{
  "id": 337650,
  "title": "Any hint to speed up execution during submission?",
  "url": "/competitions/AI4Code/discussion/337650",
  "author_name": "",
  "post_date": "2022-07-17T01:18:48.783656200Z",
  "votes": 6,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Hello all, I am still new in data science and challenging this task as part of my learning.</p>\n<p>I am approaching this task as binary classification in this notebook <a href=\"https://www.kaggle.com/code/hechtjp/ai4code-inference-xgb-binary-classification\" target=\"_blank\">Link</a> but it's time out during submission.</p>\n<p>I am thinking to use cudf instead of pandas now but if you have any advice to me to speed up my code, could you share it with me?</p>\n<p>Thank you in advance.</p>",
  "messages": [
    {
      "id": "1858500",
      "postDate": "07/17/2022 01:18:48",
      "content": "<p>Hello all, I am still new in data science and challenging this task as part of my learning.</p>\n<p>I am approaching this task as binary classification in this notebook <a href=\"https://www.kaggle.com/code/hechtjp/ai4code-inference-xgb-binary-classification\" target=\"_blank\">Link</a> but it's time out during submission.</p>\n<p>I am thinking to use cudf instead of pandas now but if you have any advice to me to speed up my code, could you share it with me?</p>\n<p>Thank you in advance.</p>",
      "rawMarkdown": "Hello all, I am still new in data science and challenging this task as part of my learning.\n\nI am approaching this task as binary classification in this notebook [Link](https://www.kaggle.com/code/hechtjp/ai4code-inference-xgb-binary-classification) but it's time out during submission.\n\nI am thinking to use cudf instead of pandas now but if you have any advice to me to speed up my code, could you share it with me?\n\nThank you in advance.",
      "votes": null
    },
    {
      "id": "1859869",
      "postDate": "07/18/2022 02:58:44",
      "content": "<p>try this idea: <a href=\"https://www.kaggle.com/code/hengck23/fast-inference-deberta-xlarge-under-50min/notebook\" target=\"_blank\">https://www.kaggle.com/code/hengck23/fast-inference-deberta-xlarge-under-50min/notebook</a> </p>\n<p>But I do not think it works when you predict with a fixed length</p>",
      "rawMarkdown": "try this idea: https://www.kaggle.com/code/hengck23/fast-inference-deberta-xlarge-under-50min/notebook \n\nBut I do not think it works when you predict with a fixed length",
      "votes": null
    },
    {
      "id": "1860739",
      "postDate": "07/18/2022 14:06:33",
      "content": "<p><a href=\"https://www.kaggle.com/yuanzhezhou\" target=\"_blank\">@yuanzhezhou</a> , Thank you for your comment! I will check it as your recommendation🙏</p>",
      "rawMarkdown": "yuanzhezhou , Thank you for your comment! I will check it as your recommendation🙏",
      "votes": null
    },
    {
      "id": "1863055",
      "postDate": "07/20/2022 06:16:07",
      "content": "<p>You can try <a href=\"https://www.kaggle.com/competitions/AI4Code/discussion/336756\" target=\"_blank\">https://www.kaggle.com/competitions/AI4Code/discussion/336756</a></p>",
      "rawMarkdown": "You can try https://www.kaggle.com/competitions/AI4Code/discussion/336756",
      "votes": null
    },
    {
      "id": "1863951",
      "postDate": "07/20/2022 16:13:53",
      "content": "<p><a href=\"https://www.kaggle.com/readoc\" target=\"_blank\">@readoc</a> thanks for your comments! I checked your proposal in that link and will try it out! </p>",
      "rawMarkdown": "readoc thanks for your comments! I checked your proposal in that link and will try it out!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1859869,
      "author_name": "yuanzhezhou",
      "author_url": "",
      "post_date": "07/18/2022 02:58:44",
      "content": "<p>try this idea: <a href=\"https://www.kaggle.com/code/hengck23/fast-inference-deberta-xlarge-under-50min/notebook\" target=\"_blank\">https://www.kaggle.com/code/hengck23/fast-inference-deberta-xlarge-under-50min/notebook</a> </p>\n<p>But I do not think it works when you predict with a fixed length</p>",
      "votes": null,
      "replies": [
        {
          "id": 1860739,
          "author_name": "hechtjp",
          "author_url": "",
          "post_date": "07/18/2022 14:06:33",
          "content": "<p><a href=\"https://www.kaggle.com/yuanzhezhou\" target=\"_blank\">@yuanzhezhou</a> , Thank you for your comment! I will check it as your recommendation🙏</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1863055,
      "author_name": "readoc",
      "author_url": "",
      "post_date": "07/20/2022 06:16:07",
      "content": "<p>You can try <a href=\"https://www.kaggle.com/competitions/AI4Code/discussion/336756\" target=\"_blank\">https://www.kaggle.com/competitions/AI4Code/discussion/336756</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 1863951,
          "author_name": "hechtjp",
          "author_url": "",
          "post_date": "07/20/2022 16:13:53",
          "content": "<p><a href=\"https://www.kaggle.com/readoc\" target=\"_blank\">@readoc</a> thanks for your comments! I checked your proposal in that link and will try it out! </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1858500": "Hello all, I am still new in data science and challenging this task as part of my learning.\n\nI am approaching this task as binary classification in this notebook [Link](https://www.kaggle.com/code/hechtjp/ai4code-inference-xgb-binary-classification) but it's time out during submission.\n\nI am thinking to use cudf instead of pandas now but if you have any advice to me to speed up my code, could you share it with me?\n\nThank you in advance.",
    "1859869": "try this idea: https://www.kaggle.com/code/hengck23/fast-inference-deberta-xlarge-under-50min/notebook \n\nBut I do not think it works when you predict with a fixed length",
    "1860739": "yuanzhezhou , Thank you for your comment! I will check it as your recommendation🙏",
    "1863055": "You can try https://www.kaggle.com/competitions/AI4Code/discussion/336756",
    "1863951": "readoc thanks for your comments! I checked your proposal in that link and will try it out!"
  },
  "source": "meta"
}