# Projects

# NRL Interactive Performance Timeline

A 3D data visualisation of NRL teams across seasons 2015-2022.

# Data Science Boilerplate

A standardised project structure for doing and sharing data science work that enforces best practices.

# Spotify Playlist Recycling Plant

A tool for intelligently generating new Spotify playlists by recycling old ones.

# A.I. Fieri (Food Recommendation Engine)

This is a food pairing model and app I created using data from ~300k recipes. The recommendations are generated using Association Rule Learning.

This is a web app I use every day that acts as an extension of my brain. The human brain is ok 🙄 but there are some tasks that it struggles with (like retaining trivia in long term memory). So far I have created four modules.

# T20 Cricket Simulator

This is a model and simulation engine I built to predict the outcome of T20 cricket matches.

# Robby Robot

This is my Python implementation of the Robby Robot genetic algorithm described in Melanie Mitchell's "Complexity: A Guided Tour".

# A.I. Rowling (Harry Potter Text Generator)

This is a neural network for generating new Harry Potter content. I trained the model on the entire book series and it can now produce completely new text in the style of J.K. Rowling. It probably isn’t quite good enough to fool an attentive reader but it has captured a lot of the writing style and vocabulary of these famous books.

# Tommy Robotikis (NRL Form Model)

This is an interactive visualisation of the form of NRL teams through time. Form is calculated using a custom algorithm I created (inspired by Google's Page Rank) and updates every night.

# Tennis Model (Betfair Australian Open Datathon)

This was a data science contest run by Betfair to predict the results of the Australian Open (tennis) in 2019 using historical data. I managed to win first place ($5000 cash prize) and even beat Betfair’s internal models, which were published as benchmarks.

# Spotify Playlist Visualisations

Streaming services are fine but one thing I miss about my iPod is scrolling through my library and rediscovering songs I liked 10 years ago. These are live visualisations based on data from my giant Spotify playlist.

# Sci-Cheat

This is an exploratory data analysis python package that I developed to save time when working with new datasets. Leveraging packages such as skearn, pandas and seaborn, this tool provides quick and easy insights into tabular datasets including distributions, correlations and feature importance.