{
  "id": 286493,
  "title": "Meaning of supplemental_train ?",
  "url": "/competitions/g-research-crypto-forecasting/discussion/286493",
  "author_name": "",
  "post_date": "2021-11-09T12:18:38.511770Z",
  "votes": 11,
  "comment_count": 1,
  "views": 0,
  "content": "<p>The description in the \"Data\" section:</p>\n<blockquote>\n  <p>After the submission period is over this file's data will be replaced with cryptoasset prices from the submission period. In the Evaluation phase, the train, train supplement, and test set will be contiguous in time, apart from any missing data. The current copy, which is just filled approximately the right amount of data from train.csv is provided as a placeholder.</p>\n</blockquote>\n<p>Does this mean that we should replace train.csv with supplemental_train.csv before submitting, and re-train in the submission notebook? 🤔</p>",
  "messages": [
    {
      "id": "1576726",
      "postDate": "11/09/2021 12:18:38",
      "content": "<p>The description in the \"Data\" section:</p>\n<blockquote>\n  <p>After the submission period is over this file's data will be replaced with cryptoasset prices from the submission period. In the Evaluation phase, the train, train supplement, and test set will be contiguous in time, apart from any missing data. The current copy, which is just filled approximately the right amount of data from train.csv is provided as a placeholder.</p>\n</blockquote>\n<p>Does this mean that we should replace train.csv with supplemental_train.csv before submitting, and re-train in the submission notebook? 🤔</p>",
      "rawMarkdown": "The description in the \"Data\" section:\n>  After the submission period is over this file's data will be replaced with cryptoasset prices from the submission period. In the Evaluation phase, the train, train supplement, and test set will be contiguous in time, apart from any missing data. The current copy, which is just filled approximately the right amount of data from train.csv is provided as a placeholder.\n\nDoes this mean that we should replace train.csv with supplemental_train.csv before submitting, and re-train in the submission notebook? 🤔",
      "votes": null
    },
    {
      "id": "1615107",
      "postDate": "12/11/2021 20:31:39",
      "content": "<p>I think, the <code>train.csv</code> will stay untouched and the <code>supplemental_train.csv</code> will be changing every 2 weeks. It will contain the data from the 2 Feb 2022 and up to the 3 Mar 2022. Then how much data there will be in the iterations? </p>\n<pre><code>env = gresearch_crypto.make_env()\niter_test = env.iter_test()\nfor df_test, df_pred in iter_test:\n   ...\n</code></pre>\n<p>Every iteration will have the 1 min data? How many iterations? From… and up to…?</p>",
      "rawMarkdown": "I think, the `train.csv` will stay untouched and the `supplemental_train.csv` will be changing every 2 weeks. It will contain the data from the 2 Feb 2022 and up to the 3 Mar 2022. Then how much data there will be in the iterations? \n```\nenv = gresearch_crypto.make_env()\niter_test = env.iter_test()\nfor df_test, df_pred in iter_test:\n   ...\n```\n\nEvery iteration will have the 1 min data? How many iterations? From... and up to...?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1615107,
      "author_name": "markbquant",
      "author_url": "",
      "post_date": "12/11/2021 20:31:39",
      "content": "<p>I think, the <code>train.csv</code> will stay untouched and the <code>supplemental_train.csv</code> will be changing every 2 weeks. It will contain the data from the 2 Feb 2022 and up to the 3 Mar 2022. Then how much data there will be in the iterations? </p>\n<pre><code>env = gresearch_crypto.make_env()\niter_test = env.iter_test()\nfor df_test, df_pred in iter_test:\n   ...\n</code></pre>\n<p>Every iteration will have the 1 min data? How many iterations? From… and up to…?</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1576726": "The description in the \"Data\" section:\n>  After the submission period is over this file's data will be replaced with cryptoasset prices from the submission period. In the Evaluation phase, the train, train supplement, and test set will be contiguous in time, apart from any missing data. The current copy, which is just filled approximately the right amount of data from train.csv is provided as a placeholder.\n\nDoes this mean that we should replace train.csv with supplemental_train.csv before submitting, and re-train in the submission notebook? 🤔",
    "1615107": "I think, the `train.csv` will stay untouched and the `supplemental_train.csv` will be changing every 2 weeks. It will contain the data from the 2 Feb 2022 and up to the 3 Mar 2022. Then how much data there will be in the iterations? \n```\nenv = gresearch_crypto.make_env()\niter_test = env.iter_test()\nfor df_test, df_pred in iter_test:\n   ...\n```\n\nEvery iteration will have the 1 min data? How many iterations? From... and up to...?"
  },
  "source": "meta"
}