{
  "id": 43810,
  "title": "Item_nbr not seen before in the training dataset",
  "url": "/competitions/favorita-grocery-sales-forecasting/discussion/43810",
  "author_name": "",
  "post_date": "2017-11-20T04:11:05.683616200Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Does the test data set contain Item_nbrs that have not been seen before in the training dataset?  If so how can you train your model.</p>\n\n<p>This is what I got when i tried to run model.predict for the training portion of my dataset on xgboost</p>\n\n<p>item_nbr: y contains new labels: ['0' '1' '10' '100' '1000' '10000' '100000' '1000000' '1000001' '1000002'\n '1000003' '1000004' '1000005' '1000006' '1000007' '1000008' '1000009'\n '100001' '1000010' '1000011' ..., '999981' '999982' '999983' '999984'\n '999985' '999986' '999987' '999988' '999989' '99999' '999990' '999991'\n '999992' '999993' '999994' '999995' '999996' '999997' '999998' '999999']</p>",
  "messages": [
    {
      "id": "245916",
      "postDate": "11/20/2017 04:11:05",
      "content": "<p>Does the test data set contain Item_nbrs that have not been seen before in the training dataset?  If so how can you train your model.</p>\n\n<p>This is what I got when i tried to run model.predict for the training portion of my dataset on xgboost</p>\n\n<p>item_nbr: y contains new labels: ['0' '1' '10' '100' '1000' '10000' '100000' '1000000' '1000001' '1000002'\n '1000003' '1000004' '1000005' '1000006' '1000007' '1000008' '1000009'\n '100001' '1000010' '1000011' ..., '999981' '999982' '999983' '999984'\n '999985' '999986' '999987' '999988' '999989' '99999' '999990' '999991'\n '999992' '999993' '999994' '999995' '999996' '999997' '999998' '999999']</p>",
      "rawMarkdown": "Does the test data set contain Item_nbrs that have not been seen before in the training dataset?  If so how can you train your model.\n\nThis is what I got when i tried to run model.predict for the training portion of my dataset on xgboost\n\nitem_nbr: y contains new labels: ['0' '1' '10' '100' '1000' '10000' '100000' '1000000' '1000001' '1000002'\n '1000003' '1000004' '1000005' '1000006' '1000007' '1000008' '1000009'\n '100001' '1000010' '1000011' ..., '999981' '999982' '999983' '999984'\n '999985' '999986' '999987' '999988' '999989' '99999' '999990' '999991'\n '999992' '999993' '999994' '999995' '999996' '999997' '999998' '999999']",
      "votes": null
    },
    {
      "id": "246315",
      "postDate": "11/20/2017 23:51:59",
      "content": "<p>Yes in fact, there is an extensive discussion about this here: <a href=\"https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/42964\">https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/42964</a>  and there is a little information in the data description.  :)</p>",
      "rawMarkdown": "Yes in fact, there is an extensive discussion about this here: https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/42964  and there is a little information in the data description.  :)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 246315,
      "author_name": "skyrmion",
      "author_url": "",
      "post_date": "11/20/2017 23:51:59",
      "content": "<p>Yes in fact, there is an extensive discussion about this here: <a href=\"https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/42964\">https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/42964</a>  and there is a little information in the data description.  :)</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "245916": "Does the test data set contain Item_nbrs that have not been seen before in the training dataset?  If so how can you train your model.\n\nThis is what I got when i tried to run model.predict for the training portion of my dataset on xgboost\n\nitem_nbr: y contains new labels: ['0' '1' '10' '100' '1000' '10000' '100000' '1000000' '1000001' '1000002'\n '1000003' '1000004' '1000005' '1000006' '1000007' '1000008' '1000009'\n '100001' '1000010' '1000011' ..., '999981' '999982' '999983' '999984'\n '999985' '999986' '999987' '999988' '999989' '99999' '999990' '999991'\n '999992' '999993' '999994' '999995' '999996' '999997' '999998' '999999']",
    "246315": "Yes in fact, there is an extensive discussion about this here: https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/42964  and there is a little information in the data description.  :)"
  },
  "source": "meta"
}