Skip to content

PyMC3 beginner friendly

Photo of Peadar Coyle
Hosted By
Peadar C.
PyMC3 beginner friendly

Details

Probabilistic programming are a family of programming languages where a probabilistic model can be specified, in order to do inference over unknown variables.

A common application is in financial markets, where probabilistic programming can be used to infer expected returns or risk.

The best introduction to Bayesian methods and probabilistic programming I know is this excellent book: https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers

https://secure.meetupstatic.com/photos/event/6/b/4/7/600_465207463.jpeg

PyMC3 (https://github.com/pymc-devs/pymc3) is a Python package for Bayesian statistical modeling and Probabilistic Machine Learning which focuses on advanced Markov chain Monte Carlo and variational fitting algorithms.

In this sprint we'll address PyMC3 beginner friendly issues (https://github.com/pymc-devs/pymc3/issues?q=is%3Aissue+is%3Aopen+label%3Abeginner_friendly).

If the meetup is full, or you can't attend in person, feel free to join remotely:

Gitter channel (chat) during the sprint: https://gitter.im/py-sprints/pymc3

Short videocall at 7pm: Hangouts link (https://plus.google.com/hangouts/_/calendar/Z2FyY2lhLm1hcmNAZ21haWwuY29t.55ipep9qnd33surdfrrsnhd763?authuser=0)

https://secure.meetupstatic.com/photos/event/6/b/7/c/600_465207516.jpeg

Thanks to our sponsor Zopa (https://www.zopa.com/), for making this sprint possible.

https://secure.meetupstatic.com/photos/event/6/b/8/9/600_465207529.jpeg

Please set up a development environment before the sprint:

Fork PyMC3 repository by clicking in the top right button at:

https://github.com/pymc-devs/pymc3

After it completes, run in your computer terminal.

$ git clone https://github.com/ /pymc3

$ cd pymc3

$ git remote add upstream git@github.com:pymc-devs/pymc3.git

Download and install Anaconda from: https://www.anaconda.com/download/ (http://meet.meetup.com/wf/click?upn=pEEcc35imY7Cq0tG1vyTt45mZa7RQhrDun4GaOz4VCMNBdVHxUvrij57tfKWAO-2Bq_v655q35lr747ElyfPGSUh046oGHdEMFAcxOonLu-2Fm0JZczNJBiF0HIg0yRWx4wXrsRtCeL7UDjbgHTidR-2FG30KibXFDMMquRBlsa2WlQD8VyLAAMyhY9B8kNbMuWrCkUeYo-2B4MKFWom9JYG-2BgS4cmK-2B9dnDcBNwhRBxWlpouJmyb4EIc2At0JP84vmELypxXSmvQsCWYuvGDIsuN5hrI8M-2BICEE5xWPTmpFCs3y1SeY-3D)

After restarting the terminal, run:

$ conda config --add channels conda-forge

$ conda create -n pymc3_dev

$ source activate pymc3_dev

$ pip install -r /requirements-dev.txt

Full notes on contributing to PyMC3 can be found here: https://github.com/pymc-devs/pymc3/blob/master/CONTRIBUTING.md

Suggested tickets

https://github.com/pymc-devs/pymc3/issues/2245

https://github.com/pymc-devs/pymc3/issues/2472

https://github.com/pymc-devs/pymc3/issues/2300

https://github.com/pymc-devs/pymc3/issues/2560

Photo of London Python Sprints group
London Python Sprints
See more events
Zopa
Cottons Centre, Tooley St, SE1 2QG · London