A project that seeks to solve the business problem: "what obligations do I have as a business buried in all my terms and conditions documents" using pre-trained Natural Language Processing (NLP) models available for Python.

A project to analyze social media Tweets relating to a bank (NAB) to get an understanding of changing sentiment over time, as well as the topics that are driving that sentiment. The application uses the Tweepy Twitter API to collect the tweets, the NLTK Natural Language Processing Toolkit to analyse the text and the Vader library to analyse sentiment.

This project utilizes publicly available data to recommend 10 similar suburbs in Australia to a given suburb. This could be useful for people trying to decide where to work, rent or buy property. It utilizes K-Means clustering from Scikit-learn to cluster venue and cultural data, the pandasdmx package to interface with the Australian Bureau of Statistics API, and the Beautiful Soup package to scrape demographic information from the web.