{
  "id": 395468,
  "title": "On StartHesitation label",
  "url": "/competitions/tlvmc-parkinsons-freezing-gait-prediction/discussion/395468",
  "author_name": "",
  "post_date": "2023-03-17T11:56:51.203995700Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I would like to ask for clarification concerning the \"StartHesitation\" label. I gave a glance at the demo data, 15-20 files, and I have not found any row with StartHesitation equal to 1 (the filter on the column headers had just the value 0, while the other two labels walking and turning have both the choices). The question: is StartHesitation kept at 1 for the whole period in which FOG is occurring or just once when the operator \"arbitrarily\" decided that the phenomenon began? In the latest case, how is the quality of the classification evaluated? Thank you.</p>",
  "messages": [
    {
      "id": "2185899",
      "postDate": "03/17/2023 11:56:51",
      "content": "<p>I would like to ask for clarification concerning the \"StartHesitation\" label. I gave a glance at the demo data, 15-20 files, and I have not found any row with StartHesitation equal to 1 (the filter on the column headers had just the value 0, while the other two labels walking and turning have both the choices). The question: is StartHesitation kept at 1 for the whole period in which FOG is occurring or just once when the operator \"arbitrarily\" decided that the phenomenon began? In the latest case, how is the quality of the classification evaluated? Thank you.</p>",
      "rawMarkdown": "I would like to ask for clarification concerning the \"StartHesitation\" label. I gave a glance at the demo data, 15-20 files, and I have not found any row with StartHesitation equal to 1 (the filter on the column headers had just the value 0, while the other two labels walking and turning have both the choices). The question: is StartHesitation kept at 1 for the whole period in which FOG is occurring or just once when the operator \"arbitrarily\" decided that the phenomenon began? In the latest case, how is the quality of the classification evaluated? Thank you.",
      "votes": null
    },
    {
      "id": "2185913",
      "postDate": "03/17/2023 12:05:19",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/federicobari\" target=\"_blank\">@federicobari</a> ,</p>\n<p>Some events might not be present in a given series. I do see that <code>0d7ab3a9f9</code> has StartHesitation type events though. The <code>1</code> annotation should be present during the whole duration of the event. You can find the original annotations with beginning and ending times in the <code>events.csv</code> file.</p>",
      "rawMarkdown": "Hi @federicobari ,\n\nSome events might not be present in a given series. I do see that `0d7ab3a9f9` has StartHesitation type events though. The `1` annotation should be present during the whole duration of the event. You can find the original annotations with beginning and ending times in the `events.csv` file.",
      "votes": null
    },
    {
      "id": "2185998",
      "postDate": "03/17/2023 13:38:35",
      "content": "<p>Thank you, I give a look at 0d7ab3a9f9  file; the \"Start\" in StartHesitation and the missing example worried me! ^_^</p>",
      "rawMarkdown": "Thank you, I give a look at 0d7ab3a9f9  file; the \"Start\" in StartHesitation and the missing example worried me! ^_^",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2185913,
      "author_name": "ryanholbrook",
      "author_url": "",
      "post_date": "03/17/2023 12:05:19",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/federicobari\" target=\"_blank\">@federicobari</a> ,</p>\n<p>Some events might not be present in a given series. I do see that <code>0d7ab3a9f9</code> has StartHesitation type events though. The <code>1</code> annotation should be present during the whole duration of the event. You can find the original annotations with beginning and ending times in the <code>events.csv</code> file.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2185998,
          "author_name": "federicobari",
          "author_url": "",
          "post_date": "03/17/2023 13:38:35",
          "content": "<p>Thank you, I give a look at 0d7ab3a9f9  file; the \"Start\" in StartHesitation and the missing example worried me! ^_^</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2185899": "I would like to ask for clarification concerning the \"StartHesitation\" label. I gave a glance at the demo data, 15-20 files, and I have not found any row with StartHesitation equal to 1 (the filter on the column headers had just the value 0, while the other two labels walking and turning have both the choices). The question: is StartHesitation kept at 1 for the whole period in which FOG is occurring or just once when the operator \"arbitrarily\" decided that the phenomenon began? In the latest case, how is the quality of the classification evaluated? Thank you.",
    "2185913": "Hi @federicobari ,\n\nSome events might not be present in a given series. I do see that `0d7ab3a9f9` has StartHesitation type events though. The `1` annotation should be present during the whole duration of the event. You can find the original annotations with beginning and ending times in the `events.csv` file.",
    "2185998": "Thank you, I give a look at 0d7ab3a9f9  file; the \"Start\" in StartHesitation and the missing example worried me! ^_^"
  },
  "source": "meta"
}