{
  "fetched_at": "2026-10-20T06:38:16Z",
  "source_url": "https://www.kaggle.com/competitions/applications-of-deep-learning-wustl-spring-2017/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>This page shows up underneath the data files. Here you describe what files you have provided and the format of each. There is no single format for this page that is appropriate for all competitons, but you should strive to describe as much as you can here. A little time spent describing the data here can save a lot of time answering questions later.</p>\r\n<p>Participants should be able to answer questions like these after reading the data description: What files do I need? What should I expect the data format to be? What am I predicting? What acroynms will I encounter?</p>\r\n<h2>File descriptions</h2>\r\n<ul>\r\n<li><strong>train.csv</strong> - the training set</li>\r\n<li><strong>test.csv</strong> - the test set</li>\r\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\r\n</ul>\r\n<h2>Data fields</h2>\r\n<ul>\r\n<li>id - An ID that is unique to each row.</li>\r\n<li>title - The title to the Wikipedia article.</li>\r\n<li>len - The length of the Wikipedia article.</li>\r\n<li>cite_arXiv - Count of arXiv citations in article.</li>\r\n<li>cite_av_media - Count of AV media citations in article.</li>\r\n<li>cite_book - Count of book citations in article.</li>\r\n<li>cite_comic - Count of comic book citations in article.</li>\r\n<li>cite_conference - Count of conference citations in article.</li>\r\n<li>cite_encyclopedia - Count of encyclopedia citations in article.</li>\r\n<li>cite_episode - Count of episode citations in article.</li>\r\n<li>cite_govtrack - Count of govtrack citations in article.</li>\r\n<li>cite_journal - Count of journal citations in article.</li>\r\n<li>cite_magazine - Count of magazine citations in article.</li>\r\n<li>cite_press_release - Count of press release citations in article.</li>\r\n<li>cite_web - Count of web citations in article.</li>\r\n<li>links - Count of links to other wikipedia articles.</li>\r\n<li>tables - Count of tables in article.</li>\r\n<li>files - Count of files (e.g. images) in article.</li>\r\n<li>math - Count of math expressions in article.</li>\r\n<li>class - The class of the article (this is the target), these have the following meaning:</li>\r\n<ul>\r\n<li>0 is a company</li>\r\n<li>1 is a politician</li>\r\n<li>2 is a scientist</li>\r\n<li>3 is a university</li>\r\n<li>4 is an automobile</li>\r\n<li>5 is a type of dog</li>\r\n</ul>\r\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is programming assignment 3 from the course <a href=\"https://sites.wustl.edu/jeffheaton/t81-558/\" target=\"_blank\">T81-855: Applications of Deep Learning</a> at Washington University in St. Louis. All students must create a Kaggle account and submit a solution. Once you have submitted your solution entry log into Blackboard (at WUSTL) and submit a single file telling me your Kaggle name on the leaderboard (you do not need to register to Kaggle with your real name). This competition will be visible to the public, so there may be non-student submissions as well as student.</p>\r\n<p>The data set for this competition consists of 18 input columns that should be used to predict an outcome class. This is a classification problem. The dataset was collected from Wikipedia.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Submissions are evaluated on <a href=\"https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class3_training.ipynb\">Multi Class Log Loss (MLogLoss)</a> between the submitted outcome and the the observed outcome from the data set.</p>\r\n<p>\\[ \\text{log loss} = -\\frac{1}{N}\\sum_{i=1}^N {( {y}_i\\log(\\hat{y}_i) + (1 - {y}_i)\\log(1 - \\hat{y}_i))} \\]</p>\r\n<h1>Submission File</h1>\r\n<p>For each Id in the test set, you must predict the value of the outcome variable. The file should contain a header and have the following format:</p>\r\n<pre>Id,class-0,class-1,class-2,class-3,class-4<br />146,1,0,0,0,0<br />147,0,1,0,0,0<br />148,0.01,0.01,0.9,0.01,0.07<br />etc.</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<!-- Begin Base Rules -->\r\n<h3>One account per participant</h3>\r\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n<h3>No private sharing outside teams</h3>\r\n<p>Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.</p>\r\n<h3>Team Mergers</h3>\r\n<p>Team mergers are not allowed in this competition.</p>\r\n<h3>Team Limits</h3>\r\n<p>There is no maximum team size.</p>\r\n<h3>Submission Limits</h3>\r\n<p>You may submit a maximum of 2 entries per day.</p>\r\n<p>You may select up to 2 final submissions for judging.</p>\r\n<h3>Competition Timeline</h3>\r\n<p>Start Date: <strong>TBA</strong></p>\r\n<p>Merger Deadline: <strong>None</strong></p>\r\n<p>Entry Deadline: <strong>None</strong></p>\r\n<p>End Date: <strong>2/1/2014 12:00 AM UTC</strong></p>\r\n<!-- End Base Rules -->\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}