{
  "id": 541968,
  "title": "Leveraging Kaggle Notebook With IDE(e,g Pycharm)",
  "url": "/competitions/ariel-data-challenge-2024/discussion/541968",
  "author_name": "work work",
  "post_date": "2024-10-22T10:07:56.167000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I think as the data for this competition is very huge, one approach is write the files project in local machine using IDE and clone it into kaggle notebook (add the path) without loading the data and training in the notebook , so we benefit from advantage of both kaggle notebook and IDE advantages</p>",
  "messages": [
    {
      "id": 3025039,
      "postDate": "2024-10-22T10:07:56.167Z",
      "content": "<p>I think as the data for this competition is very huge, one approach is write the files project in local machine using IDE and clone it into kaggle notebook (add the path) without loading the data and training in the notebook , so we benefit from advantage of both kaggle notebook and IDE advantages</p>",
      "rawMarkdown": "I think as the data for this competition is very huge, one approach is write the files project in local machine using IDE and clone it into kaggle notebook (add the path) without loading the data and training in the notebook , so we benefit from advantage of both kaggle notebook and IDE advantages",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "3025039": "I think as the data for this competition is very huge, one approach is write the files project in local machine using IDE and clone it into kaggle notebook (add the path) without loading the data and training in the notebook , so we benefit from advantage of both kaggle notebook and IDE advantages"
  }
}