/Binary-Decision-Trees

Implementation of a Binary Decision Tree (DT) classification algorithm as part of the Introduction to Machine Learning (COMP90049) course at The University of Melbourne.

Primary LanguageJupyter Notebook

Decision Tree Classification for National Flags

This repository contains the implementation of a binary Decision Tree (DT) classification algorithm as part of the Introduction to Machine Learning (COMP90049) course at The University of Melbourne. The purpose is to predict the predominant color of national flags using a diverse set of features, including country features such as language, population, and other structural properties. The dataset used is a modified version of the Flags dataset from the UCI Machine Learning repository.

Project Structure

  • DT.ipynb: Jupyter Notebook containing the code for the Decision Tree implementation and analysis.
  • flags.data.csv: Dataset file containing 194 instances, one line per instance, with 25 features. The last column specifies the predominant color of each flag.
  • flag.names: Information about different features and the possible range of values in the flag dataset.

Getting Started

  1. Clone this repository to your local machine:
git clone https://github.com/KIAND-glitch/Binary-Decision-Trees.git