
A Python Pygame 2D action RPG inspired by Legend of Zelda, featuring real-time combat with 5 weapons, magic spells, 4 enemy types, and character progression.
Learning game development through tutorials only teaches isolated concepts — rendering, collision, AI — without showing how they integrate into a complete game. Building a full action RPG from scratch requires understanding how game loops, entity systems, physics, rendering, and AI all work together in a real-time interactive application.
I chose to build a complete Zelda-inspired RPG as a learning project, implementing every system from scratch using Pygame. The game is structured around an object-oriented Entity system where all game objects (player, enemies, weapons, particles) share a common base class but override behavior through polymorphism. This made the codebase extensible as complexity grew.
Python with Pygame handles the game loop, rendering, and input. The Y-sort camera system renders sprites by their Y-coordinate for correct depth overlap. Enemy AI uses finite state machines with distance-based transitions between idle, patrol, chase, and attack states. The tile map system loads from TMX files for level design flexibility. Sprite animations use frame-based systems with directional variants for smooth multi-directional movement.
Completed a fully playable 2D action RPG with 5 weapons, 2 magic spells, 4 enemy types with distinct AI, an attribute upgrade system, particle effects, audio integration, and a tile-based explorable world. The project solidified my understanding of game architecture patterns, real-time rendering, and AI behavior design — fundamentals that apply beyond game development to any interactive system.

A deep learning comparative study using Simple NN, CNN, and Residual CNN architectures to classify chest X-rays as Normal or Pneumonia with TensorFlow and Keras.

A cross-language text analysis tool implementing word probability calculation with stopword filtering in Java, Python, and JavaScript for comparative study.

An information retrieval system that recommends anime and manga using TF-IDF vector similarity, query spell correction, inverted indices, and user feedback refinement.