Find faults in the earth, power machine learning platforms, and more with Python
On Nov 14, join ~180 devs at SF Python's presentation night and learn more about how you can use Python to find faults in the Earth, build machine learning infrastructure, and more!
If you'd like to present a 5 mins Lightning talk or a 10-15 mins Short Talk at future meetups, please submit your talk ideas here.
Our generous sponsor Yelp will also provide pizza and drinks for this evening.
- Where's All the Development? a simple, instructive, take on a git-like VCS, Edmund Huber
- Why we choose Python/Flask to power some of the largest retailers in the world, Morgan Linton
Short talk(~10 mins + Q&A)
Finding faults with Python, Rob Sare
Rob Sare is an Earth observation and Python enthusiast who enjoys working on impactful problems involving spatial and environmental data. He is pursuing a Ph.D. at Stanford, where he uses image processing and numerical modelling techniques to investigate landscapes affected by earthquakes and other tectonic activity at regional and global scales. In his free time, he is an avid cyclist and enjoys contributing to open source projects, and has recently developed tools for classification of rivers in satellite imagery and real-time gas sensor data analysis during internships at Los Alamos National Lab and the U.S. Geological Survey.
Most people living in the Bay Area have felt an earthquake and the instrumental record gives us a real-time view of seismic activity today. However, even in areas with sparse historic data, the landscape can give us important clues to how mature or active a fault zone might be in the form of fault scarps and other earthquake-related landforms like those in the famous Olema Valley south of Point Reyes. This talk is about scarplet, a Python image processing package for detecting and measuring key attributes of these and other landforms in topographic data.
Main talk (~25 mins + Q&A)
LyftLearn - Machine Learning Infrastructure at Lyft, Narek Amirbekian
Narek is a software engineer on the Machine Learning Platform team at Lyft. Previously, he's worked at a number of data centric roles at Zendesk, 4INFO, Edmodo, and Aarki. In his spare time he enjoys biking and brewing hoppy beers.
Lyft has hundreds of machine learning models running at any given time. In the past every team had to build custom infrastructure for prototyping, training, and deploying models. Lyft learn gives data scientists and engineers at Lyft a shared environment to do all of these thing. Our tech stack is built on python flask and kubernetes.
6:00p - Check-in and mingle, with food provided by our generous sponsor!
7:05p - Welcome
7:30p - Door close
7:10p - Announcements, lightning talks and main talk
8:15p - More mingling
9:30p - Hard stop