This is the final project for CS-5950 Machine Learning. The goal is to use various machine learning techniques to build a mushroom edibility classifier. To do this we are using UCI's 'mushroom' data set which contains 8124 specific mushroom instances each of which has 22 identifying attributes. Each instance is labelled as edible or not-edible.

The project requirements are:

* Use some form of Data Partitioning to perform cross-validation
  on the data.

* Use some form of boosting/bootstrapping to reduce variance

* Generate one Decision Tree type classifier for the data.

* Generate one alternate classifier type for the data.

* Produce a report detailing the results and specifically 
  comparing and contrasting the two methods used for building
  the models.

Group Members:

* Colin Maccreery
* Benjamin Mechling
* Christopher Carlson

Honorary Members:

* James Jenkins