{
  "id": 67462,
  "title": "Mismatch in distinct classes to classify (train and test",
  "url": "/competitions/PLAsTiCC-2018/discussion/67462",
  "author_name": "",
  "post_date": "2018-10-03T01:35:36.215379800Z",
  "votes": 1,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Hi all, \nI explored the number of distinct classes in the target variable for train_set_metadata. There are altogether 14 classes.</p>\n\n<p>However, the sample_submission file shows 1 extra i.e. 'class_99'.\nHas anyone experienced a similar problem?</p>\n\n<p>Thanks,\nJojo</p>",
  "messages": [
    {
      "id": "397713",
      "postDate": "10/03/2018 01:35:36",
      "content": "<p>Hi all, \nI explored the number of distinct classes in the target variable for train_set_metadata. There are altogether 14 classes.</p>\n\n<p>However, the sample_submission file shows 1 extra i.e. 'class_99'.\nHas anyone experienced a similar problem?</p>\n\n<p>Thanks,\nJojo</p>",
      "rawMarkdown": "Hi all, \nI explored the number of distinct classes in the target variable for train_set_metadata. There are altogether 14 classes.\n\nHowever, the sample_submission file shows 1 extra i.e. 'class_99'.\nHas anyone experienced a similar problem?\n\nThanks,\nJojo",
      "votes": null
    },
    {
      "id": "397725",
      "postDate": "10/03/2018 02:14:35",
      "content": "<p>The <a href=\"https://www.kaggle.com/c/PLAsTiCC-2018/data\">data description</a> for the competition discusses class 99:</p>\n\n<blockquote>\n  <p>target: The class of the astronomical source. This is provided in the training data. Correctly determining the target (correctly assigning classification probabilities to the objects) is the ‘goal’ of the classification challenge for the test data. Note that there is one class in the test set that does not occur in the training set: class_99 serves as an \"other\" class for objects that don't belong in any of the 14 classes in the training set.</p>\n</blockquote>",
      "rawMarkdown": "The [data description][1] for the competition discusses class 99:\n\n&gt; target: The class of the astronomical source. This is provided in the training data. Correctly determining the target (correctly assigning classification probabilities to the objects) is the ‘goal’ of the classification challenge for the test data. Note that there is one class in the test set that does not occur in the training set: class_99 serves as an \"other\" class for objects that don't belong in any of the 14 classes in the training set.\n\n\n  [1]: https://www.kaggle.com/c/PLAsTiCC-2018/data",
      "votes": null
    },
    {
      "id": "397739",
      "postDate": "10/03/2018 02:57:02",
      "content": "<p>Thanks for pointing this out!</p>",
      "rawMarkdown": "Thanks for pointing this out!",
      "votes": null
    },
    {
      "id": "398001",
      "postDate": "10/03/2018 12:21:07",
      "content": "<p>also make sure to check out <a href=\"https://arxiv.org/abs/1810.00001\">https://arxiv.org/abs/1810.00001</a> for more info!</p>",
      "rawMarkdown": "also make sure to check out https://arxiv.org/abs/1810.00001 for more info!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 397725,
      "author_name": "nnnnick",
      "author_url": "",
      "post_date": "10/03/2018 02:14:35",
      "content": "<p>The <a href=\"https://www.kaggle.com/c/PLAsTiCC-2018/data\">data description</a> for the competition discusses class 99:</p>\n\n<blockquote>\n  <p>target: The class of the astronomical source. This is provided in the training data. Correctly determining the target (correctly assigning classification probabilities to the objects) is the ‘goal’ of the classification challenge for the test data. Note that there is one class in the test set that does not occur in the training set: class_99 serves as an \"other\" class for objects that don't belong in any of the 14 classes in the training set.</p>\n</blockquote>",
      "votes": null,
      "replies": []
    },
    {
      "id": 397739,
      "author_name": "jojomoolayil",
      "author_url": "",
      "post_date": "10/03/2018 02:57:02",
      "content": "<p>Thanks for pointing this out!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 398001,
      "author_name": "reneehlozek",
      "author_url": "",
      "post_date": "10/03/2018 12:21:07",
      "content": "<p>also make sure to check out <a href=\"https://arxiv.org/abs/1810.00001\">https://arxiv.org/abs/1810.00001</a> for more info!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "397713": "Hi all, \nI explored the number of distinct classes in the target variable for train_set_metadata. There are altogether 14 classes.\n\nHowever, the sample_submission file shows 1 extra i.e. 'class_99'.\nHas anyone experienced a similar problem?\n\nThanks,\nJojo",
    "397725": "The [data description][1] for the competition discusses class 99:\n\n&gt; target: The class of the astronomical source. This is provided in the training data. Correctly determining the target (correctly assigning classification probabilities to the objects) is the ‘goal’ of the classification challenge for the test data. Note that there is one class in the test set that does not occur in the training set: class_99 serves as an \"other\" class for objects that don't belong in any of the 14 classes in the training set.\n\n\n  [1]: https://www.kaggle.com/c/PLAsTiCC-2018/data",
    "397739": "Thanks for pointing this out!",
    "398001": "also make sure to check out https://arxiv.org/abs/1810.00001 for more info!"
  },
  "source": "meta"
}