{
  "id": 75791,
  "title": "Not consistent target within same id_measurement (is it ok?)",
  "url": "/competitions/vsb-power-line-fault-detection/discussion/75791",
  "author_name": "",
  "post_date": "2018-12-26T15:50:24.012455100Z",
  "votes": 4,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Hi there,</p>\n\n<p>Is it ok that the same measurement have different target labels between signals?\nAccording to data description it should be the same (or not really?) . There are 38 cases of measurements with not consistent labels between signals.</p>\n\n<p>Quick and dirty code to show the problem here:\n<a href=\"https://www.kaggle.com/konradcieslik/target-not-consistent-between-signals/notebook\">https://www.kaggle.com/konradcieslik/target-not-consistent-between-signals/notebook</a></p>",
  "messages": [
    {
      "id": "445511",
      "postDate": "12/26/2018 15:50:24",
      "content": "<p>Hi there,</p>\n\n<p>Is it ok that the same measurement have different target labels between signals?\nAccording to data description it should be the same (or not really?) . There are 38 cases of measurements with not consistent labels between signals.</p>\n\n<p>Quick and dirty code to show the problem here:\n<a href=\"https://www.kaggle.com/konradcieslik/target-not-consistent-between-signals/notebook\">https://www.kaggle.com/konradcieslik/target-not-consistent-between-signals/notebook</a></p>",
      "rawMarkdown": "Hi there,\n\nIs it ok that the same measurement have different target labels between signals?\nAccording to data description it should be the same (or not really?) . There are 38 cases of measurements with not consistent labels between signals.\n\nQuick and dirty code to show the problem here:\nhttps://www.kaggle.com/konradcieslik/target-not-consistent-between-signals/notebook",
      "votes": null
    },
    {
      "id": "445529",
      "postDate": "12/26/2018 16:49:10",
      "content": "<p>This is expected, yes. A fault in the line won't necessarily impact all 3 phases.</p>",
      "rawMarkdown": "This is expected, yes. A fault in the line won't necessarily impact all 3 phases.",
      "votes": null
    },
    {
      "id": "445543",
      "postDate": "12/26/2018 17:22:51",
      "content": "<p>Thank you!</p>",
      "rawMarkdown": "Thank you!",
      "votes": null
    },
    {
      "id": "446644",
      "postDate": "12/28/2018 12:28:48",
      "content": "<p>But we submit a prediction for the line, not a phase, so a fault in a any single phase should produse a \"1\" in the submit file, isn't it?</p>",
      "rawMarkdown": "But we submit a prediction for the line, not a phase, so a fault in a any single phase should produse a \"1\" in the submit file, isn't it?",
      "votes": null
    },
    {
      "id": "446874",
      "postDate": "12/28/2018 20:12:13",
      "content": "<p>The submitted predictions have one phase in each row of the csv file. So a fault in phase 0 should produce a 1 in row #0, but there may not be a fault in phase 1, so there should be a 0 in row #1.</p>",
      "rawMarkdown": "The submitted predictions have one phase in each row of the csv file. So a fault in phase 0 should produce a 1 in row #0, but there may not be a fault in phase 1, so there should be a 0 in row #1.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 445529,
      "author_name": "sohier",
      "author_url": "",
      "post_date": "12/26/2018 16:49:10",
      "content": "<p>This is expected, yes. A fault in the line won't necessarily impact all 3 phases.</p>",
      "votes": null,
      "replies": [
        {
          "id": 445543,
          "author_name": "konradcieslik",
          "author_url": "",
          "post_date": "12/26/2018 17:22:51",
          "content": "<p>Thank you!</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 446644,
          "author_name": "langmuir",
          "author_url": "",
          "post_date": "12/28/2018 12:28:48",
          "content": "<p>But we submit a prediction for the line, not a phase, so a fault in a any single phase should produse a \"1\" in the submit file, isn't it?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 446874,
          "author_name": "jfr311",
          "author_url": "",
          "post_date": "12/28/2018 20:12:13",
          "content": "<p>The submitted predictions have one phase in each row of the csv file. So a fault in phase 0 should produce a 1 in row #0, but there may not be a fault in phase 1, so there should be a 0 in row #1.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "445511": "Hi there,\n\nIs it ok that the same measurement have different target labels between signals?\nAccording to data description it should be the same (or not really?) . There are 38 cases of measurements with not consistent labels between signals.\n\nQuick and dirty code to show the problem here:\nhttps://www.kaggle.com/konradcieslik/target-not-consistent-between-signals/notebook",
    "445529": "This is expected, yes. A fault in the line won't necessarily impact all 3 phases.",
    "445543": "Thank you!",
    "446644": "But we submit a prediction for the line, not a phase, so a fault in a any single phase should produse a \"1\" in the submit file, isn't it?",
    "446874": "The submitted predictions have one phase in each row of the csv file. So a fault in phase 0 should produce a 1 in row #0, but there may not be a fault in phase 1, so there should be a 0 in row #1."
  },
  "source": "meta"
}