{
  "id": 301049,
  "title": "Errors in supplemental_train csv update.",
  "url": "/competitions/g-research-crypto-forecasting/discussion/301049",
  "author_name": "Tom Forbes",
  "post_date": "2022-01-15T15:33:43.806000",
  "votes": 13,
  "comment_count": 4,
  "views": 0,
  "content": "<p>After testing my models on the updated supplemental_train.csv and getting poor results, i noticed probable data errors in the updated csv.</p>\n<p><a href=\"https://www.kaggle.com/tomforbes/errors-in-supplemental-train-csv\" target=\"_blank\">Please see my notebook for an explanation.</a></p>\n<p>Can the hosts comment on these errors?</p>\n<p><a href=\"https://www.kaggle.com/sohier\" target=\"_blank\">@sohier</a> <br>\n<a href=\"https://www.kaggle.com/andrewscherer\" target=\"_blank\">@andrewscherer</a> <br>\n<a href=\"https://www.kaggle.com/kierangarvey\" target=\"_blank\">@kierangarvey</a> </p>",
  "messages": [
    {
      "id": 1651162,
      "postDate": "2022-01-15T15:33:43.807Z",
      "content": "<p>After testing my models on the updated supplemental_train.csv and getting poor results, i noticed probable data errors in the updated csv.</p>\n<p><a href=\"https://www.kaggle.com/tomforbes/errors-in-supplemental-train-csv\" target=\"_blank\">Please see my notebook for an explanation.</a></p>\n<p>Can the hosts comment on these errors?</p>\n<p><a href=\"https://www.kaggle.com/sohier\" target=\"_blank\">@sohier</a> <br>\n<a href=\"https://www.kaggle.com/andrewscherer\" target=\"_blank\">@andrewscherer</a> <br>\n<a href=\"https://www.kaggle.com/kierangarvey\" target=\"_blank\">@kierangarvey</a> </p>",
      "rawMarkdown": "After testing my models on the updated supplemental_train.csv and getting poor results, i noticed probable data errors in the updated csv.\n\n[Please see my notebook for an explanation.](https://www.kaggle.com/tomforbes/errors-in-supplemental-train-csv)\n\nCan the hosts comment on these errors?\n\n@sohier \n@andrewscherer \n@kierangarvey ",
      "votes": 13
    },
    {
      "id": 1654845,
      "postDate": "2022-01-18T21:35:14.593Z",
      "content": "<p>Good catch <a href=\"https://www.kaggle.com/tomforbes\" target=\"_blank\">@tomforbes</a>. We are looking into the source of the outliers and how we will deal with them.</p>",
      "rawMarkdown": "Good catch @tomforbes. We are looking into the source of the outliers and how we will deal with them.",
      "votes": 3
    },
    {
      "id": 1651178,
      "postDate": "2022-01-15T15:50:53.040Z",
      "content": "<p>Will the online supplemental_train.csv 's timestamp be located right before the timestamp of test data?</p>",
      "rawMarkdown": "Will the online supplemental_train.csv 's timestamp be located right before the timestamp of test data?",
      "votes": 1
    },
    {
      "id": 1651210,
      "postDate": "2022-01-15T16:06:43.210Z",
      "content": "<p>Yeah, I noticed the same thing.  I was getting -0.10866 as the correlation for TRON.  And, the std for some of my features in the test set were over 20 when I was using standard scaling.</p>",
      "rawMarkdown": "Yeah, I noticed the same thing.  I was getting -0.10866 as the correlation for TRON.  And, the std for some of my features in the test set were over 20 when I was using standard scaling.",
      "votes": 2
    },
    {
      "id": 1651190,
      "postDate": "2022-01-15T15:57:50.803Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 1654845,
      "author_name": "Carlos Stein N Brito",
      "author_url": "",
      "post_date": "2022-01-18T21:35:14.593000",
      "content": "<p>Good catch <a href=\"https://www.kaggle.com/tomforbes\" target=\"_blank\">@tomforbes</a>. We are looking into the source of the outliers and how we will deal with them.</p>",
      "votes": 3,
      "replies": []
    },
    {
      "id": 1651178,
      "author_name": "yuanzhe zhou",
      "author_url": "",
      "post_date": "2022-01-15T15:50:53.040000",
      "content": "<p>Will the online supplemental_train.csv 's timestamp be located right before the timestamp of test data?</p>",
      "votes": 1,
      "replies": []
    },
    {
      "id": 1651210,
      "author_name": "Kyle Peters",
      "author_url": "",
      "post_date": "2022-01-15T16:06:43.210000",
      "content": "<p>Yeah, I noticed the same thing.  I was getting -0.10866 as the correlation for TRON.  And, the std for some of my features in the test set were over 20 when I was using standard scaling.</p>",
      "votes": 2,
      "replies": []
    },
    {
      "id": 1651190,
      "author_name": "",
      "author_url": "",
      "post_date": "2022-01-15T15:57:50.803000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1651162": "After testing my models on the updated supplemental_train.csv and getting poor results, i noticed probable data errors in the updated csv.\n\n[Please see my notebook for an explanation.](https://www.kaggle.com/tomforbes/errors-in-supplemental-train-csv)\n\nCan the hosts comment on these errors?\n\n@sohier \n@andrewscherer \n@kierangarvey ",
    "1654845": "Good catch @tomforbes. We are looking into the source of the outliers and how we will deal with them.",
    "1651178": "Will the online supplemental_train.csv 's timestamp be located right before the timestamp of test data?",
    "1651210": "Yeah, I noticed the same thing.  I was getting -0.10866 as the correlation for TRON.  And, the std for some of my features in the test set were over 20 when I was using standard scaling.",
    "1651190": ""
  }
}