{
  "id": 1186,
  "title": "Help on Algos",
  "url": "/competitions/WhatDoYouKnow/discussion/1186",
  "author_name": "",
  "post_date": "2011-12-20T16:32:40.433Z",
  "votes": null,
  "comment_count": 1,
  "views": 2087,
  "content": "<p>Dears</p>\r\n<p>I am using Knime which is giving Java Heap space error. I tried to extend the memory through ini file but it didnt work. I cannot run any classification technique in Knime and Weka due to this and I dont know how to use 'R'?</p>\r\n<p>Can anybody help in this?</p>\r\n<p>Regards</p>\r\n<p>M Asif</p>",
  "messages": [
    {
      "id": "7380",
      "postDate": "12/20/2011 16:32:40",
      "content": "<p>Dears</p>\r\n<p>I am using Knime which is giving Java Heap space error. I tried to extend the memory through ini file but it didnt work. I cannot run any classification technique in Knime and Weka due to this and I dont know how to use 'R'?</p>\r\n<p>Can anybody help in this?</p>\r\n<p>Regards</p>\r\n<p>M Asif</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "7444",
      "postDate": "12/23/2011 01:37:48",
      "content": "<p>Hi Asif:</p>\r\n<p>Looks like you are getting &quot;heap space error&quot; because you are running out of memory.\r\n</p>\r\n<p>Here's a high-level suggestion that may or may not help:</p>\r\n<p>When you run into memory problems, at some level you have to partition the problem. If the training file is large, you have to figure out ways to break it up into meaningful pieces. You can use any programming language (or scripting software) to accomplish\r\n this - for example Python if you can use that. One logical way to break up the data in the Grockit competition would be by (say) group<em>name or track</em>name.</p>\r\n<p>The paradigm doesn't change: S-A-C Split, Apply (some processing) and Combine. The details is what always takes time for all of us.</p>\r\n<p>I apologize if this is too elementary or too high-level.</p>\r\n<p>Ram</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 7444,
      "author_name": "ramn25556",
      "author_url": "",
      "post_date": "12/23/2011 01:37:48",
      "content": "<p>Hi Asif:</p>\r\n<p>Looks like you are getting &quot;heap space error&quot; because you are running out of memory.\r\n</p>\r\n<p>Here's a high-level suggestion that may or may not help:</p>\r\n<p>When you run into memory problems, at some level you have to partition the problem. If the training file is large, you have to figure out ways to break it up into meaningful pieces. You can use any programming language (or scripting software) to accomplish\r\n this - for example Python if you can use that. One logical way to break up the data in the Grockit competition would be by (say) group<em>name or track</em>name.</p>\r\n<p>The paradigm doesn't change: S-A-C Split, Apply (some processing) and Combine. The details is what always takes time for all of us.</p>\r\n<p>I apologize if this is too elementary or too high-level.</p>\r\n<p>Ram</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "7380": "",
    "7444": ""
  },
  "source": "meta"
}