{
  "id": 678985,
  "title": "The 'amount' column on raw_train.csv",
  "url": "/competitions/bidding-predictions-for-construction/discussion/678985",
  "author_name": "",
  "post_date": "2026-02-26T09:42:05.449185100Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I was wondering what the **'amount' **column actually represent.\nThe description provided is a little vague</p>\n<p><code>amount - f64 - the UNIT PRICE submitted for that pay-item</code></p>\n<p>Is it a scaling factor like currency exchange rate?</p>\n<p>It is also not present in the <code>raw_test.csv</code>, so using it as a input feature for modelling is more or less impractical.</p>",
  "messages": [
    {
      "id": "3414226",
      "postDate": "02/26/2026 09:42:05",
      "content": "<p>I was wondering what the **'amount' **column actually represent.\nThe description provided is a little vague</p>\n<p><code>amount - f64 - the UNIT PRICE submitted for that pay-item</code></p>\n<p>Is it a scaling factor like currency exchange rate?</p>\n<p>It is also not present in the <code>raw_test.csv</code>, so using it as a input feature for modelling is more or less impractical.</p>",
      "rawMarkdown": "I was wondering what the **'amount' **column actually represent.\nThe description provided is a little vague\n\n `amount - f64 - the UNIT PRICE submitted for that pay-item`\n\nIs it a scaling factor like currency exchange rate?\n\nIt is also not present in the `raw_test.csv`, so using it as a input feature for modelling is more or less impractical.",
      "votes": null
    },
    {
      "id": "3414669",
      "postDate": "02/27/2026 11:37:00",
      "content": "<p>It is the cost of a single item in the row. For example, if you have row with:\nquantity: 239\namount: 305\npay_item_description: PLANT DECIDUOUS TREE SINGLE STEM 1.25 IN OR UNDER</p>\n<p>It means that the contractor proposes to plant 239 trees, and each tree would cost 305$</p>\n<p>If you multiply quantity by amount, and then summarise it for all rows for some row_id, you will get exactly the target feature for that row_id. This is why it's not provided in test.</p>",
      "rawMarkdown": "It is the cost of a single item in the row. For example, if you have row with:\nquantity: 239\namount: 305\npay_item_description: PLANT DECIDUOUS TREE SINGLE STEM 1.25 IN OR UNDER\n\nIt means that the contractor proposes to plant 239 trees, and each tree would cost 305$\n\nIf you multiply quantity by amount, and then summarise it for all rows for some row_id, you will get exactly the target feature for that row_id. This is why it's not provided in test.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3414669,
      "author_name": "ehrenstein",
      "author_url": "",
      "post_date": "02/27/2026 11:37:00",
      "content": "<p>It is the cost of a single item in the row. For example, if you have row with:\nquantity: 239\namount: 305\npay_item_description: PLANT DECIDUOUS TREE SINGLE STEM 1.25 IN OR UNDER</p>\n<p>It means that the contractor proposes to plant 239 trees, and each tree would cost 305$</p>\n<p>If you multiply quantity by amount, and then summarise it for all rows for some row_id, you will get exactly the target feature for that row_id. This is why it's not provided in test.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "3414226": "I was wondering what the **'amount' **column actually represent.\nThe description provided is a little vague\n\n `amount - f64 - the UNIT PRICE submitted for that pay-item`\n\nIs it a scaling factor like currency exchange rate?\n\nIt is also not present in the `raw_test.csv`, so using it as a input feature for modelling is more or less impractical.",
    "3414669": "It is the cost of a single item in the row. For example, if you have row with:\nquantity: 239\namount: 305\npay_item_description: PLANT DECIDUOUS TREE SINGLE STEM 1.25 IN OR UNDER\n\nIt means that the contractor proposes to plant 239 trees, and each tree would cost 305$\n\nIf you multiply quantity by amount, and then summarise it for all rows for some row_id, you will get exactly the target feature for that row_id. This is why it's not provided in test."
  },
  "source": "meta"
}