{
  "id": 129555,
  "title": "Ensemble of 3 Models",
  "url": "/competitions/cat-in-the-dat-ii/discussion/129555",
  "author_name": "",
  "post_date": "2020-02-09T00:18:54.694309700Z",
  "votes": 9,
  "comment_count": 7,
  "views": 0,
  "content": "<p>Hello friends,</p>\n\n<p>I have created a kernel which shows how to create an ensemble of three methods. It gives you the weight for each method to achieve a better auc - because prediction variance decreases. \nAlthough it is created in R you can translate it easily to Python. </p>\n\n<p><a href=\"https://www.kaggle.com/frankmollard/bag3models\">Bag3Models</a></p>\n\n<p>It is my first kernel. Donˋt hesitate to comment. If you find it useful, please upvote the kernel.</p>\n\n<p>Thank you!</p>",
  "messages": [
    {
      "id": "740139",
      "postDate": "02/09/2020 00:18:54",
      "content": "<p>Hello friends,</p>\n\n<p>I have created a kernel which shows how to create an ensemble of three methods. It gives you the weight for each method to achieve a better auc - because prediction variance decreases. \nAlthough it is created in R you can translate it easily to Python. </p>\n\n<p><a href=\"https://www.kaggle.com/frankmollard/bag3models\">Bag3Models</a></p>\n\n<p>It is my first kernel. Donˋt hesitate to comment. If you find it useful, please upvote the kernel.</p>\n\n<p>Thank you!</p>",
      "rawMarkdown": "Hello friends,\n\nI have created a kernel which shows how to create an ensemble of three methods. It gives you the weight for each method to achieve a better auc - because prediction variance decreases. \nAlthough it is created in R you can translate it easily to Python. \n\n[Bag3Models](https://www.kaggle.com/frankmollard/bag3models)\n\nIt is my first kernel. Donˋt hesitate to comment. If you find it useful, please upvote the kernel.\n\nThank you!",
      "votes": null
    },
    {
      "id": "741604",
      "postDate": "02/10/2020 20:34:57",
      "content": "<p>Thanks for the kernel ! very helpful</p>",
      "rawMarkdown": "Thanks for the kernel ! very helpful",
      "votes": null
    },
    {
      "id": "745197",
      "postDate": "02/13/2020 15:50:07",
      "content": "<p>You are welcome 😊 </p>",
      "rawMarkdown": "You are welcome 😊",
      "votes": null
    },
    {
      "id": "761531",
      "postDate": "03/02/2020 16:22:30",
      "content": "<p>Nice kernel. </p>",
      "rawMarkdown": "Nice kernel.",
      "votes": null
    },
    {
      "id": "761532",
      "postDate": "03/02/2020 16:25:49",
      "content": "<p>Thank you!!!</p>",
      "rawMarkdown": "Thank you!!!",
      "votes": null
    },
    {
      "id": "762384",
      "postDate": "03/03/2020 13:38:45",
      "content": "<p>beautiful!\nupvoted!👍 </p>",
      "rawMarkdown": "beautiful!\nupvoted!👍",
      "votes": null
    },
    {
      "id": "762391",
      "postDate": "03/03/2020 13:39:48",
      "content": "<p>beautiful!!\nupvoted!!</p>",
      "rawMarkdown": "beautiful!!\nupvoted!!",
      "votes": null
    },
    {
      "id": "762474",
      "postDate": "03/03/2020 14:38:22",
      "content": "<p>great <a href=\"/frankmollard\">@frankmollard</a> ! thanks for sharing</p>",
      "rawMarkdown": "great @frankmollard ! thanks for sharing",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 741604,
      "author_name": "anisszakari",
      "author_url": "",
      "post_date": "02/10/2020 20:34:57",
      "content": "<p>Thanks for the kernel ! very helpful</p>",
      "votes": null,
      "replies": [
        {
          "id": 745197,
          "author_name": "frankmollard",
          "author_url": "",
          "post_date": "02/13/2020 15:50:07",
          "content": "<p>You are welcome 😊 </p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 761531,
      "author_name": "manishkr73",
      "author_url": "",
      "post_date": "03/02/2020 16:22:30",
      "content": "<p>Nice kernel. </p>",
      "votes": null,
      "replies": [
        {
          "id": 761532,
          "author_name": "frankmollard",
          "author_url": "",
          "post_date": "03/02/2020 16:25:49",
          "content": "<p>Thank you!!!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 762384,
      "author_name": "",
      "author_url": "",
      "post_date": "03/03/2020 13:38:45",
      "content": "<p>beautiful!\nupvoted!👍 </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 762391,
      "author_name": "",
      "author_url": "",
      "post_date": "03/03/2020 13:39:48",
      "content": "<p>beautiful!!\nupvoted!!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 762474,
      "author_name": "waeldahech",
      "author_url": "",
      "post_date": "03/03/2020 14:38:22",
      "content": "<p>great <a href=\"/frankmollard\">@frankmollard</a> ! thanks for sharing</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "740139": "Hello friends,\n\nI have created a kernel which shows how to create an ensemble of three methods. It gives you the weight for each method to achieve a better auc - because prediction variance decreases. \nAlthough it is created in R you can translate it easily to Python. \n\n[Bag3Models](https://www.kaggle.com/frankmollard/bag3models)\n\nIt is my first kernel. Donˋt hesitate to comment. If you find it useful, please upvote the kernel.\n\nThank you!",
    "741604": "Thanks for the kernel ! very helpful",
    "745197": "You are welcome 😊",
    "761531": "Nice kernel.",
    "761532": "Thank you!!!",
    "762384": "beautiful!\nupvoted!👍",
    "762391": "beautiful!!\nupvoted!!",
    "762474": "great @frankmollard ! thanks for sharing"
  },
  "source": "meta"
}