We are happy to announce the 23nd PyData Cambridge meetup!

IMPORTANT

Due to COVID-19 social distancing measures, this edition will be hosted online using the Zoom platform.

==> meetup link (typo in original link!): https://zoom.us/j/98082584157?pwd=REpORlFOYXhpa0ZqY3p0bXhtRVBnZz09 <==

Agenda

19:00 - Introduction
19:15 - "Using deep learning to count albatrosses from space" -- Ellie Bowler
19:45 - "From Jupyter notebooks to production code, a Kedro introduction" -- Lais Carvalho
20:15 - End

Code of Conduct

PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form.

The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen (leah@numfocus.org) or organizers.

Talks

Title: Using deep learning to count albatrosses from space
Speaker: Ellie Bowler

Abstract: Wandering Albatrosses have seen dramatic declines in recent decades, leading to concern over their conservation. However due to their highly dispersed and inaccessible nesting locations, population surveys are expensive, infrequent, and often incomplete. In this work we address this issue by counting albatrosses directly from space, using 31-cm resolution WorldView-3 satellite imagery. We particularly focus on manual and automated methods for detecting the birds, and investigate how observer uncertainty in ground truth labels can impact supervised CNN training schemes.

Bio: Ellie Bowler is a PhD student under the supervision of Michal Mackiewicz at the University of East Anglia. Her background is in mathematics and computational ecology, with a particular interest in computer vision and deep learning. Her current research is on automated UAV and satellite image analysis for wildlife monitoring, working in collaboration with Peter Fretwell at the British Antarctic Survey.

Title: From Jupyter notebooks to production code, a Kedro introduction
Speaker: Lais Carvalho

Kedro is an open-source Python library that helps data scientists write data pipelines following software engineering best practices from the start. Since our last visit to PyData Cambridge, we released several new features. In this talk, I will walk through some of those features and show you how to convert your Jupyter notebooks to a Kedro project, allowing you to scale your project and collaborate effectively on a team. Come and say hello. 😊

Bio: Lais Carvalho is a developer advocate for QuantumBlack. IT student, her background is on civil & env. engineering and customer service. Board member of Python Ireland, Laís was part of the organisation of EuroPython 2020 and hosted the PyData Dublin Summer edition of same year.