{
  "id": 40265,
  "title": "Distribution of Test Dataset",
  "url": "/competitions/cdiscount-image-classification-challenge/discussion/40265",
  "author_name": "",
  "post_date": "2017-09-30T08:05:57.523117400Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>We know that each categories have different numbers of products. Could we know that the distribution of test dataset? Does each category in test dataset also have different numbers of products?</p>",
  "messages": [
    {
      "id": "225875",
      "postDate": "09/30/2017 08:05:57",
      "content": "<p>We know that each categories have different numbers of products. Could we know that the distribution of test dataset? Does each category in test dataset also have different numbers of products?</p>",
      "rawMarkdown": "We know that each categories have different numbers of products. Could we know that the distribution of test dataset? Does each category in test dataset also have different numbers of products?",
      "votes": null
    },
    {
      "id": "225945",
      "postDate": "09/30/2017 13:47:31",
      "content": "<p>It is reasonable to assume that the test set follows a similar distribution as the training set, otherwise it's not a very good training set.</p>",
      "rawMarkdown": "It is reasonable to assume that the test set follows a similar distribution as the training set, otherwise it's not a very good training set.",
      "votes": null
    },
    {
      "id": "226093",
      "postDate": "10/01/2017 01:31:05",
      "content": "<p>Especially since the sponsor probably wants a useful algorithm so no incentive to trick us </p>",
      "rawMarkdown": "Especially since the sponsor probably wants a useful algorithm so no incentive to trick us",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 225945,
      "author_name": "humananalog",
      "author_url": "",
      "post_date": "09/30/2017 13:47:31",
      "content": "<p>It is reasonable to assume that the test set follows a similar distribution as the training set, otherwise it's not a very good training set.</p>",
      "votes": null,
      "replies": [
        {
          "id": 226093,
          "author_name": "julienpantz",
          "author_url": "",
          "post_date": "10/01/2017 01:31:05",
          "content": "<p>Especially since the sponsor probably wants a useful algorithm so no incentive to trick us </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "225875": "We know that each categories have different numbers of products. Could we know that the distribution of test dataset? Does each category in test dataset also have different numbers of products?",
    "225945": "It is reasonable to assume that the test set follows a similar distribution as the training set, otherwise it's not a very good training set.",
    "226093": "Especially since the sponsor probably wants a useful algorithm so no incentive to trick us"
  },
  "source": "meta"
}