{
  "id": 20628,
  "title": "How long does it take to generate results with R roughly?",
  "url": "/competitions/expedia-hotel-recommendations/discussion/20628",
  "author_name": "",
  "post_date": "2016-05-02T14:45:03.027Z",
  "votes": null,
  "comment_count": 1,
  "views": 392,
  "content": "<p>Could I know roughly how long it takes to generate results with R roughly?</p>",
  "messages": [
    {
      "id": "118016",
      "postDate": "05/02/2016 14:45:03",
      "content": "<p>Could I know roughly how long it takes to generate results with R roughly?</p>",
      "rawMarkdown": "Could I know roughly how long it takes to generate results with R roughly?",
      "votes": null
    },
    {
      "id": "118019",
      "postDate": "05/02/2016 14:55:55",
      "content": "<p>This will depend on the train size (rows and columns) you choose to use. And of course on the model. And on your CPU/cores and RAM.</p>\n\n<p>Can't tell!</p>\n\n<p>But for reasonable results it will take both a good amount of RAM and CPU! We are talking hours and hours. Had an xgboost with 2.500.000 train rows cross validating and predicting for maybe 10 hours on a 8 core machine with 32 GB of RAM. Result: 0.28.</p>\n\n<p>Gerhard</p>",
      "rawMarkdown": "This will depend on the train size (rows and columns) you choose to use. And of course on the model. And on your CPU/cores and RAM.\r\n\r\nCan't tell!\r\n\r\n\r\nBut for reasonable results it will take both a good amount of RAM and CPU! We are talking hours and hours. Had an xgboost with 2.500.000 train rows cross validating and predicting for maybe 10 hours on a 8 core machine with 32 GB of RAM. Result: 0.28.\r\n\r\nGerhard",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 118019,
      "author_name": "mightybird",
      "author_url": "",
      "post_date": "05/02/2016 14:55:55",
      "content": "<p>This will depend on the train size (rows and columns) you choose to use. And of course on the model. And on your CPU/cores and RAM.</p>\n\n<p>Can't tell!</p>\n\n<p>But for reasonable results it will take both a good amount of RAM and CPU! We are talking hours and hours. Had an xgboost with 2.500.000 train rows cross validating and predicting for maybe 10 hours on a 8 core machine with 32 GB of RAM. Result: 0.28.</p>\n\n<p>Gerhard</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "118016": "Could I know roughly how long it takes to generate results with R roughly?",
    "118019": "This will depend on the train size (rows and columns) you choose to use. And of course on the model. And on your CPU/cores and RAM.\r\n\r\nCan't tell!\r\n\r\n\r\nBut for reasonable results it will take both a good amount of RAM and CPU! We are talking hours and hours. Had an xgboost with 2.500.000 train rows cross validating and predicting for maybe 10 hours on a 8 core machine with 32 GB of RAM. Result: 0.28.\r\n\r\nGerhard"
  },
  "source": "meta"
}