Can I safely combine my local personal data with a public large language model to understand my texting behaviour? A project combining natural language and generative AI models to explore my private data without sharing (too much of) my personal life with the robots. ✍️ A blog about exploratory data…

Generative AI (GenAI) is a type of Artificial Intelligence that can create a wide variety of images, video and text. To accelerate the robot uprising I chained two GenAI models together to build a camera which describes the current scene in words, and then uses a second model to create…

Fitbit activity analysis with DuckDB — Wearable fitness trackers have become an integral part of our lives, collecting and tracking data about our daily activities, sleep patterns, location, heart rate, and much more. I’ve been using a Fitbit device for 6 years to monitor my health. However, I have always found the data analysis capabilities lacking…

Exploratory data analysis of user activity, server popularity, and language usage on Mastodon — Mastodon is a decentralized social networking platform. Users are members of a specific Mastodon instance, and servers are capable of joining other servers to form a federated social network. I wanted to start exploring Mastodon usage, and perform exploratory data analysis of user activity, server popularity and language usage. I…

Wildlife monitoring is critical for keeping track of population changes of vulnerable animals. As part of the Confluent Hackathon ʼ22, I was inspired to investigate if a streaming platform could help with tracking animal movement patterns. …

A cat prediction model using past behaviour and weather observations — With months of historic location and temperature data captured, this blog covers how to train a machine learning (ML) model to predict where my cat would go throughout her day. For the impatient, you can skip directly to the prediction web-app here. Does past cat behaviour predict future sleeping location? With some inexpensive hardware (and a cat ambivalent…

It’s 9am on a rainy Tuesday morning — can a simple ML model predict where my cat will be sleeping? How I used a bluetooth tracker, a dozen microcontrollers plus a bit of Python to predict where Snowy the cat would be napping in the next hour. Summary With some inexpensive…

Collecting streaming data is easy — but understanding it is much harder! With months of 🐱 weight data captured I discovered sensor data can be very messy⚡. …

Our cat Snowy 😸 has been enjoying her meals over winter. I wanted to start collecting data on her eating habits, and analyse her weight over time. This data is collected with food and cat weight measurements; alongside phots taken by two cameras. Data is collected and images processed locally…