{
  "id": 76286,
  "title": "difference b/w  \"new_merchant_transactions.csv\" and \"historical_transactions.csv\" ",
  "url": "/competitions/elo-merchant-category-recommendation/discussion/76286",
  "author_name": "",
  "post_date": "2018-12-31T16:26:15.240467Z",
  "votes": 3,
  "comment_count": 5,
  "views": 0,
  "content": "<p>is there any difference between \"new_merchant_transactions.csv\" and \"historical_transactions.csv\" except Date,\nwhat is the point of giving them separately ?</p>",
  "messages": [
    {
      "id": "448268",
      "postDate": "12/31/2018 16:26:15",
      "content": "<p>is there any difference between \"new_merchant_transactions.csv\" and \"historical_transactions.csv\" except Date,\nwhat is the point of giving them separately ?</p>",
      "rawMarkdown": "is there any difference between \"new_merchant_transactions.csv\" and \"historical_transactions.csv\" except Date,\nwhat is the point of giving them separately ?",
      "votes": null
    },
    {
      "id": "448351",
      "postDate": "12/31/2018 20:57:40",
      "content": "<p>From <a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/data\">https://www.kaggle.com/c/elo-merchant-category-recommendation/data</a>, which I recommend you read if you haven't:</p>\n\n<blockquote>\n  <p>historical transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant ids. new merchant transactions.csv contains the transactions at new merchants (merchant ids that this particular card id has not yet visited) over a period of two months.</p>\n</blockquote>",
      "rawMarkdown": "From https://www.kaggle.com/c/elo-merchant-category-recommendation/data, which I recommend you read if you haven't:\n\n&gt; historical transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant ids. new merchant transactions.csv contains the transactions at new merchants (merchant ids that this particular card id has not yet visited) over a period of two months.",
      "votes": null
    },
    {
      "id": "448450",
      "postDate": "01/01/2019 08:14:59",
      "content": "<p>I understood that. but its like partition of a dataframe into two parts with different date  </p>",
      "rawMarkdown": "I understood that. but its like partition of a dataframe into two parts with different date",
      "votes": null
    },
    {
      "id": "448454",
      "postDate": "01/01/2019 08:20:42",
      "content": "<p>It is not purely a partition, as there is both a date constraint (before vs. after a reference period) and a constraint on merchant id (only merchant ids not in the first set are present in the second set).</p>",
      "rawMarkdown": "It is not purely a partition, as there is both a date constraint (before vs. after a reference period) and a constraint on merchant id (only merchant ids not in the first set are present in the second set).",
      "votes": null
    },
    {
      "id": "448937",
      "postDate": "01/02/2019 11:42:22",
      "content": "<p>I am confused too</p>",
      "rawMarkdown": "I am confused too",
      "votes": null
    },
    {
      "id": "448991",
      "postDate": "01/02/2019 13:49:26",
      "content": "<p>Hi!, These two datasets are quite confusing, but also they are essential improving to improve your RMSE particularly the way that can be combined, I believe the reason is that \"newmerchanttransactions\" have customers that never came back to a store/market, highlighting potential less Loyal; customers.</p>",
      "rawMarkdown": "Hi!, These two datasets are quite confusing, but also they are essential improving to improve your RMSE particularly the way that can be combined, I believe the reason is that \"newmerchanttransactions\" have customers that never came back to a store/market, highlighting potential less Loyal; customers.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 448351,
      "author_name": "peterhurford",
      "author_url": "",
      "post_date": "12/31/2018 20:57:40",
      "content": "<p>From <a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/data\">https://www.kaggle.com/c/elo-merchant-category-recommendation/data</a>, which I recommend you read if you haven't:</p>\n\n<blockquote>\n  <p>historical transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant ids. new merchant transactions.csv contains the transactions at new merchants (merchant ids that this particular card id has not yet visited) over a period of two months.</p>\n</blockquote>",
      "votes": null,
      "replies": [
        {
          "id": 448450,
          "author_name": "mks2192",
          "author_url": "",
          "post_date": "01/01/2019 08:14:59",
          "content": "<p>I understood that. but its like partition of a dataframe into two parts with different date  </p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 448454,
          "author_name": "peterhurford",
          "author_url": "",
          "post_date": "01/01/2019 08:20:42",
          "content": "<p>It is not purely a partition, as there is both a date constraint (before vs. after a reference period) and a constraint on merchant id (only merchant ids not in the first set are present in the second set).</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 448937,
      "author_name": "maying",
      "author_url": "",
      "post_date": "01/02/2019 11:42:22",
      "content": "<p>I am confused too</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 448991,
      "author_name": "cv13j0",
      "author_url": "",
      "post_date": "01/02/2019 13:49:26",
      "content": "<p>Hi!, These two datasets are quite confusing, but also they are essential improving to improve your RMSE particularly the way that can be combined, I believe the reason is that \"newmerchanttransactions\" have customers that never came back to a store/market, highlighting potential less Loyal; customers.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "448268": "is there any difference between \"new_merchant_transactions.csv\" and \"historical_transactions.csv\" except Date,\nwhat is the point of giving them separately ?",
    "448351": "From https://www.kaggle.com/c/elo-merchant-category-recommendation/data, which I recommend you read if you haven't:\n\n&gt; historical transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant ids. new merchant transactions.csv contains the transactions at new merchants (merchant ids that this particular card id has not yet visited) over a period of two months.",
    "448450": "I understood that. but its like partition of a dataframe into two parts with different date",
    "448454": "It is not purely a partition, as there is both a date constraint (before vs. after a reference period) and a constraint on merchant id (only merchant ids not in the first set are present in the second set).",
    "448937": "I am confused too",
    "448991": "Hi!, These two datasets are quite confusing, but also they are essential improving to improve your RMSE particularly the way that can be combined, I believe the reason is that \"newmerchanttransactions\" have customers that never came back to a store/market, highlighting potential less Loyal; customers."
  },
  "source": "meta"
}