This repository contains the skeleton code and dataset files that you need in order to complete the coursework.

The data/ directory contains the character datasets:

The primary datasets are:

• train_full.txt
• train_sub.txt
• train_noisy.txt
• validation.txt

Some simpler datasets that you may use to help you with implementation or debugging:

• toy.txt
• simple1.txt
• simple2.txt

The official test set is test.txt.

• classification.py

  • Contains the code DecisionTreeClassifier class.

• eval.py

  • Contains the code for the Evaluator class.

• main.py

  • Contains the implementation of the classes in classification.py and eval.py

• pruning.py

  • Contains the code to prune decision tree