{
  "id": 41557,
  "title": "onpromotion field is empty",
  "url": "/competitions/favorita-grocery-sales-forecasting/discussion/41557",
  "author_name": "",
  "post_date": "2017-10-20T07:20:13.512695800Z",
  "votes": 2,
  "comment_count": 7,
  "views": 0,
  "content": "<p>As per Data Description, Approximately 16% of the <strong>onpromotion</strong> values in train.csv file are NaN. But <strong>onpromotion</strong> field is empty for train.csv.</p>",
  "messages": [
    {
      "id": "233437",
      "postDate": "10/20/2017 07:20:13",
      "content": "<p>As per Data Description, Approximately 16% of the <strong>onpromotion</strong> values in train.csv file are NaN. But <strong>onpromotion</strong> field is empty for train.csv.</p>",
      "rawMarkdown": "As per Data Description, Approximately 16% of the **onpromotion** values in train.csv file are NaN. But **onpromotion** field is empty for train.csv.",
      "votes": null
    },
    {
      "id": "233527",
      "postDate": "10/20/2017 13:07:08",
      "content": "<p>Hi Akshay -</p>\n\n<p>This is what I'm seeing. Can you check <code>train.tail()</code>?</p>\n\n<p><img src=\"https://i.imgur.com/glXADoi.png\" alt=\"tail\" title=\"\"></p>",
      "rawMarkdown": "Hi Akshay -\n\nThis is what I'm seeing. Can you check `train.tail()`?\n\n![tail][1]\n\n\n  [1]: https://i.imgur.com/glXADoi.png",
      "votes": null
    },
    {
      "id": "233742",
      "postDate": "10/21/2017 02:08:38",
      "content": "<p>Hitting this too</p>",
      "rawMarkdown": "Hitting this too",
      "votes": null
    },
    {
      "id": "233779",
      "postDate": "10/21/2017 07:23:09",
      "content": "<p>Pandas is giving a warning of having mixed data types in column 5 but in my case it automatically changes the datatype to 'O' .  Try specifying the datatype in read_csv command.</p>",
      "rawMarkdown": "Pandas is giving a warning of having mixed data types in column 5 but in my case it automatically changes the datatype to 'O' .  Try specifying the datatype in read_csv command.",
      "votes": null
    },
    {
      "id": "234189",
      "postDate": "10/22/2017 15:34:49",
      "content": "<p>It's empty correct, any idea how to go about it</p>",
      "rawMarkdown": "It's empty correct, any idea how to go about it",
      "votes": null
    },
    {
      "id": "236235",
      "postDate": "10/26/2017 21:07:48",
      "content": "<p>First I thought its all NaN, but once you look at the tail, you see there are either true or false. \nThanks.</p>\n\n<p>id  date    store_nbr   item_nbr    unit_sales  onpromotion\n125497035   125497035   2017-08-15  54  2089339 4.0 False\n125497036   125497036   2017-08-15  54  2106464 1.0 True\n125497037   125497037   2017-08-15  54  2110456      192.0  False\n125497038   125497038   2017-08-15  54  2113914     198.0   True\n125497039   125497039   2017-08-15  54  2116416    2.0  False</p>",
      "rawMarkdown": "First I thought its all NaN, but once you look at the tail, you see there are either true or false. \nThanks.\n\n\nid\tdate\tstore_nbr\titem_nbr\tunit_sales\tonpromotion\n125497035\t125497035\t2017-08-15\t54\t2089339\t4.0\tFalse\n125497036\t125497036\t2017-08-15\t54\t2106464\t1.0\tTrue\n125497037\t125497037\t2017-08-15\t54\t2110456\t     192.0\tFalse\n125497038\t125497038\t2017-08-15\t54\t2113914\t    198.0\tTrue\n125497039\t125497039\t2017-08-15\t54\t2116416\t   2.0\tFalse",
      "votes": null
    },
    {
      "id": "236849",
      "postDate": "10/28/2017 12:03:27",
      "content": "<p><strong>onpromotion</strong> has values since 2014-04-01</p>",
      "rawMarkdown": "**onpromotion** has values since 2014-04-01",
      "votes": null
    },
    {
      "id": "240455",
      "postDate": "11/06/2017 16:35:33",
      "content": "<p>When training model values of onpromotion converts to 1 or 0, so it is not needed to treat them before encoding</p>",
      "rawMarkdown": "When training model values of onpromotion converts to 1 or 0, so it is not needed to treat them before encoding",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 233527,
      "author_name": "inversion",
      "author_url": "",
      "post_date": "10/20/2017 13:07:08",
      "content": "<p>Hi Akshay -</p>\n\n<p>This is what I'm seeing. Can you check <code>train.tail()</code>?</p>\n\n<p><img src=\"https://i.imgur.com/glXADoi.png\" alt=\"tail\" title=\"\"></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 233742,
      "author_name": "batterman",
      "author_url": "",
      "post_date": "10/21/2017 02:08:38",
      "content": "<p>Hitting this too</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 233779,
      "author_name": "trekkerthemaker",
      "author_url": "",
      "post_date": "10/21/2017 07:23:09",
      "content": "<p>Pandas is giving a warning of having mixed data types in column 5 but in my case it automatically changes the datatype to 'O' .  Try specifying the datatype in read_csv command.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 234189,
      "author_name": "cmogre",
      "author_url": "",
      "post_date": "10/22/2017 15:34:49",
      "content": "<p>It's empty correct, any idea how to go about it</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 236235,
      "author_name": "yektayazdani",
      "author_url": "",
      "post_date": "10/26/2017 21:07:48",
      "content": "<p>First I thought its all NaN, but once you look at the tail, you see there are either true or false. \nThanks.</p>\n\n<p>id  date    store_nbr   item_nbr    unit_sales  onpromotion\n125497035   125497035   2017-08-15  54  2089339 4.0 False\n125497036   125497036   2017-08-15  54  2106464 1.0 True\n125497037   125497037   2017-08-15  54  2110456      192.0  False\n125497038   125497038   2017-08-15  54  2113914     198.0   True\n125497039   125497039   2017-08-15  54  2116416    2.0  False</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 236849,
      "author_name": "gaogao",
      "author_url": "",
      "post_date": "10/28/2017 12:03:27",
      "content": "<p><strong>onpromotion</strong> has values since 2014-04-01</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 240455,
      "author_name": "hemantnyadav",
      "author_url": "",
      "post_date": "11/06/2017 16:35:33",
      "content": "<p>When training model values of onpromotion converts to 1 or 0, so it is not needed to treat them before encoding</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "233437": "As per Data Description, Approximately 16% of the **onpromotion** values in train.csv file are NaN. But **onpromotion** field is empty for train.csv.",
    "233527": "Hi Akshay -\n\nThis is what I'm seeing. Can you check `train.tail()`?\n\n![tail][1]\n\n\n  [1]: https://i.imgur.com/glXADoi.png",
    "233742": "Hitting this too",
    "233779": "Pandas is giving a warning of having mixed data types in column 5 but in my case it automatically changes the datatype to 'O' .  Try specifying the datatype in read_csv command.",
    "234189": "It's empty correct, any idea how to go about it",
    "236235": "First I thought its all NaN, but once you look at the tail, you see there are either true or false. \nThanks.\n\n\nid\tdate\tstore_nbr\titem_nbr\tunit_sales\tonpromotion\n125497035\t125497035\t2017-08-15\t54\t2089339\t4.0\tFalse\n125497036\t125497036\t2017-08-15\t54\t2106464\t1.0\tTrue\n125497037\t125497037\t2017-08-15\t54\t2110456\t     192.0\tFalse\n125497038\t125497038\t2017-08-15\t54\t2113914\t    198.0\tTrue\n125497039\t125497039\t2017-08-15\t54\t2116416\t   2.0\tFalse",
    "236849": "**onpromotion** has values since 2014-04-01",
    "240455": "When training model values of onpromotion converts to 1 or 0, so it is not needed to treat them before encoding"
  },
  "source": "meta"
}