https://github.com/arseniistratiuk/decision-tree-classifier-lab

A student lab project focused on tree algorithms and a Decision Tree classifier.
https://github.com/arseniistratiuk/decision-tree-classifier-lab

bellman-ford decision-tree-classifier floyd-warshall graph-algorithms kruskal-algorithm machine-learning networkx prim-algorithm scikit-learn

Last synced: 1 day ago
JSON representation

A student lab project focused on tree algorithms and a Decision Tree classifier.

• Host: GitHub
• URL: https://github.com/arseniistratiuk/decision-tree-classifier-lab
• Owner: ArseniiStratiuk
• License: mit
• Created: 2025-02-04T10:45:42.000Z (7 days ago)
• Default Branch: main
• Last Pushed: 2025-02-04T15:28:33.000Z (7 days ago)
• Last Synced: 2025-02-04T16:29:41.786Z (7 days ago)
• Topics: bellman-ford, decision-tree-classifier, floyd-warshall, graph-algorithms, kruskal-algorithm, machine-learning, networkx, prim-algorithm, scikit-learn
• Language: Jupyter Notebook
• Homepage:
• Size: 576 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Tree Algorithms and Decision Tree Classifier Lab

## Overview

**Team 5, Arsenii Stratiuk, Viktor Syrotiuk**

This repository contains a student lab project focused on implementing and analyzing fundamental tree algorithms and a Decision Tree classifier. The project is divided into two main tasks:

1. **Task 1: Graph Algorithm Analysis**  

   - Implementation and comparison of **Kruskal's** and **Prim's** algorithms for Minimum Spanning Trees (MST).  

   - Analysis of **Bellman-Ford** and **Floyd-Warshall** algorithms for shortest path detection in graphs.  

   - Time complexity measurements and performance plots for varying graph sizes.

2. **Task 2: Decision Tree Classifier**  

   - A custom Decision Tree classifier built from scratch using Gini impurity.  

   - Validation on the Iris dataset, with comparisons to scikit-learn's implementation.  

   - Visualization of tree structures and accuracy evaluation.

## Features

- Random graph generation with adjustable completeness and weights.  

- MST algorithms (Kruskal/Prim) and shortest path algorithms (Bellman-Ford/Floyd-Warshall).  

- Decision Tree classifier with training, prediction, and evaluation.  

- Integration with `networkx`, `scikit-learn`, and `graphviz` for visualization.