{
  "id": 81615,
  "title": "TIME_TO_FAILURE IS NOT 0!!!!!",
  "url": "/competitions/LANL-Earthquake-Prediction/discussion/81615",
  "author_name": "",
  "post_date": "2019-02-23T11:11:49.718498900Z",
  "votes": -7,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I'm getting crazy because when i test my model  i use the time_to_failure values those are 0, to validate my model. And I think that the values are not zero, are just other values that they don't want to tell us. Somebody could tell me if my hypothesis is right?</p>\n\n<p>Thank You</p>",
  "messages": [
    {
      "id": "476874",
      "postDate": "02/23/2019 11:11:49",
      "content": "<p>I'm getting crazy because when i test my model  i use the time_to_failure values those are 0, to validate my model. And I think that the values are not zero, are just other values that they don't want to tell us. Somebody could tell me if my hypothesis is right?</p>\n\n<p>Thank You</p>",
      "rawMarkdown": "I'm getting crazy because when i test my model  i use the time_to_failure values those are 0, to validate my model. And I think that the values are not zero, are just other values that they don't want to tell us. Somebody could tell me if my hypothesis is right?\n\nThank You",
      "votes": null
    },
    {
      "id": "476936",
      "postDate": "02/23/2019 13:35:49",
      "content": "<p>The time to failure on the test data is unknown for us, you can't use it to refine your model.  You have to replace the 0s by your estimated time to failure and submit it to Kaggle.  Kaggle knows the actual time to failure of the test data and will compute your score based on your submission.</p>",
      "rawMarkdown": "The time to failure on the test data is unknown for us, you can't use it to refine your model.  You have to replace the 0s by your estimated time to failure and submit it to Kaggle.  Kaggle knows the actual time to failure of the test data and will compute your score based on your submission.",
      "votes": null
    },
    {
      "id": "477574",
      "postDate": "02/24/2019 21:59:02",
      "content": "<p>Time to failure in the training set also is never exactly 0, \nthe lowest points are in between 0.0010 and 0.0006 , but never exactly 0.</p>\n\n<p>If that is your question?</p>",
      "rawMarkdown": "Time to failure in the training set also is never exactly 0, \nthe lowest points are in between 0.0010 and 0.0006 , but never exactly 0.\n\nIf that is your question?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 476936,
      "author_name": "gguillard",
      "author_url": "",
      "post_date": "02/23/2019 13:35:49",
      "content": "<p>The time to failure on the test data is unknown for us, you can't use it to refine your model.  You have to replace the 0s by your estimated time to failure and submit it to Kaggle.  Kaggle knows the actual time to failure of the test data and will compute your score based on your submission.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 477574,
      "author_name": "theupgrade",
      "author_url": "",
      "post_date": "02/24/2019 21:59:02",
      "content": "<p>Time to failure in the training set also is never exactly 0, \nthe lowest points are in between 0.0010 and 0.0006 , but never exactly 0.</p>\n\n<p>If that is your question?</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "476874": "I'm getting crazy because when i test my model  i use the time_to_failure values those are 0, to validate my model. And I think that the values are not zero, are just other values that they don't want to tell us. Somebody could tell me if my hypothesis is right?\n\nThank You",
    "476936": "The time to failure on the test data is unknown for us, you can't use it to refine your model.  You have to replace the 0s by your estimated time to failure and submit it to Kaggle.  Kaggle knows the actual time to failure of the test data and will compute your score based on your submission.",
    "477574": "Time to failure in the training set also is never exactly 0, \nthe lowest points are in between 0.0010 and 0.0006 , but never exactly 0.\n\nIf that is your question?"
  },
  "source": "meta"
}