{
  "id": 285554,
  "title": "50 days gap + Neutralizing Features + DenseNet = my bronze medal at Jane Street competition",
  "url": "/competitions/g-research-crypto-forecasting/discussion/285554",
  "author_name": "",
  "post_date": "2021-11-05T07:17:11.592103400Z",
  "votes": 10,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi all :)</p>\n<p>I would like to share how I got a bronze medal at Jane Street competition which can be useful for this competition</p>\n<ul>\n<li>50 days gap</li>\n</ul>\n<pre><code>X_tr = train.query('date&lt;350')[features].values\ny_tr = (train.query('date&lt;350')[resp_cols].values &gt; 0).astype(int)\n\nX_val = train.query('date&gt;400')[features].values\ny_val = (train.query('date&gt;400')[resp_cols].values &gt; 0).astype(int)\n</code></pre>\n<ul>\n<li>Neutralizing Features </li>\n<li>DenseNet </li>\n</ul>\n<p>The code<br>\n<a href=\"https://www.kaggle.com/faisalalsrheed/jane-street-densenet-neutralizing-features\" target=\"_blank\">https://www.kaggle.com/faisalalsrheed/jane-street-densenet-neutralizing-features</a></p>\n<p>I have to say BIG  thank you to </p>\n<p><a href=\"https://www.kaggle.com/snippsy\" target=\"_blank\">@snippsy</a> <br>\n<a href=\"https://www.kaggle.com/code1110\" target=\"_blank\">@code1110</a></p>\n<p>and everyone share any ideas that helped to make this code.</p>\n<p>All the best </p>",
  "messages": [
    {
      "id": "1571814",
      "postDate": "11/05/2021 07:17:11",
      "content": "<p>Hi all :)</p>\n<p>I would like to share how I got a bronze medal at Jane Street competition which can be useful for this competition</p>\n<ul>\n<li>50 days gap</li>\n</ul>\n<pre><code>X_tr = train.query('date&lt;350')[features].values\ny_tr = (train.query('date&lt;350')[resp_cols].values &gt; 0).astype(int)\n\nX_val = train.query('date&gt;400')[features].values\ny_val = (train.query('date&gt;400')[resp_cols].values &gt; 0).astype(int)\n</code></pre>\n<ul>\n<li>Neutralizing Features </li>\n<li>DenseNet </li>\n</ul>\n<p>The code<br>\n<a href=\"https://www.kaggle.com/faisalalsrheed/jane-street-densenet-neutralizing-features\" target=\"_blank\">https://www.kaggle.com/faisalalsrheed/jane-street-densenet-neutralizing-features</a></p>\n<p>I have to say BIG  thank you to </p>\n<p><a href=\"https://www.kaggle.com/snippsy\" target=\"_blank\">@snippsy</a> <br>\n<a href=\"https://www.kaggle.com/code1110\" target=\"_blank\">@code1110</a></p>\n<p>and everyone share any ideas that helped to make this code.</p>\n<p>All the best </p>",
      "rawMarkdown": "Hi all :)\n\nI would like to share how I got a bronze medal at Jane Street competition which can be useful for this competition\n\n- 50 days gap\n\n```\nX_tr = train.query('date<350')[features].values\ny_tr = (train.query('date<350')[resp_cols].values > 0).astype(int)\n    \nX_val = train.query('date>400')[features].values\ny_val = (train.query('date>400')[resp_cols].values > 0).astype(int)\n```\n\n\n- Neutralizing Features \n- DenseNet \n\nThe code\nhttps://www.kaggle.com/faisalalsrheed/jane-street-densenet-neutralizing-features\n\nI have to say BIG  thank you to \n\n@snippsy \n@code1110\n\nand everyone share any ideas that helped to make this code.\n\nAll the best",
      "votes": null
    },
    {
      "id": "1576320",
      "postDate": "11/09/2021 04:57:36",
      "content": "<p>Hi. Congrats on your medal. And it is 51 days gap 😜</p>",
      "rawMarkdown": "Hi. Congrats on your medal. And it is 51 days gap 😜",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1576320,
      "author_name": "rajkumarl",
      "author_url": "",
      "post_date": "11/09/2021 04:57:36",
      "content": "<p>Hi. Congrats on your medal. And it is 51 days gap 😜</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1571814": "Hi all :)\n\nI would like to share how I got a bronze medal at Jane Street competition which can be useful for this competition\n\n- 50 days gap\n\n```\nX_tr = train.query('date<350')[features].values\ny_tr = (train.query('date<350')[resp_cols].values > 0).astype(int)\n    \nX_val = train.query('date>400')[features].values\ny_val = (train.query('date>400')[resp_cols].values > 0).astype(int)\n```\n\n\n- Neutralizing Features \n- DenseNet \n\nThe code\nhttps://www.kaggle.com/faisalalsrheed/jane-street-densenet-neutralizing-features\n\nI have to say BIG  thank you to \n\n@snippsy \n@code1110\n\nand everyone share any ideas that helped to make this code.\n\nAll the best",
    "1576320": "Hi. Congrats on your medal. And it is 51 days gap 😜"
  },
  "source": "meta"
}