{
  "fetched_at": "2026-10-20T10:17:51Z",
  "source_url": "https://www.kaggle.com/competitions/cs5644/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n  * train.csv -- training file to learn from description below\n  * test_set.csv -- contains a set of features that you must predict and submit to the leaderboard\n  * sample_solutions.csv -- a sample submission that represents random guesses for the answers to test_test, you may use this to check to see if your file conforms to the format required for submission\n\n## Data Description\nThis applies to both the train and test_set files.  The only thing different about the test_test file is that it does not contain the target column.  Your job is of course to predict what the target column should say in the test file_set.csv file.\n\n * no name -- row identifier column\n * target -- column containing the data you must predict\n * a -- integer column representing a series of categories\n * b -- boolean column\n * c --  integer valued column, contains missing values\n * d -- integer valued column\n * e -- integer valued column\n * f -- positive float value column\n * g -- categorical column, single letter names\n * h -- categorical column, single letter names, contains missing values",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Extra Credit Competition\n\n Welcome to the extra credit \"competition\" for CS5644.  Your job should you choose to accept it is to take the supplied data set and try to earn the top score.\n\n## Data set \n\nThe data comes from a common example test set but has been 'anonymized' somewhat so as not to giveaway it's origin or the answers.  After the end of the competition I will point you to the original data set.\n\n## Example notebook\n\nYou can find an example notebook that makes a baseline model based on one of our first models that we learned about:  Decision Tree.  It also provides some simple code to make use of scikit-learn pipelines to perform basic imputation and one hot encoding.  There are some new and somewhat advanced techniques in there that you can read about in the documentation or get some more information in the pipeline module on the course website.\n\n## Submitting for a grade and Grading\n\nPlease see the canvas website for more information on how to submit for a grade your scores on the leaderboard.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is  Categorization Accurcacy\n\n<h2>Submission Format</h2>\n<p><strong>For every row in the dataset</strong>, submission files should contain two columns: Id and Predicted. Your job, for each row, is to predict 0 or 1 based upon the features in the test dataset.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>Id,Predicted<br>1,1<br>1,0<br>1,1<br>...\n</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat! (i.e. try to figure out what the dataset is or share work)\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}