SF Python Presentation Night - Interpreting and understanding DSLs and ML models

Are you going?

35 people going


Every 2nd Wednesday of the month

Location image of event venue


On 13 March 2019, join ~180 devs at SF Python's presentation night and learn more about “Interpreting and understanding DSLs, Machine Learning, and lots more!”

Please register on Tito: https://ti.to/sf-python/march-2019-presentation-night

If you'd like to give a lightning talk at this meetup or present at future meetups, please submit your talk ideas at https://bit.ly/sfpythoncfp

Our generous sponsor Checkr will also provide pizza and drinks for this evening.


# Lightning talks
- Math Adventures with Python
- Introduction to Serverless
- Using Python to build Slack-bots at CMB
- Could Be You!

# Short Talk (~15 mins)
Explainable Machine Learning

As machine learning applications become more specialized, the models become increasingly opaque and harder to interpret. The ability to interpret “black-box” non-linear models is critical in certain fields such as finance, healthcare and self-driving technology. At Flowcast, we partner with several banks and leverage their proprietary data to build credit-risk models using machine learning which help unlock capital for small to medium businesses (SMB).

Come and learn how to interpret black-box non-linear machine learning algorithms at the prediction level using Python and Jupyter Notebook.

This talk will be also given at Strata EU (London UK).

### Speaker Bio
Eitan Anzenberg leads the data science team to execute on the development and productization of Flowcast’s AI platform. Etian has over 7+ years of experience in Data Science with a background in machine learning, applied statistics, modeling and engineering.

## Main Talk (~25 mins)
Parsing a medieval heraldic DSL (PyCon 2019 exclusive!)

Medieval European feudal families had a coat of arms for each family name. The cost of arms were generated from formulas called Blazons that were written in a medieval Domain Specific Language - the language of heraldry, which reads like a stilted lovechild of English and Latin. This is a language with a specific syntax, keywords, variables and recursion.
I am writing a parser for this medieval DSL that can automatically generate coat of arm images. I’ll explore how a parser works, the types available, and how to write an interpreter for a DSL in Python. My goal is to be able to parse a blazon into an ast and generate a coat of arms image from it.

### Speaker Bio
Chris Beacham aka Lady Red is a python backend developer, artist and maker, and is a member of Noisebridge Hackerspace

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

SF Python is run by volunteers aiming to foster the Python community in the Bay Area. Please consider making a donation to SF Python and saying a big thank you to Checkr for providing pizza, beer, and the venue for this Wednesday's meetup.

Food, drinks, and venue for this meetup is through the generosity of
Checkr. Checkr is modernizing background checks to build a fairer future by improving the understand of the past. Please consider their job opportunities(https://checkr.com/careers/?gh_src=gi63rn5r1) if you or someone you know are looking!