{
  "id": 836,
  "title": "Can you post a condensed train file?",
  "url": "/competitions/ClaimPredictionChallenge/discussion/836",
  "author_name": "",
  "post_date": "2011-09-06T20:12:56.277Z",
  "votes": null,
  "comment_count": 3,
  "views": 4256,
  "content": "<p>Kaggle,</p>\r\n<p>I'd like to work on the Insurance challenge.&nbsp; The large file size is hard for me to handle.&nbsp; It has been said on the forum, that the characteristics are shared for each submodel.&nbsp; Could you wrap up the train file by submodel as said above and make that file\r\n available in the data download area?&nbsp;&nbsp;</p>\r\n<p>&nbsp;</p>",
  "messages": [
    {
      "id": "5428",
      "postDate": "09/06/2011 20:12:56",
      "content": "<p>Kaggle,</p>\r\n<p>I'd like to work on the Insurance challenge.&nbsp; The large file size is hard for me to handle.&nbsp; It has been said on the forum, that the characteristics are shared for each submodel.&nbsp; Could you wrap up the train file by submodel as said above and make that file\r\n available in the data download area?&nbsp;&nbsp;</p>\r\n<p>&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "5429",
      "postDate": "09/06/2011 20:23:48",
      "content": "<p>Is the issue transferring the file? If so, have you tried the more tightly compressed .7z files? If it's handling them once you've received them, have you tried importing them into a database?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "5430",
      "postDate": "09/06/2011 22:17:40",
      "content": "<p>Download went fine.&nbsp; There would be a learning curve for me to learn the database skills needed to condense the file?&nbsp; If this was easy for the administrator to do, I'd appreciate it.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "5431",
      "postDate": "09/06/2011 22:57:04",
      "content": "<p>It'd be a bit complicated to create since not all categories are shared amongst submodels (i.e. Row_ID of 12 and 13 differ in Cat11 and Cat12 although they are the same submodel). In addition, the similar columns aren't always the same (i.e. Row_ID 39 and\r\n 40 share same submodel, but differ in Cat9, Cat11, Cat10, Cat11, and Cat12). &nbsp;Also, it'd require more work on your side to effectively &quot;decompress&quot; this encoding.</p>\r\n<p>Therefore, I'd recommend that you use a database like SQLite, SQL Server Express, MySQL, or similar database. I show an example of what I did for this competition using SQL Server at:&nbsp;<a href=\"http://www.kaggle.com/c/ClaimPredictionChallenge/forums/t/711/importing-to-sql-server-and-aggregate-statistics/4605\">http://www.kaggle.com/c/ClaimPredictionChallenge/forums/t/711/importing-to-sql-server-and-aggregate-statistics/4605</a></p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 5429,
      "author_name": "jeffmoser",
      "author_url": "",
      "post_date": "09/06/2011 20:23:48",
      "content": "<p>Is the issue transferring the file? If so, have you tried the more tightly compressed .7z files? If it's handling them once you've received them, have you tried importing them into a database?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 5430,
      "author_name": "stephencollins",
      "author_url": "",
      "post_date": "09/06/2011 22:17:40",
      "content": "<p>Download went fine.&nbsp; There would be a learning curve for me to learn the database skills needed to condense the file?&nbsp; If this was easy for the administrator to do, I'd appreciate it.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 5431,
      "author_name": "jeffmoser",
      "author_url": "",
      "post_date": "09/06/2011 22:57:04",
      "content": "<p>It'd be a bit complicated to create since not all categories are shared amongst submodels (i.e. Row_ID of 12 and 13 differ in Cat11 and Cat12 although they are the same submodel). In addition, the similar columns aren't always the same (i.e. Row_ID 39 and\r\n 40 share same submodel, but differ in Cat9, Cat11, Cat10, Cat11, and Cat12). &nbsp;Also, it'd require more work on your side to effectively &quot;decompress&quot; this encoding.</p>\r\n<p>Therefore, I'd recommend that you use a database like SQLite, SQL Server Express, MySQL, or similar database. I show an example of what I did for this competition using SQL Server at:&nbsp;<a href=\"http://www.kaggle.com/c/ClaimPredictionChallenge/forums/t/711/importing-to-sql-server-and-aggregate-statistics/4605\">http://www.kaggle.com/c/ClaimPredictionChallenge/forums/t/711/importing-to-sql-server-and-aggregate-statistics/4605</a></p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "5428": "",
    "5429": "",
    "5430": "",
    "5431": ""
  },
  "source": "meta"
}