744,
  "content": "<p>In the submission, you need a probability? OR just a 0 or 1 (have not or have seizure)?&nbsp;</p>",
  "messages": [
    {
      "id": "52467",
      "postDate": "08/26/2014 18:36:11",
      "content": "<p>In the submission, you need a probability? OR just a 0 or 1 (have not or have seizure)?&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "52468",
      "postDate": "08/26/2014 18:37:18",
      "content": "<p>For each clip in the test set, you should predict a real-valued probability that a given clip is preictal.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "52469",
      "postDate": "08/26/2014 18:40:09",
      "content": "<p>Great thanks,</p>\n\n<p>So it should look like:</p>\n<p>clip preictal<br>Dog_1_test_segment_x.mat <strong>0.4</strong><br>Dog_1_test_segment_y.mat <strong>0.9</strong><br>Dog_1_test_segment_z.mat <strong>0.1</strong></p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "52471",
      "postDate": "08/26/2014 18:43:12",
      "content": "<p>It should be comma separated like the sample:</p>\n\n<p>clip,preictal<br>Dog_1_test_segment_1.mat,0<br>Dog_1_test_segment_2.mat,0<br>Dog_1_test_segment_3.mat,0</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "52472",
      "postDate": "08/26/2014 18:45:31",
      "content": "<p>Yes I deleted the comma by accident.&nbsp;</p>\n<p>So it should be:</p>\n<p>clip,preictal<br>Dog_1_test_segment_1.mat,<strong>0.4</strong><br>Dog_1_test_segment_2.mat,<strong>0.9</strong><br>Dog_1_test_segment_3.mat,<strong>0.1</strong></p>\n<p>and NOT&nbsp;translating the above probabilities to 0 and 1:&nbsp;</p>\n<p>clip,preictal<br>Dog_1_test_segment_1.mat,<strong>0</strong><br>Dog_1_test_segment_2.mat,<strong>1</strong><br>Dog_1_test_segment_3.mat,<strong>0</strong></p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "53309",
      "postDate": "09/08/2014 00:17:06",
      "content": "<p>[quote=jlc142;52468]</p>\n<p>For each clip in the test set, you should predict a real-valued probability that a given clip is preictal.</p>\n<p>[/quote]</p>\n<p>How is scoring done? Given that the competition administrators have a binary outcome, interictal or preictal. For example, if the outcome is preictal (1) and the answer submitted is 0.6 how will this be scored? Also, if the outcome is preictal (1) and the answer submitted is 0.4 how will this be scored?</p>\n<p>Thanks,</p>\n<p>Kevin</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "53323",
      "postDate": "09/08/2014 05:55:46",
      "content": "<p>It uses the Area Under the Curve (AUC) of the Receiver operating characteristic (ROC)</p>\n<p>you can read more about it here http://en.wikipedia.org/wiki/Receiver_operating_characteristic</p>\n\n<p>basically it tests your predictions for various thresholds and judges the overall performance</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 52468,
      "author_name": "jlc142",
      "author_url": "",
      "post_date": "08/26/2014 18:37:18",
      "content": "<p>For each clip in the test set, you should predict a real-valued probability that a given clip is preictal.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 52469,
      "author_name": "kchlou",
      "author_url": "",
      "post_date": "08/26/2014 18:40:09",
      "content": "<p>Great thanks,</p>\n\n<p>So it should look like:</p>\n<p>clip preictal<br>Dog_1_test_segment_x.mat <strong>0.4</strong><br>Dog_1_test_segment_y.mat <strong>0.9</strong><br>Dog_1_test_segment_z.mat <strong>0.1</strong></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 52471,
      "author_name": "jlc142",
      "author_url": "",
      "post_date": "08/26/2014 18:43:12",
      "content": "<p>It should be comma separated like the sample:</p>\n\n<p>clip,preictal<br>Dog_1_test_segment_1.mat,0<br>Dog_1_test_segment_2.mat,0<br>Dog_1_test_segment_3.mat,0</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 52472,
      "author_name": "kchlou",
      "author_url": "",
      "post_date": "08/26/2014 18:45:31",
      "content": "<p>Yes I deleted the comma by accident.&nbsp;</p>\n<p>So it should be:</p>\n<p>clip,preictal<br>Dog_1_test_segment_1.mat,<strong>0.4</strong><br>Dog_1_test_segment_2.mat,<strong>0.9</strong><br>Dog_1_test_segment_3.mat,<strong>0.1</strong></p>\n<p>and NOT&nbsp;translating the above probabilities to 0 and 1:&nbsp;</p>\n<p>clip,preictal<br>Dog_1_test_segment_1.mat,<strong>0</strong><br>Dog_1_test_segment_2.mat,<strong>1</strong><br>Dog_1_test_segment_3.mat,<strong>0</strong></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 53309,
      "author_name": "kevinjos",
      "author_url": "",
      "post_date": "09/08/2014 00:17:06",
      "content": "<p>[quote=jlc142;52468]</p>\n<p>For each clip in the test set, you should predict a real-valued probability that a given clip is preictal.</p>\n<p>[/quote]</p>\n<p>How is scoring done? Given that the competition administrators have a binary outcome, interictal or preictal. For example, if the outcome is preictal (1) and the answer submitted is 0.6 how will this be scored? Also, if the outcome is preictal (1) and the answer submitted is 0.4 how will this be scored?</p>\n<p>Thanks,</p>\n<p>Kevin</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 53323,
      "author_name": "franklyn",
      "author_url": "",
      "post_date": "09/08/2014 05:55:46",
      "content": "<p>It uses the Area Under the Curve (AUC) of the Receiver operating characteristic (ROC)</p>\n<p>you can read more about it here http://en.wikipedia.org/wiki/Receiver_operating_characteristic</p>\n\n<p>basically it tests your predictions for various thresholds and judges the overall performance</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "52467": "",
    "52468": "",
    "52469": "",
    "52471": "",
    "52472": "",
    "53309": "",
    "53323": ""
  },
  "source": "meta"
}