{
  "id": 369419,
  "title": "💡 How to split the data for training a two-stage recommender?",
  "url": "/competitions/otto-recommender-system/discussion/369419",
  "author_name": "",
  "post_date": "2022-11-30T06:39:46.846392500Z",
  "votes": 6,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hey!</p>\n<p>This is a question I get asked a lot. I thought I'd share some information that can maybe make this consideration more approachable.</p>\n<p>As this pertains to data, I have added a completely new section to my EDA on this:</p>\n<p><a href=\"https://www.kaggle.com/code/radek1/eda-a-look-at-the-data-training-splits\" target=\"_blank\">📈 [EDA] A look at the data + training splits</a>. </p>\n<p>If you have any questions on this, let me know! Happy to also upload another dataset that would contain the full validation setup I mention there if that would be useful.</p>\n<p>Happy Kaggling! 🥳</p>",
  "messages": [
    {
      "id": "2049437",
      "postDate": "11/30/2022 06:39:46",
      "content": "<p>Hey!</p>\n<p>This is a question I get asked a lot. I thought I'd share some information that can maybe make this consideration more approachable.</p>\n<p>As this pertains to data, I have added a completely new section to my EDA on this:</p>\n<p><a href=\"https://www.kaggle.com/code/radek1/eda-a-look-at-the-data-training-splits\" target=\"_blank\">📈 [EDA] A look at the data + training splits</a>. </p>\n<p>If you have any questions on this, let me know! Happy to also upload another dataset that would contain the full validation setup I mention there if that would be useful.</p>\n<p>Happy Kaggling! 🥳</p>",
      "rawMarkdown": "Hey!\n\nThis is a question I get asked a lot. I thought I'd share some information that can maybe make this consideration more approachable.\n\nAs this pertains to data, I have added a completely new section to my EDA on this:\n\n[📈 [EDA] A look at the data + training splits](https://www.kaggle.com/code/radek1/eda-a-look-at-the-data-training-splits). \n\nIf you have any questions on this, let me know! Happy to also upload another dataset that would contain the full validation setup I mention there if that would be useful.\n\nHappy Kaggling! 🥳",
      "votes": null
    },
    {
      "id": "2050740",
      "postDate": "12/01/2022 00:22:41",
      "content": "<p>Thank you <a href=\"https://www.kaggle.com/radek1\" target=\"_blank\">@radek1</a> for the notebook. Very helpful and clean code </p>",
      "rawMarkdown": "Thank you @radek1 for the notebook. Very helpful and clean code",
      "votes": null
    },
    {
      "id": "2051033",
      "postDate": "12/01/2022 06:53:57",
      "content": "<p>My pleasure! 🙂 Glad you've found it useful!</p>",
      "rawMarkdown": "My pleasure! 🙂 Glad you've found it useful!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2050740,
      "author_name": "abhishek14398",
      "author_url": "",
      "post_date": "12/01/2022 00:22:41",
      "content": "<p>Thank you <a href=\"https://www.kaggle.com/radek1\" target=\"_blank\">@radek1</a> for the notebook. Very helpful and clean code </p>",
      "votes": null,
      "replies": [
        {
          "id": 2051033,
          "author_name": "radek1",
          "author_url": "",
          "post_date": "12/01/2022 06:53:57",
          "content": "<p>My pleasure! 🙂 Glad you've found it useful!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2049437": "Hey!\n\nThis is a question I get asked a lot. I thought I'd share some information that can maybe make this consideration more approachable.\n\nAs this pertains to data, I have added a completely new section to my EDA on this:\n\n[📈 [EDA] A look at the data + training splits](https://www.kaggle.com/code/radek1/eda-a-look-at-the-data-training-splits). \n\nIf you have any questions on this, let me know! Happy to also upload another dataset that would contain the full validation setup I mention there if that would be useful.\n\nHappy Kaggling! 🥳",
    "2050740": "Thank you @radek1 for the notebook. Very helpful and clean code",
    "2051033": "My pleasure! 🙂 Glad you've found it useful!"
  },
  "source": "meta"
}