{
  "id": 441799,
  "title": "Data processing is slow, any tips?",
  "url": "/competitions/predict-ai-model-runtime/discussion/441799",
  "author_name": "",
  "post_date": "2023-09-20T08:19:50.678035300Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Processing/formatting data to train my GNN is taking a lot of time, is there any way to speed this up?</p>",
  "messages": [
    {
      "id": "2447737",
      "postDate": "09/20/2023 08:19:50",
      "content": "<p>Processing/formatting data to train my GNN is taking a lot of time, is there any way to speed this up?</p>",
      "rawMarkdown": "Processing/formatting data to train my GNN is taking a lot of time, is there any way to speed this up?",
      "votes": null
    },
    {
      "id": "2448303",
      "postDate": "09/20/2023 14:06:21",
      "content": "<p>If you use tabular data anywhere in the process, I may recommend to use RAPIDS CuDF/ Polars instead of pandas. This offers a huge boost with regard to speed and ease of execution too. Also, using a PC with a good RAM and a good GPU will also help you. You may consider subscribing to a cloud service if your PC hardware is lacking too <a href=\"https://www.kaggle.com/vasudevak\" target=\"_blank\">@vasudevak</a> </p>",
      "rawMarkdown": "If you use tabular data anywhere in the process, I may recommend to use RAPIDS CuDF/ Polars instead of pandas. This offers a huge boost with regard to speed and ease of execution too. Also, using a PC with a good RAM and a good GPU will also help you. You may consider subscribing to a cloud service if your PC hardware is lacking too @vasudevak",
      "votes": null
    },
    {
      "id": "2448331",
      "postDate": "09/20/2023 14:19:51",
      "content": "<p>Thanks, I will check them out!</p>",
      "rawMarkdown": "Thanks, I will check them out!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2448303,
      "author_name": "ravi20076",
      "author_url": "",
      "post_date": "09/20/2023 14:06:21",
      "content": "<p>If you use tabular data anywhere in the process, I may recommend to use RAPIDS CuDF/ Polars instead of pandas. This offers a huge boost with regard to speed and ease of execution too. Also, using a PC with a good RAM and a good GPU will also help you. You may consider subscribing to a cloud service if your PC hardware is lacking too <a href=\"https://www.kaggle.com/vasudevak\" target=\"_blank\">@vasudevak</a> </p>",
      "votes": null,
      "replies": [
        {
          "id": 2448331,
          "author_name": "vasudevak",
          "author_url": "",
          "post_date": "09/20/2023 14:19:51",
          "content": "<p>Thanks, I will check them out!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2447737": "Processing/formatting data to train my GNN is taking a lot of time, is there any way to speed this up?",
    "2448303": "If you use tabular data anywhere in the process, I may recommend to use RAPIDS CuDF/ Polars instead of pandas. This offers a huge boost with regard to speed and ease of execution too. Also, using a PC with a good RAM and a good GPU will also help you. You may consider subscribing to a cloud service if your PC hardware is lacking too @vasudevak",
    "2448331": "Thanks, I will check them out!"
  },
  "source": "meta"
}