{
  "id": 338635,
  "title": "GANs for tabular data?",
  "url": "/competitions/amex-default-prediction/discussion/338635",
  "author_name": "",
  "post_date": "2022-07-21T08:55:19.972116100Z",
  "votes": 5,
  "comment_count": 6,
  "views": 0,
  "content": "<p>Anyone know how to implement GANs for tabular data? or can anyone point me to where it is located? or any relevant information. Googling gives pretty vague answers, searching through the code section of the competition did little to help as well as going  through the discussions was futile and I am hoping anyone here might have experience implementing it. The reason  ask is because I feel using a GAN might help squeeze out a little more  out of the models , we all know the positive effect it has in computer vision , It might just be amazing for tabular data specifically this competition. I could be wrong but there's only one way to find out right</p>",
  "messages": [
    {
      "id": "1864712",
      "postDate": "07/21/2022 08:55:19",
      "content": "<p>Anyone know how to implement GANs for tabular data? or can anyone point me to where it is located? or any relevant information. Googling gives pretty vague answers, searching through the code section of the competition did little to help as well as going  through the discussions was futile and I am hoping anyone here might have experience implementing it. The reason  ask is because I feel using a GAN might help squeeze out a little more  out of the models , we all know the positive effect it has in computer vision , It might just be amazing for tabular data specifically this competition. I could be wrong but there's only one way to find out right</p>",
      "rawMarkdown": "Anyone know how to implement GANs for tabular data? or can anyone point me to where it is located? or any relevant information. Googling gives pretty vague answers, searching through the code section of the competition did little to help as well as going  through the discussions was futile and I am hoping anyone here might have experience implementing it. The reason  ask is because I feel using a GAN might help squeeze out a little more  out of the models , we all know the positive effect it has in computer vision , It might just be amazing for tabular data specifically this competition. I could be wrong but there's only one way to find out right",
      "votes": null
    },
    {
      "id": "1864851",
      "postDate": "07/21/2022 10:38:32",
      "content": "<p><a href=\"https://www.kaggle.com/competitions/lish-moa/discussion/194976\" target=\"_blank\">CTGAN</a></p>",
      "rawMarkdown": "[CTGAN](https://www.kaggle.com/competitions/lish-moa/discussion/194976)",
      "votes": null
    },
    {
      "id": "1864856",
      "postDate": "07/21/2022 10:44:13",
      "content": "<p>I found a pretty informative youtube video.</p>\n<p><a href=\"url\" target=\"_blank\">https://www.youtube.com/watch?v=yujdA46HKwA</a></p>",
      "rawMarkdown": "I found a pretty informative youtube video.\n\n[https://www.youtube.com/watch?v=yujdA46HKwA](url)",
      "votes": null
    },
    {
      "id": "1864864",
      "postDate": "07/21/2022 10:48:25",
      "content": "<p>Thanks! <a href=\"https://www.kaggle.com/thedevastator\" target=\"_blank\">@thedevastator</a> </p>",
      "rawMarkdown": "Thanks! @thedevastator",
      "votes": null
    },
    {
      "id": "1864969",
      "postDate": "07/21/2022 12:05:25",
      "content": "<p>try sdv actually, it has 3 different gan models for tabular data and is pretty easy to use. i thought about using gan but it takes a very long time to train so i ended up focusing on improving other parts of my model… <br>\n<a href=\"https://sdv.dev/SDV/\" target=\"_blank\">https://sdv.dev/SDV/</a></p>",
      "rawMarkdown": "try sdv actually, it has 3 different gan models for tabular data and is pretty easy to use. i thought about using gan but it takes a very long time to train so i ended up focusing on improving other parts of my model... \nhttps://sdv.dev/SDV/",
      "votes": null
    },
    {
      "id": "1865941",
      "postDate": "07/22/2022 07:15:56",
      "content": "<p>thanks for the information </p>",
      "rawMarkdown": "thanks for the information",
      "votes": null
    },
    {
      "id": "2093941",
      "postDate": "01/10/2023 13:25:39",
      "content": "<p>Life saver ;)</p>",
      "rawMarkdown": "Life saver ;)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1864851,
      "author_name": "thedevastator",
      "author_url": "",
      "post_date": "07/21/2022 10:38:32",
      "content": "<p><a href=\"https://www.kaggle.com/competitions/lish-moa/discussion/194976\" target=\"_blank\">CTGAN</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 1864864,
          "author_name": "wuuthraad",
          "author_url": "",
          "post_date": "07/21/2022 10:48:25",
          "content": "<p>Thanks! <a href=\"https://www.kaggle.com/thedevastator\" target=\"_blank\">@thedevastator</a> </p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1864856,
      "author_name": "wuuthraad",
      "author_url": "",
      "post_date": "07/21/2022 10:44:13",
      "content": "<p>I found a pretty informative youtube video.</p>\n<p><a href=\"url\" target=\"_blank\">https://www.youtube.com/watch?v=yujdA46HKwA</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1864969,
      "author_name": "evanning",
      "author_url": "",
      "post_date": "07/21/2022 12:05:25",
      "content": "<p>try sdv actually, it has 3 different gan models for tabular data and is pretty easy to use. i thought about using gan but it takes a very long time to train so i ended up focusing on improving other parts of my model… <br>\n<a href=\"https://sdv.dev/SDV/\" target=\"_blank\">https://sdv.dev/SDV/</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 1865941,
          "author_name": "wuuthraad",
          "author_url": "",
          "post_date": "07/22/2022 07:15:56",
          "content": "<p>thanks for the information </p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 2093941,
          "author_name": "tharex",
          "author_url": "",
          "post_date": "01/10/2023 13:25:39",
          "content": "<p>Life saver ;)</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1864712": "Anyone know how to implement GANs for tabular data? or can anyone point me to where it is located? or any relevant information. Googling gives pretty vague answers, searching through the code section of the competition did little to help as well as going  through the discussions was futile and I am hoping anyone here might have experience implementing it. The reason  ask is because I feel using a GAN might help squeeze out a little more  out of the models , we all know the positive effect it has in computer vision , It might just be amazing for tabular data specifically this competition. I could be wrong but there's only one way to find out right",
    "1864851": "[CTGAN](https://www.kaggle.com/competitions/lish-moa/discussion/194976)",
    "1864856": "I found a pretty informative youtube video.\n\n[https://www.youtube.com/watch?v=yujdA46HKwA](url)",
    "1864864": "Thanks! @thedevastator",
    "1864969": "try sdv actually, it has 3 different gan models for tabular data and is pretty easy to use. i thought about using gan but it takes a very long time to train so i ended up focusing on improving other parts of my model... \nhttps://sdv.dev/SDV/",
    "1865941": "thanks for the information",
    "2093941": "Life saver ;)"
  },
  "source": "meta"
}