{
  "id": 11201,
  "title": "submission failing 'cause 4560000+ ids not matching after upload",
  "url": "/competitions/avazu-ctr-prediction/discussion/11201",
  "author_name": "",
  "post_date": "2014-12-10T23:13:55.050Z",
  "votes": 1,
  "comment_count": 5,
  "views": 1345,
  "content": "<p>Hi...while uploading submission, an error shows up saying&nbsp;4560000+ are not matching and then gives several ids which are actually not matching.</p>\n<p>I checked some of the ids which are showed by the error and all of them matches with both &nbsp;submission.csv and the test data.</p>\n<p>Has anyone else faced this problem? Would appreciate if thrown some light on this.</p>\n<p>Thanks,</p>\n<p>Avishek</p>",
  "messages": [
    {
      "id": "59976",
      "postDate": "12/10/2014 23:13:55",
      "content": "<p>Hi...while uploading submission, an error shows up saying&nbsp;4560000+ are not matching and then gives several ids which are actually not matching.</p>\n<p>I checked some of the ids which are showed by the error and all of them matches with both &nbsp;submission.csv and the test data.</p>\n<p>Has anyone else faced this problem? Would appreciate if thrown some light on this.</p>\n<p>Thanks,</p>\n<p>Avishek</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "59998",
      "postDate": "12/11/2014 13:45:42",
      "content": "<p>If you post the method you've used to create your submission then I'm sure someone will be able to spot what is going wrong. There was a post about R converting the ids into scientific notation and that was easily solved by forcing them to be read as 'character'. But it probably all depends on which tools and code you are using.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "60181",
      "postDate": "12/14/2014 08:06:49",
      "content": "<p>I am facing the same problem, in MATLAB. The ID's don't match those of the test data.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "60195",
      "postDate": "12/14/2014 17:32:52",
      "content": "<p>In MATLAB, I read the entire file test.csv as a dataset. I then convert the id column into a character string (num2str) and then create the submission file.&nbsp;I still get a similar error. Attached is a screenshot.&nbsp;</p>\n<p>Any suggestions?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "60223",
      "postDate": "12/15/2014 05:49:24",
      "content": "<p>@lewis ml - you are right.</p>\n<p>The ids get changed due to the precision. I have the same issue.&nbsp;</p>\n<p>Until I figure out, I simply read the ids as string from the sampleSubmission.csv and used it. As long as the order remains the same, this should do.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "60246",
      "postDate": "12/15/2014 18:03:49",
      "content": "<p>Problem solved after reading id as string.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 59998,
      "author_name": "cartographic",
      "author_url": "",
      "post_date": "12/11/2014 13:45:42",
      "content": "<p>If you post the method you've used to create your submission then I'm sure someone will be able to spot what is going wrong. There was a post about R converting the ids into scientific notation and that was easily solved by forcing them to be read as 'character'. But it probably all depends on which tools and code you are using.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 60181,
      "author_name": "anujamkelkar",
      "author_url": "",
      "post_date": "12/14/2014 08:06:49",
      "content": "<p>I am facing the same problem, in MATLAB. The ID's don't match those of the test data.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 60195,
      "author_name": "",
      "author_url": "",
      "post_date": "12/14/2014 17:32:52",
      "content": "<p>In MATLAB, I read the entire file test.csv as a dataset. I then convert the id column into a character string (num2str) and then create the submission file.&nbsp;I still get a similar error. Attached is a screenshot.&nbsp;</p>\n<p>Any suggestions?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 60223,
      "author_name": "ipower2",
      "author_url": "",
      "post_date": "12/15/2014 05:49:24",
      "content": "<p>@lewis ml - you are right.</p>\n<p>The ids get changed due to the precision. I have the same issue.&nbsp;</p>\n<p>Until I figure out, I simply read the ids as string from the sampleSubmission.csv and used it. As long as the order remains the same, this should do.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 60246,
      "author_name": "avishek",
      "author_url": "",
      "post_date": "12/15/2014 18:03:49",
      "content": "<p>Problem solved after reading id as string.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "59976": "",
    "59998": "",
    "60181": "",
    "60195": "",
    "60223": "",
    "60246": ""
  },
  "source": "meta"
}