{
  "id": 72898,
  "title": "Difference between train and test data sets",
  "url": "/competitions/elo-merchant-category-recommendation/discussion/72898",
  "author_name": "",
  "post_date": "2018-11-28T06:47:59.441303300Z",
  "votes": null,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I thought the columns in train and test data sets need to be similar. it appears that target is missing in train.csv. Did I miss anything here?</p>",
  "messages": [
    {
      "id": "428970",
      "postDate": "11/28/2018 06:47:59",
      "content": "<p>I thought the columns in train and test data sets need to be similar. it appears that target is missing in train.csv. Did I miss anything here?</p>",
      "rawMarkdown": "I thought the columns in train and test data sets need to be similar. it appears that target is missing in train.csv. Did I miss anything here?",
      "votes": null
    },
    {
      "id": "429085",
      "postDate": "11/28/2018 10:15:43",
      "content": "<p>How are you processing the data? When I read it via read_csv (in R), I get the columns</p>\n\n<p>\"first_active_month\" \"card_id\"            \"feature_1\"          \"feature_2\"          \"feature_3\"          \"target\"          </p>",
      "rawMarkdown": "How are you processing the data? When I read it via read_csv (in R), I get the columns\n\n \"first_active_month\" \"card_id\"            \"feature_1\"          \"feature_2\"          \"feature_3\"          \"target\"",
      "votes": null
    },
    {
      "id": "429221",
      "postDate": "11/28/2018 14:43:19",
      "content": "<p>I have the feeling that you mean that what is missing is the variable <em>target</em> in <em>test.csv</em>. This is done so you can cast your predictions and upload the result to the competition. It is based on those predictions that you will be positioned on the leaderboard.</p>\n\n<p>All your cross-validation, in which you need the <em>target</em>, needs to be done using the <em>train.csv</em>.</p>",
      "rawMarkdown": "I have the feeling that you mean that what is missing is the variable _target_ in _test.csv_. This is done so you can cast your predictions and upload the result to the competition. It is based on those predictions that you will be positioned on the leaderboard.\n\nAll your cross-validation, in which you need the _target_, needs to be done using the _train.csv_.",
      "votes": null
    },
    {
      "id": "429376",
      "postDate": "11/28/2018 19:03:40",
      "content": "<p>Albert,</p>\n\n<p>Essentially my train.csv needs to be split 80:20 or 70:30 for validation. I mistook train.csv to contain only training data not validation. </p>\n\n<p>Thanks</p>",
      "rawMarkdown": "Albert,\n\nEssentially my train.csv needs to be split 80:20 or 70:30 for validation. I mistook train.csv to contain only training data not validation. \n\nThanks",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 429085,
      "author_name": "konradb",
      "author_url": "",
      "post_date": "11/28/2018 10:15:43",
      "content": "<p>How are you processing the data? When I read it via read_csv (in R), I get the columns</p>\n\n<p>\"first_active_month\" \"card_id\"            \"feature_1\"          \"feature_2\"          \"feature_3\"          \"target\"          </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 429221,
      "author_name": "almarin",
      "author_url": "",
      "post_date": "11/28/2018 14:43:19",
      "content": "<p>I have the feeling that you mean that what is missing is the variable <em>target</em> in <em>test.csv</em>. This is done so you can cast your predictions and upload the result to the competition. It is based on those predictions that you will be positioned on the leaderboard.</p>\n\n<p>All your cross-validation, in which you need the <em>target</em>, needs to be done using the <em>train.csv</em>.</p>",
      "votes": null,
      "replies": [
        {
          "id": 429376,
          "author_name": "rphanu",
          "author_url": "",
          "post_date": "11/28/2018 19:03:40",
          "content": "<p>Albert,</p>\n\n<p>Essentially my train.csv needs to be split 80:20 or 70:30 for validation. I mistook train.csv to contain only training data not validation. </p>\n\n<p>Thanks</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "428970": "I thought the columns in train and test data sets need to be similar. it appears that target is missing in train.csv. Did I miss anything here?",
    "429085": "How are you processing the data? When I read it via read_csv (in R), I get the columns\n\n \"first_active_month\" \"card_id\"            \"feature_1\"          \"feature_2\"          \"feature_3\"          \"target\"",
    "429221": "I have the feeling that you mean that what is missing is the variable _target_ in _test.csv_. This is done so you can cast your predictions and upload the result to the competition. It is based on those predictions that you will be positioned on the leaderboard.\n\nAll your cross-validation, in which you need the _target_, needs to be done using the _train.csv_.",
    "429376": "Albert,\n\nEssentially my train.csv needs to be split 80:20 or 70:30 for validation. I mistook train.csv to contain only training data not validation. \n\nThanks"
  },
  "source": "meta"
}