{
  "id": 180445,
  "title": "Nocall model : LB 0.427",
  "url": "/competitions/birdsong-recognition/discussion/180445",
  "author_name": "",
  "post_date": "2020-09-05T05:00:29.871511100Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I trained binary classification call/nocall it gives CV : 0.97+ AUC</p>\n<p>Here is the update for nocall model</p>\n<p><code>\"nocall\" if pred_proba &gt; 0.5 else \"none\" -&gt; LB : 0.427</code></p>\n<p>only with nocall LB max is 0.55 my model predicts LB: 0.427 with a simple threshold 0.5</p>\n<p>This is discussions thread : <a href=\"https://www.kaggle.com/c/birdsong-recognition/discussion/180028#997031\" target=\"_blank\">https://www.kaggle.com/c/birdsong-recognition/discussion/180028#997031</a></p>",
  "messages": [
    {
      "id": "998799",
      "postDate": "09/05/2020 05:00:29",
      "content": "<p>I trained binary classification call/nocall it gives CV : 0.97+ AUC</p>\n<p>Here is the update for nocall model</p>\n<p><code>\"nocall\" if pred_proba &gt; 0.5 else \"none\" -&gt; LB : 0.427</code></p>\n<p>only with nocall LB max is 0.55 my model predicts LB: 0.427 with a simple threshold 0.5</p>\n<p>This is discussions thread : <a href=\"https://www.kaggle.com/c/birdsong-recognition/discussion/180028#997031\" target=\"_blank\">https://www.kaggle.com/c/birdsong-recognition/discussion/180028#997031</a></p>",
      "rawMarkdown": "I trained binary classification call/nocall it gives CV : 0.97+ AUC\n\nHere is the update for nocall model\n\n`\"nocall\" if pred_proba > 0.5 else \"none\" -> LB : 0.427`\n\nonly with nocall LB max is 0.55 my model predicts LB: 0.427 with a simple threshold 0.5\n\nThis is discussions thread : https://www.kaggle.com/c/birdsong-recognition/discussion/180028#997031",
      "votes": null
    },
    {
      "id": "998957",
      "postDate": "09/05/2020 08:26:47",
      "content": "<p>thanks for your sharing. May I know how can we make use of this info?</p>",
      "rawMarkdown": "thanks for your sharing. May I know how can we make use of this info?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 998957,
      "author_name": "fiyeroleung",
      "author_url": "",
      "post_date": "09/05/2020 08:26:47",
      "content": "<p>thanks for your sharing. May I know how can we make use of this info?</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "998799": "I trained binary classification call/nocall it gives CV : 0.97+ AUC\n\nHere is the update for nocall model\n\n`\"nocall\" if pred_proba > 0.5 else \"none\" -> LB : 0.427`\n\nonly with nocall LB max is 0.55 my model predicts LB: 0.427 with a simple threshold 0.5\n\nThis is discussions thread : https://www.kaggle.com/c/birdsong-recognition/discussion/180028#997031",
    "998957": "thanks for your sharing. May I know how can we make use of this info?"
  },
  "source": "meta"
}