{
  "id": 79435,
  "title": "Is there difference between StratifiedKFold and uniform the sample?",
  "url": "/competitions/elo-merchant-category-recommendation/discussion/79435",
  "author_name": "",
  "post_date": "2019-02-04T01:18:31.121344600Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>hello everyone!\ni see some of you mentioned uniform distribution of train data in discussion. (reference: <a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/78903\">check this comments of post</a> It seems they do this to balance data. I am wondering what's the difference between this method and StratifiedKFold? Can anyone tell me please?</p>",
  "messages": [
    {
      "id": "465771",
      "postDate": "02/04/2019 01:18:31",
      "content": "<p>hello everyone!\ni see some of you mentioned uniform distribution of train data in discussion. (reference: <a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/78903\">check this comments of post</a> It seems they do this to balance data. I am wondering what's the difference between this method and StratifiedKFold? Can anyone tell me please?</p>",
      "rawMarkdown": "hello everyone!\ni see some of you mentioned uniform distribution of train data in discussion. (reference: [check this comments of post][1] It seems they do this to balance data. I am wondering what's the difference between this method and StratifiedKFold? Can anyone tell me please?\n\n\n  [1]: https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/78903",
      "votes": null
    },
    {
      "id": "465960",
      "postDate": "02/04/2019 12:12:14",
      "content": "<p>Hello)</p>\n\n<p>The presence of certain outlayers in the fold affects the accuracy of the model, but it is also important to have an equal number of outlayers in each fold. You can play with randomized permutations of outliers - I am sure you can find good seed. Good Luck!</p>",
      "rawMarkdown": "Hello)\n\nThe presence of certain outlayers in the fold affects the accuracy of the model, but it is also important to have an equal number of outlayers in each fold. You can play with randomized permutations of outliers - I am sure you can find good seed. Good Luck!",
      "votes": null
    },
    {
      "id": "466200",
      "postDate": "02/04/2019 21:03:49",
      "content": "<p>Hello Aleksandr, thank you for answer my question. Does sklearn.StratifiedKFold do the job you said? \"but it is also important to have an equal number of outlayers in each fold. \"</p>",
      "rawMarkdown": "Hello Aleksandr, thank you for answer my question. Does sklearn.StratifiedKFold do the job you said? \"but it is also important to have an equal number of outlayers in each fold. \"",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 465960,
      "author_name": "jingobox",
      "author_url": "",
      "post_date": "02/04/2019 12:12:14",
      "content": "<p>Hello)</p>\n\n<p>The presence of certain outlayers in the fold affects the accuracy of the model, but it is also important to have an equal number of outlayers in each fold. You can play with randomized permutations of outliers - I am sure you can find good seed. Good Luck!</p>",
      "votes": null,
      "replies": [
        {
          "id": 466200,
          "author_name": "worldkeeping",
          "author_url": "",
          "post_date": "02/04/2019 21:03:49",
          "content": "<p>Hello Aleksandr, thank you for answer my question. Does sklearn.StratifiedKFold do the job you said? \"but it is also important to have an equal number of outlayers in each fold. \"</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "465771": "hello everyone!\ni see some of you mentioned uniform distribution of train data in discussion. (reference: [check this comments of post][1] It seems they do this to balance data. I am wondering what's the difference between this method and StratifiedKFold? Can anyone tell me please?\n\n\n  [1]: https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/78903",
    "465960": "Hello)\n\nThe presence of certain outlayers in the fold affects the accuracy of the model, but it is also important to have an equal number of outlayers in each fold. You can play with randomized permutations of outliers - I am sure you can find good seed. Good Luck!",
    "466200": "Hello Aleksandr, thank you for answer my question. Does sklearn.StratifiedKFold do the job you said? \"but it is also important to have an equal number of outlayers in each fold. \""
  },
  "source": "meta"
}