Jay Qi
Jay Qi is a lead data scientist at DrivenData where he helps mission-driven organizations and institutions leverage machine learning, data science, and data engineering for social impact. He has worked on applying machine learning to a wide range of scientific contexts, including hydrological modeling, spacecraft dynamics, and wildlife conservation. Before DrivenData, Jay modeled failures of industrial machines using sensor data at Uptake, and he has a background in aerospace engineering and computational fluid dynamics. Jay is also an active open source software maintainer and contributor, working on projects including cookiecutter-data-science, cloudpathlib, and erdantic.
Sessions
Camera traps are an essential tool for wildlife research. Zamba is an open source Python package that leverages machine learning and computer vision to automate time-intensive processing tasks for wildlife camera trap data. This talk will dive into Zamba's capabilities and key factors that influenced its design and development. Topics will include the importance of code-free custom model training, Zamba’s origins in an open machine learning competition, and the technical challenges of processing video data. Attendees will walk away with a better understanding of how machine learning and Python tools can support conservation efforts.
When sharing code for any reason—whether for teaching, documentation, asking for help, or reporting a bug—you will more likely be successful if your code example is easy to run and reproducible. reprexlite is a lightweight yet flexible tool to make it as easy as possible to create a Python "reprex", a reproducible code example with expected outputs that can be pasted and immediately reproducibly run. This poster will show the different ways you can easily use reprexlite and will share about its design philosophy. Attendees will walk away knowing about a simple new tool that will make it easy for them to share reproducible Python code examples.