{
  "id": 51518,
  "title": "data descriptions",
  "url": "/competitions/talkingdata-adtracking-fraud-detection/discussion/51518",
  "author_name": "",
  "post_date": "2018-03-09T20:01:57.189829800Z",
  "votes": 1,
  "comment_count": 5,
  "views": 0,
  "content": "<ol>\n<li>In train dataset, what is meant by \"encoded\"?  Does it mean this variables should be treated as categorical variables? \n<ol><li>In test dataset, what exactly is \"click_id: reference for making predictions\" ?</li>\n<li>What is the variable \"channel: channel id of mobile ad publisher\" ? I'm specifically confused about what is a channel. Is it possible to have an example ? </li></ol></li>\n</ol>\n\n<p>Thanks!</p>",
  "messages": [
    {
      "id": "293420",
      "postDate": "03/09/2018 20:01:57",
      "content": "<ol>\n<li>In train dataset, what is meant by \"encoded\"?  Does it mean this variables should be treated as categorical variables? \n<ol><li>In test dataset, what exactly is \"click_id: reference for making predictions\" ?</li>\n<li>What is the variable \"channel: channel id of mobile ad publisher\" ? I'm specifically confused about what is a channel. Is it possible to have an example ? </li></ol></li>\n</ol>\n\n<p>Thanks!</p>",
      "rawMarkdown": "1. In train dataset, what is meant by \"encoded\"?  Does it mean this variables should be treated as categorical variables? \n2. In test dataset, what exactly is \"click_id: reference for making predictions\" ?\n3.  What is the variable \"channel: channel id of mobile ad publisher\" ? I'm specifically confused about what is a channel. Is it possible to have an example ? \n\nThanks!",
      "votes": null
    },
    {
      "id": "293723",
      "postDate": "03/10/2018 12:37:55",
      "content": "<p>my understanding for 'channel' is that 'channel'  means advertisement company, for example facebook is an advertisement channel.</p>",
      "rawMarkdown": "my understanding for 'channel' is that 'channel'  means advertisement company, for example facebook is an advertisement channel.",
      "votes": null
    },
    {
      "id": "294084",
      "postDate": "03/11/2018 08:33:24",
      "content": "<p>From what I have understood : 1) it is just an id... nothing more than this... \n2) channel - what @Luke said complies with the terminology used in the ad business: the advertisment channel - be it facebook, real time bidding exchange, etc.</p>",
      "rawMarkdown": "From what I have understood : 1) it is just an id... nothing more than this... \n2) channel - what @Luke said complies with the terminology used in the ad business: the advertisment channel - be it facebook, real time bidding exchange, etc.",
      "votes": null
    },
    {
      "id": "294261",
      "postDate": "03/11/2018 16:53:50",
      "content": "<p>Got it. Thanks for the clarification! </p>",
      "rawMarkdown": "Got it. Thanks for the clarification!",
      "votes": null
    },
    {
      "id": "294262",
      "postDate": "03/11/2018 16:54:04",
      "content": "<p>Got it. Thanks!</p>",
      "rawMarkdown": "Got it. Thanks!",
      "votes": null
    },
    {
      "id": "294524",
      "postDate": "03/12/2018 04:14:19",
      "content": "<p>Encoded means the actual value was changed to ID number. \"I Phone 7\" =&gt; \"1\", \"Galaxy Nexus\" =&gt; \"2\". I believe this should be treated as \"categorical\" value. But you might be able to recover some \"continuity\" of the data by doing some unsupervised learning, or supervised using other variables as target.</p>",
      "rawMarkdown": "Encoded means the actual value was changed to ID number. \"I Phone 7\" =&gt; \"1\", \"Galaxy Nexus\" =&gt; \"2\". I believe this should be treated as \"categorical\" value. But you might be able to recover some \"continuity\" of the data by doing some unsupervised learning, or supervised using other variables as target.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 293723,
      "author_name": "masaladata",
      "author_url": "",
      "post_date": "03/10/2018 12:37:55",
      "content": "<p>my understanding for 'channel' is that 'channel'  means advertisement company, for example facebook is an advertisement channel.</p>",
      "votes": null,
      "replies": [
        {
          "id": 294262,
          "author_name": "chisq1564",
          "author_url": "",
          "post_date": "03/11/2018 16:54:04",
          "content": "<p>Got it. Thanks!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 294084,
      "author_name": "asparuhhristov",
      "author_url": "",
      "post_date": "03/11/2018 08:33:24",
      "content": "<p>From what I have understood : 1) it is just an id... nothing more than this... \n2) channel - what @Luke said complies with the terminology used in the ad business: the advertisment channel - be it facebook, real time bidding exchange, etc.</p>",
      "votes": null,
      "replies": [
        {
          "id": 294261,
          "author_name": "chisq1564",
          "author_url": "",
          "post_date": "03/11/2018 16:53:50",
          "content": "<p>Got it. Thanks for the clarification! </p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 294524,
      "author_name": "muhammadalfiansyah",
      "author_url": "",
      "post_date": "03/12/2018 04:14:19",
      "content": "<p>Encoded means the actual value was changed to ID number. \"I Phone 7\" =&gt; \"1\", \"Galaxy Nexus\" =&gt; \"2\". I believe this should be treated as \"categorical\" value. But you might be able to recover some \"continuity\" of the data by doing some unsupervised learning, or supervised using other variables as target.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "293420": "1. In train dataset, what is meant by \"encoded\"?  Does it mean this variables should be treated as categorical variables? \n2. In test dataset, what exactly is \"click_id: reference for making predictions\" ?\n3.  What is the variable \"channel: channel id of mobile ad publisher\" ? I'm specifically confused about what is a channel. Is it possible to have an example ? \n\nThanks!",
    "293723": "my understanding for 'channel' is that 'channel'  means advertisement company, for example facebook is an advertisement channel.",
    "294084": "From what I have understood : 1) it is just an id... nothing more than this... \n2) channel - what @Luke said complies with the terminology used in the ad business: the advertisment channel - be it facebook, real time bidding exchange, etc.",
    "294261": "Got it. Thanks for the clarification!",
    "294262": "Got it. Thanks!",
    "294524": "Encoded means the actual value was changed to ID number. \"I Phone 7\" =&gt; \"1\", \"Galaxy Nexus\" =&gt; \"2\". I believe this should be treated as \"categorical\" value. But you might be able to recover some \"continuity\" of the data by doing some unsupervised learning, or supervised using other variables as target."
  },
  "source": "meta"
}