Website that takes in user inputted tokens, performs a lookup for their corresponding embedding, performs PCA, and renders back the main components and their closest descriptions to the front-end. Intended to be used as a tool to introduce natural language embeddings to MBA students in MBA 261 (Graduate Marketing Research).

See the README of the Github repo for more details.

The first project of my first CS class at Berkeley was to write the logic for a modified version of the dice game Hog. The game itself is pretty simple (roll die to score points, first to 100 wins), and the project was more a less just a warm-up to get everyone used to Python syntax and higher order functions. The extra credit option, however, was a bit more interesting.

This project consisted of three main parts:

• Rasterize map tiles of backend and serve to the front end
• Modify an XML parser to convert OpenStreetMap data for the city of Berkeley into appropriate data structures on the backend
• Implement A* search to provide navigation directions

Source | Specification

Tools for developing optimal strategies for the game of Hog when complete information is available, and for approximating solutions when there is incomplete information. Includes visualization tools to watch strategies evolve between iterations. More details in this post