{
  "id": 173706,
  "title": "What is the value in case on Nan in TFRec datasets",
  "url": "/competitions/siim-isic-melanoma-classification/discussion/173706",
  "author_name": "",
  "post_date": "2020-08-10T11:09:19.076069500Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> , first of all thanks a ton for sharing tfrecord datasets. In these datasets, what is the value in case meta data info for some attribute is missing? I am not sure what is the recommended way of handling Nan in TFRecords.</p>",
  "messages": [
    {
      "id": "965064",
      "postDate": "08/10/2020 11:09:19",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> , first of all thanks a ton for sharing tfrecord datasets. In these datasets, what is the value in case meta data info for some attribute is missing? I am not sure what is the recommended way of handling Nan in TFRecords.</p>",
      "rawMarkdown": "Hi @cdeotte , first of all thanks a ton for sharing tfrecord datasets. In these datasets, what is the value in case meta data info for some attribute is missing? I am not sure what is the recommended way of handling Nan in TFRecords.",
      "votes": null
    },
    {
      "id": "965851",
      "postDate": "08/10/2020 22:52:21",
      "content": "<p>Depends. You need see how many cases do you have in your dataset.</p>\n\n<p>You can use the average of the column or delete if is a simple line for example, depends on your analysis</p>",
      "rawMarkdown": "Depends. You need see how many cases do you have in your dataset.\n\nYou can use the average of the column or delete if is a simple line for example, depends on your analysis",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 965851,
      "author_name": "vnidias",
      "author_url": "",
      "post_date": "08/10/2020 22:52:21",
      "content": "<p>Depends. You need see how many cases do you have in your dataset.</p>\n\n<p>You can use the average of the column or delete if is a simple line for example, depends on your analysis</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "965064": "Hi @cdeotte , first of all thanks a ton for sharing tfrecord datasets. In these datasets, what is the value in case meta data info for some attribute is missing? I am not sure what is the recommended way of handling Nan in TFRecords.",
    "965851": "Depends. You need see how many cases do you have in your dataset.\n\nYou can use the average of the column or delete if is a simple line for example, depends on your analysis"
  },
  "source": "meta"
}