COSC 387 Project 5

COSC 387: Artificial Intelligence

Project 5
Fall 2010

Due: Thu, Dec 9 @ 10 P.M.
13 points

Using a language of your choosing, implement a version of IREP as discussed in Cohen's paper entitled Fast Effective Rule Induction. You can use only the standard libraries included with the programming language. We will talk about rule-selection heuristics in lecture.

To make the project tractable, your implementation does not need to handle numeric attributes, it does not need to prune, and it needs to work only with the 1984 Congressional Voting Record. See also the names file. I put a version of this data set in a simplified format here and on seva, which you can retrieve from the latter using the commands:

seva% cp ~maloofm/cosc387/votes.dta ./

Feel free to remove the comments and read the data set into your program, or you can hard-code the data set into your program.

To evaluate the learned rules, implement the hold-out method, which involves selecting a random set of the original examples as a training set and using the remaining examples as a testing set. It is common to select 66% or 75% of the original examples as the training set. The training set serves as input to IREP. Once the program produces a set of rules, then it evaluates the rules on the examples of the test set.

The implementation should print the rules it learns from the training examples and the accuracy of those rules on the testing set for each class.

Instructions for Electronic Submission

In the header comments of the primary file, provide the following information:

;;;;
;;;; COSC 387 Project 5
;;;; Name
;;;; E-mail Address
;;;; Platform: Windows, Linux (seva), etc.
;;;; Language: C, C++, Lisp, Python, PL/I
;;;;
;;;; In accordance with the class policies and Georgetown's Honor Code,
;;;; I certify that, with the exceptions of the course materials and those
;;;; items noted below, I have neither given nor received any assistance
;;;; on this project.
;;;;

You'll be using Blackboard to submit your assignments. Please submit only a single file. If you need to submit multiple files, submit them in a zip file or a gzipped tarball. Keep in mind that Blackboard lets you submit only once.

You must submit your project before 10 PM on the due date.

Plan B

If something goes wrong with Blackboard, then send your project as an attachment to an e-mail to me.