{
  "id": 291163,
  "title": "How to use \"supplemental_train.cvs\"",
  "url": "/competitions/g-research-crypto-forecasting/discussion/291163",
  "author_name": "JianchiZhang",
  "post_date": "2021-11-28T06:29:42.260000",
  "votes": 5,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I noticed that there is similar topic at <a href=\"https://www.kaggle.com/c/g-research-crypto-forecasting/discussion/286493\" target=\"_blank\">https://www.kaggle.com/c/g-research-crypto-forecasting/discussion/286493</a>, but there is no response yet.</p>\n<p>According to the description of supplemental_train.csv:</p>\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<p>Does it means, the train.csv and supplemental_train.csv will be different and supplemental_train.csv will not be included in train.csv after the submission period (supplemental_train.csv will be replaced by current train.csv?) even though the current supplemental_train.csv is included in current train.csv?</p>\n<p>And more importantly, how we use this supplemental_train.csv? Shall we combine the train.csv with supplemental_train.csv when we are submitting the notebook? Considering that they will be different after the submission period, we may expect to see better result if we use them together?</p>",
  "messages": [
    {
      "id": 1597998,
      "postDate": "2021-11-28T06:29:42.260Z",
      "content": "<p>I noticed that there is similar topic at <a href=\"https://www.kaggle.com/c/g-research-crypto-forecasting/discussion/286493\" target=\"_blank\">https://www.kaggle.com/c/g-research-crypto-forecasting/discussion/286493</a>, but there is no response yet.</p>\n<p>According to the description of supplemental_train.csv:</p>\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<p>Does it means, the train.csv and supplemental_train.csv will be different and supplemental_train.csv will not be included in train.csv after the submission period (supplemental_train.csv will be replaced by current train.csv?) even though the current supplemental_train.csv is included in current train.csv?</p>\n<p>And more importantly, how we use this supplemental_train.csv? Shall we combine the train.csv with supplemental_train.csv when we are submitting the notebook? Considering that they will be different after the submission period, we may expect to see better result if we use them together?</p>",
      "rawMarkdown": "I noticed that there is similar topic at https://www.kaggle.com/c/g-research-crypto-forecasting/discussion/286493, but there is no response yet.\n\nAccording to the description of supplemental_train.csv:\n\nAfter 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 it means, the train.csv and supplemental_train.csv will be different and supplemental_train.csv will not be included in train.csv after the submission period (supplemental_train.csv will be replaced by current train.csv?) even though the current supplemental_train.csv is included in current train.csv?\n\nAnd more importantly, how we use this supplemental_train.csv? Shall we combine the train.csv with supplemental_train.csv when we are submitting the notebook? Considering that they will be different after the submission period, we may expect to see better result if we use them together?",
      "votes": 5
    },
    {
      "id": 1604620,
      "postDate": "2021-12-03T14:56:14.557Z",
      "content": "<p>Have just reread info in the Data tab, so I think for our final submission we should add supplemental_train.csv to our main train.csv dataset and train our model on both of them. The main concern is that we can run out of memory limit.</p>",
      "rawMarkdown": "Have just reread info in the Data tab, so I think for our final submission we should add supplemental_train.csv to our main train.csv dataset and train our model on both of them. The main concern is that we can run out of memory limit.",
      "votes": 3
    },
    {
      "id": 1604598,
      "postDate": "2021-12-03T14:20:38.373Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 1604620,
      "author_name": "Alan Kabisov",
      "author_url": "",
      "post_date": "2021-12-03T14:56:14.557000",
      "content": "<p>Have just reread info in the Data tab, so I think for our final submission we should add supplemental_train.csv to our main train.csv dataset and train our model on both of them. The main concern is that we can run out of memory limit.</p>",
      "votes": 3,
      "replies": []
    },
    {
      "id": 1604598,
      "author_name": "",
      "author_url": "",
      "post_date": "2021-12-03T14:20:38.373000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1597998": "I noticed that there is similar topic at https://www.kaggle.com/c/g-research-crypto-forecasting/discussion/286493, but there is no response yet.\n\nAccording to the description of supplemental_train.csv:\n\nAfter 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 it means, the train.csv and supplemental_train.csv will be different and supplemental_train.csv will not be included in train.csv after the submission period (supplemental_train.csv will be replaced by current train.csv?) even though the current supplemental_train.csv is included in current train.csv?\n\nAnd more importantly, how we use this supplemental_train.csv? Shall we combine the train.csv with supplemental_train.csv when we are submitting the notebook? Considering that they will be different after the submission period, we may expect to see better result if we use them together?",
    "1604620": "Have just reread info in the Data tab, so I think for our final submission we should add supplemental_train.csv to our main train.csv dataset and train our model on both of them. The main concern is that we can run out of memory limit.",
    "1604598": ""
  }
}