{
  "id": 497750,
  "title": "\"persontype\" is categorical feature",
  "url": "/competitions/home-credit-credit-risk-model-stability/discussion/497750",
  "author_name": "Tokhchukov Danil",
  "post_date": "2024-04-25T15:13:49.112000",
  "votes": 24,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Faced that in the table <code>train_person_1</code> are two features: <code>persontype_1072L</code> and <code>persontype_792L</code> that are categorical features, but they are recognized as numeric when loading tables. So don't forget to pass these features as categorical to your models.</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2F0af9eb97426e9df613d68054d1494e16%2FScreenshot%20from%202024-04-25%2018-12-02.png?generation=1714057986659571&amp;alt=media\"><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2Fe1aa230f44da44f3cadbce3e35f8ec27%2FScreenshot%20from%202024-04-25%2018-12-18.png?generation=1714057995251861&amp;alt=media\"></p>",
  "messages": [
    {
      "id": 2775260,
      "postDate": "2024-04-25T15:13:49.113Z",
      "content": "<p>Faced that in the table <code>train_person_1</code> are two features: <code>persontype_1072L</code> and <code>persontype_792L</code> that are categorical features, but they are recognized as numeric when loading tables. So don't forget to pass these features as categorical to your models.</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2F0af9eb97426e9df613d68054d1494e16%2FScreenshot%20from%202024-04-25%2018-12-02.png?generation=1714057986659571&amp;alt=media\"><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2Fe1aa230f44da44f3cadbce3e35f8ec27%2FScreenshot%20from%202024-04-25%2018-12-18.png?generation=1714057995251861&amp;alt=media\"></p>",
      "rawMarkdown": "Faced that in the table `train_person_1` are two features: `persontype_1072L` and `persontype_792L` that are categorical features, but they are recognized as numeric when loading tables. So don't forget to pass these features as categorical to your models.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2F0af9eb97426e9df613d68054d1494e16%2FScreenshot%20from%202024-04-25%2018-12-02.png?generation=1714057986659571&alt=media)\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2Fe1aa230f44da44f3cadbce3e35f8ec27%2FScreenshot%20from%202024-04-25%2018-12-18.png?generation=1714057995251861&alt=media)",
      "votes": 24
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2775260": "Faced that in the table `train_person_1` are two features: `persontype_1072L` and `persontype_792L` that are categorical features, but they are recognized as numeric when loading tables. So don't forget to pass these features as categorical to your models.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2F0af9eb97426e9df613d68054d1494e16%2FScreenshot%20from%202024-04-25%2018-12-02.png?generation=1714057986659571&alt=media)\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F8742596%2Fe1aa230f44da44f3cadbce3e35f8ec27%2FScreenshot%20from%202024-04-25%2018-12-18.png?generation=1714057995251861&alt=media)"
  }
}