{
  "id": 232200,
  "title": "Public Leaderboard Score for Individual Labels",
  "url": "/competitions/plant-pathology-2021-fgvc8/discussion/232200",
  "author_name": "",
  "post_date": "2021-04-12T16:04:26.929679100Z",
  "votes": 8,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I simply wanted to understand the distribution of labels in the available hidden dataset(which are used for public leaderboard score).  In my <code>submission.csv</code>, <code>labels</code> column only had a single class.</p>\n<p>Code snippet:</p>\n<pre><code>test_df = pd.read_csv(\"../input/plant-pathology-2021-fgvc8/sample_submission.csv\")\ntest_df[\"labels\"] = \"complex\" # replace with the desired label name\ntest_df.to_csv(\"submission.csv\", index=False)\n</code></pre>\n<p>So, here is the result - </p>\n<table>\n<thead>\n<tr>\n<th>Label</th>\n<th>Public Leaderboard Score</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>healthy</td>\n<td>0.251</td>\n</tr>\n<tr>\n<td>scab</td>\n<td>0.292</td>\n</tr>\n<tr>\n<td>frog_eye_leaf_spot</td>\n<td>0.211</td>\n</tr>\n<tr>\n<td>rust</td>\n<td>0.103</td>\n</tr>\n<tr>\n<td>complex</td>\n<td>0.103</td>\n</tr>\n<tr>\n<td>powdery_mildew</td>\n<td>0.063</td>\n</tr>\n</tbody>\n</table>\n<p></p>",
  "messages": [
    {
      "id": "1271451",
      "postDate": "04/12/2021 16:04:26",
      "content": "<p>I simply wanted to understand the distribution of labels in the available hidden dataset(which are used for public leaderboard score).  In my <code>submission.csv</code>, <code>labels</code> column only had a single class.</p>\n<p>Code snippet:</p>\n<pre><code>test_df = pd.read_csv(\"../input/plant-pathology-2021-fgvc8/sample_submission.csv\")\ntest_df[\"labels\"] = \"complex\" # replace with the desired label name\ntest_df.to_csv(\"submission.csv\", index=False)\n</code></pre>\n<p>So, here is the result - </p>\n<table>\n<thead>\n<tr>\n<th>Label</th>\n<th>Public Leaderboard Score</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>healthy</td>\n<td>0.251</td>\n</tr>\n<tr>\n<td>scab</td>\n<td>0.292</td>\n</tr>\n<tr>\n<td>frog_eye_leaf_spot</td>\n<td>0.211</td>\n</tr>\n<tr>\n<td>rust</td>\n<td>0.103</td>\n</tr>\n<tr>\n<td>complex</td>\n<td>0.103</td>\n</tr>\n<tr>\n<td>powdery_mildew</td>\n<td>0.063</td>\n</tr>\n</tbody>\n</table>\n<p></p>",
      "rawMarkdown": "I simply wanted to understand the distribution of labels in the available hidden dataset(which are used for public leaderboard score).  In my `submission.csv`, `labels` column only had a single class.\n\nCode snippet:\n```\ntest_df = pd.read_csv(\"../input/plant-pathology-2021-fgvc8/sample_submission.csv\")\ntest_df[\"labels\"] = \"complex\" # replace with the desired label name\ntest_df.to_csv(\"submission.csv\", index=False)\n```\n\nSo, here is the result - \n\n\n| Label | Public Leaderboard Score |\n| --- | --- |\n| healthy | 0.251 |\n| scab | 0.292 |\n| frog_eye_leaf_spot | 0.211 |\n| rust | 0.103 |\n| complex | 0.103 |\n| powdery_mildew | 0.063 |\n\n~~There are total of 6 labels. I could manage to get the result of 5, due to the submission limitation in one day.~~",
      "votes": null
    },
    {
      "id": "1282591",
      "postDate": "04/24/2021 05:27:41",
      "content": "<p>Wow that actually helped me thank you i have not submitted yet but i hope good results the distribution here is different from that of train.csv</p>",
      "rawMarkdown": "Wow that actually helped me thank you i have not submitted yet but i hope good results the distribution here is different from that of train.csv",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1282591,
      "author_name": "swaralipibose",
      "author_url": "",
      "post_date": "04/24/2021 05:27:41",
      "content": "<p>Wow that actually helped me thank you i have not submitted yet but i hope good results the distribution here is different from that of train.csv</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1271451": "I simply wanted to understand the distribution of labels in the available hidden dataset(which are used for public leaderboard score).  In my `submission.csv`, `labels` column only had a single class.\n\nCode snippet:\n```\ntest_df = pd.read_csv(\"../input/plant-pathology-2021-fgvc8/sample_submission.csv\")\ntest_df[\"labels\"] = \"complex\" # replace with the desired label name\ntest_df.to_csv(\"submission.csv\", index=False)\n```\n\nSo, here is the result - \n\n\n| Label | Public Leaderboard Score |\n| --- | --- |\n| healthy | 0.251 |\n| scab | 0.292 |\n| frog_eye_leaf_spot | 0.211 |\n| rust | 0.103 |\n| complex | 0.103 |\n| powdery_mildew | 0.063 |\n\n~~There are total of 6 labels. I could manage to get the result of 5, due to the submission limitation in one day.~~",
    "1282591": "Wow that actually helped me thank you i have not submitted yet but i hope good results the distribution here is different from that of train.csv"
  },
  "source": "meta"
}