{
  "id": 97953,
  "title": "Features selection tried methods? ",
  "url": "/competitions/champs-scalar-coupling/discussion/97953",
  "author_name": "",
  "post_date": "2019-06-30T07:05:37.014685700Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I tried creating additional features by log transforming original ones (and other transformations). \nOnly problem is that the new dataset is very large. So I decided to do some features selection. </p>\n\n<p>Anyone has luck with this approach already? If so, what types of algorithms have you tried? </p>\n\n<p>Many thanks. :)</p>",
  "messages": [
    {
      "id": "564924",
      "postDate": "06/30/2019 07:05:37",
      "content": "<p>I tried creating additional features by log transforming original ones (and other transformations). \nOnly problem is that the new dataset is very large. So I decided to do some features selection. </p>\n\n<p>Anyone has luck with this approach already? If so, what types of algorithms have you tried? </p>\n\n<p>Many thanks. :)</p>",
      "rawMarkdown": "I tried creating additional features by log transforming original ones (and other transformations). \nOnly problem is that the new dataset is very large. So I decided to do some features selection. \n\nAnyone has luck with this approach already? If so, what types of algorithms have you tried? \n\nMany thanks. :)",
      "votes": null
    },
    {
      "id": "564945",
      "postDate": "06/30/2019 07:46:45",
      "content": "<p>Check this:\n - <a href=\"https://www.kaggle.com/speedwagon/permutation-importance\">https://www.kaggle.com/speedwagon/permutation-importance</a>\n - <a href=\"https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc\">https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc</a></p>",
      "rawMarkdown": "Check this:\n - https://www.kaggle.com/speedwagon/permutation-importance\n - https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc",
      "votes": null
    },
    {
      "id": "564977",
      "postDate": "06/30/2019 09:24:49",
      "content": "<p>Thanks for the suggestions. 👍 </p>",
      "rawMarkdown": "Thanks for the suggestions. 👍",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 564945,
      "author_name": "speedwagon",
      "author_url": "",
      "post_date": "06/30/2019 07:46:45",
      "content": "<p>Check this:\n - <a href=\"https://www.kaggle.com/speedwagon/permutation-importance\">https://www.kaggle.com/speedwagon/permutation-importance</a>\n - <a href=\"https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc\">https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 564977,
          "author_name": "yassinealouini",
          "author_url": "",
          "post_date": "06/30/2019 09:24:49",
          "content": "<p>Thanks for the suggestions. 👍 </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "564924": "I tried creating additional features by log transforming original ones (and other transformations). \nOnly problem is that the new dataset is very large. So I decided to do some features selection. \n\nAnyone has luck with this approach already? If so, what types of algorithms have you tried? \n\nMany thanks. :)",
    "564945": "Check this:\n - https://www.kaggle.com/speedwagon/permutation-importance\n - https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc",
    "564977": "Thanks for the suggestions. 👍"
  },
  "source": "meta"
}