{
  "id": 10825,
  "title": "Code and Documentation for Winning Solution",
  "content": "<p>Hi,</p>\n<p>Here I attached the&nbsp;documentation and <a href=\"https://github.com/Yasssser/AFSIS2014\">this&nbsp;</a>is the code repository.</p>\n<p>Sorry for my poor English!</p>\n<p>Thanks,</p>\n<p>Yasser</p>",
  "comments": [
    {
      "id": 57274,
      "author_name": "Yasser Tabandeh",
      "author_url": "",
      "post_date": "2014-11-04T06:18:41.487000",
      "content": "<p>[quote=Patrick Chan;57270]</p>\n<p>Congrats Yasser, &nbsp;was wondering how you arrive at the weights for linearly combining all the ensemble of classifiers? &nbsp;Saw you put in the weight in the code. &nbsp;Can you help shine some light on this? &nbsp;Thanks.</p>\n<p>Patrick</p>\n<p>[/quote]</p>\n<p>Hi Patrick,</p>\n<p>The weights are based on the quality of results of single models in repeated<br>cross validation steps, so these weights are not optimal.</p>",
      "votes": 4,
      "replies": []
    },
    {
      "id": 111271,
      "author_name": "سیدماشالله چاقه",
      "author_url": "",
      "post_date": "2016-03-13T09:02:44.720000",
      "content": "<p>[quote=Yasser Tabandeh;57196]</p>\n<p>Hi,</p>\n<p>Here I attached the&nbsp;documentation and <a href=\"https://github.com/Yasssser/AFSIS2014\">this&nbsp;</a>is the code repository.</p>\n<p>Sorry for my poor English!</p>\n<p>Thanks,</p>\n<p>Yasser</p>\n<p>[/quote]</p>\n<p>&#1587;&#1604;&#1575;&#1605; &#1576;&#1575;&#1587;&#1585; <br>&#1578;&#1576;&#1585;&#1740;&#1705; &#1576;&#1575;&#1576;&#1578; &#1576;&#1585;&#1606;&#1583;&#1607; &#1588;&#1583;&#1606;&#1578;.&#1575;&#1586; &#1575;&#1740;&#1606;&#1705;&#1607; &#1583;&#1740;&#1583;&#1605; &#1740;&#1705; &#1575;&#1740;&#1585;&#1575;&#1606;&#1740; &#1575;&#1608;&#1604; &#1588;&#1583;&#1607; &#1582;&#1740;&#1604;&#1740; &#1582;&#1608;&#1588;&#1581;&#1575;&#1604;&#1605;.&#1585;&#1575; &#1575;&#1585;&#1578;&#1576;&#1575;&#1591;&#1740; &#1607;&#1587;&#1578; &#1705;&#1607; &#1576;&#1578;&#1608;&#1606;&#1605; &#1705;&#1605;&#1740; &#1575;&#1586; &#1578;&#1580;&#1585;&#1576;&#1740;&#1575;&#1578;&#1578; &#1575;&#1587;&#1578;&#1601;&#1575;&#1583;&#1607; &#1705;&#1606;&#1605;&#1567;<br>&#1605;&#1605;&#1606;&#1608;&#1606;</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 111270,
      "author_name": "سیدماشالله چاقه",
      "author_url": "",
      "post_date": "2016-03-13T09:00:11.717000",
      "content": "",
      "votes": 0,
      "replies": []
    },
    {
      "id": 57270,
      "author_name": "Patrick Chan",
      "author_url": "",
      "post_date": "2014-11-04T05:11:01.327000",
      "content": "<p>Congrats Yasser, &nbsp;was wondering how you arrive at the weights for linearly combining all the ensemble of classifiers? &nbsp;Saw you put in the weight in the code. &nbsp;Can you help shine some light on this? &nbsp;Thanks.</p>\n<p>Patrick</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 57268,
      "author_name": "Patrick Chan",
      "author_url": "",
      "post_date": "2014-11-04T05:03:24.340000",
      "content": "<p>Thanks Yasser.</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "comment_count": 5,
  "messages": [
    {
      "id": 57196,
      "postDate": "2014-11-02T16:03:53.807Z",
      "content": "<p>Hi,</p>\n<p>Here I attached the&nbsp;documentation and <a href=\"https://github.com/Yasssser/AFSIS2014\">this&nbsp;</a>is the code repository.</p>\n<p>Sorry for my poor English!</p>\n<p>Thanks,</p>\n<p>Yasser</p>",
      "votes": 17
    },
    {
      "id": 57274,
      "postDate": "2014-11-04T06:18:41.487Z",
      "content": "<p>[quote=Patrick Chan;57270]</p>\n<p>Congrats Yasser, &nbsp;was wondering how you arrive at the weights for linearly combining all the ensemble of classifiers? &nbsp;Saw you put in the weight in the code. &nbsp;Can you help shine some light on this? &nbsp;Thanks.</p>\n<p>Patrick</p>\n<p>[/quote]</p>\n<p>Hi Patrick,</p>\n<p>The weights are based on the quality of results of single models in repeated<br>cross validation steps, so these weights are not optimal.</p>",
      "votes": 4
    },
    {
      "id": 111271,
      "postDate": "2016-03-13T09:02:44.720Z",
      "content": "<p>[quote=Yasser Tabandeh;57196]</p>\n<p>Hi,</p>\n<p>Here I attached the&nbsp;documentation and <a href=\"https://github.com/Yasssser/AFSIS2014\">this&nbsp;</a>is the code repository.</p>\n<p>Sorry for my poor English!</p>\n<p>Thanks,</p>\n<p>Yasser</p>\n<p>[/quote]</p>\n<p>&#1587;&#1604;&#1575;&#1605; &#1576;&#1575;&#1587;&#1585; <br>&#1578;&#1576;&#1585;&#1740;&#1705; &#1576;&#1575;&#1576;&#1578; &#1576;&#1585;&#1606;&#1583;&#1607; &#1588;&#1583;&#1606;&#1578;.&#1575;&#1586; &#1575;&#1740;&#1606;&#1705;&#1607; &#1583;&#1740;&#1583;&#1605; &#1740;&#1705; &#1575;&#1740;&#1585;&#1575;&#1606;&#1740; &#1575;&#1608;&#1604; &#1588;&#1583;&#1607; &#1582;&#1740;&#1604;&#1740; &#1582;&#1608;&#1588;&#1581;&#1575;&#1604;&#1605;.&#1585;&#1575; &#1575;&#1585;&#1578;&#1576;&#1575;&#1591;&#1740; &#1607;&#1587;&#1578; &#1705;&#1607; &#1576;&#1578;&#1608;&#1606;&#1605; &#1705;&#1605;&#1740; &#1575;&#1586; &#1578;&#1580;&#1585;&#1576;&#1740;&#1575;&#1578;&#1578; &#1575;&#1587;&#1578;&#1601;&#1575;&#1583;&#1607; &#1705;&#1606;&#1605;&#1567;<br>&#1605;&#1605;&#1606;&#1608;&#1606;</p>"
    },
    {
      "id": 111270,
      "postDate": "2016-03-13T09:00:11.717Z",
      "rawMarkdown": ""
    },
    {
      "id": 57270,
      "postDate": "2014-11-04T05:11:01.327Z",
      "content": "<p>Congrats Yasser, &nbsp;was wondering how you arrive at the weights for linearly combining all the ensemble of classifiers? &nbsp;Saw you put in the weight in the code. &nbsp;Can you help shine some light on this? &nbsp;Thanks.</p>\n<p>Patrick</p>"
    },
    {
      "id": 57268,
      "postDate": "2014-11-04T05:03:24.340Z",
      "content": "<p>Thanks Yasser.</p>"
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T17:35:34Z",
  "competition_id": 3966,
  "competition_slug": "afsis-soil-properties",
  "team_id": 116423,
  "solution_url": "/competitions/afsis-soil-properties/writeups/yasser-tabandeh-code-and-documentation-for-winning"
}