Probabilistic Programming Primer by Peadar Coyle

Probabilistic Programming Primer

Level up your Data Science skills - Learn Probabilistic Programming


Probabilistic Programming is one of those tricky areas of Machine Learning and Applied Statistics.
In this course join Peadar Coyle a core-developer of PyMC3 as he takes you through
- What PyMC3 is for
- What MCMC is and why should I care
- How to know enough theano to not be scared by it
- How to diagnose things like model convergence and figure out if your model is good or not
- An introduction to Multi-level models or Bayesian Stats super sauce

What the course contains

If you've never used MCMC before but you know some frequentist stats and sklearn
(or similar tools) then after taking this course, which will
take you 4 days of solid work, you'll be able to build a multilevel model and model AB tests in the Bayesian way as a result, just like you might using frequentist stats or XGBoost.

Isn't it hard to learn?
I know how hard it is to understand some of the concepts, and I've 4 years of experience teaching this to over 400 Data Scientists and Engineers. So I assure you that if you can code you can learn this!
If you follow the course you will learn:
- What Probabilistic Programming is and why it matters
- What PyMC3 is and how it uses stochastic variables
- How to design, implement and debug solutions to real-world problems where uncertainty matters
- What Theano is and how to debug it (this will help you with MXNet and Tensorflow)
- A strict workflow for developing and debugging PyMC3 models based upon 2 years of research.
- Real world examples in sports analytics, policy modelling and AB testing plus lots more.

To help you get to grips with the material - we're also including a Slack group! 

To get invited all you need to do is sign up to one of the email lists on this course.

Other talks - Conferences

I've been giving talks about Bayesian Statistics to audiences around the world for a few years now. 

This is one on Probabilisitic Programming that's worth a look it was to a packed audience in London.
Click here


Peadar has been producing insightful and useful educational material on Data Science and Bayesian Stats for years.
Alejandro Correra Bahnsen - Data Science Research VP

What's included?

Video Icon 29 videos File Icon 14 files Text Icon 1 text file


An Introduction to Probabilistic Programming
29 mins
A modern Bayesian Workflow.pdf
1.33 MB
Slack Channel Link
Hands on introduction to PyMC3
How do I install PyMC3?
How do I do Bayesian AB Testing? - Probabilistic Programming Primer -
Probabilistic Programming Primer: Bayesian Changepoint Detection
184 KB
Case Study 1- Bayesian_Changepoint_Detection.ipynb
194 KB
How to build a Logistic Regression model the Bayesian way
10 mins
What is PyMC3 and how do I get started?
1. Introduction to PyMC3.ipynb
305 KB
64 KB
ppp_intro_to_pymc3_2 Edited.mp4
2 mins
ppp_intro_to_pymc3_1 Edited.mp4
5 mins
ppp_intro_to_pymc3_3 Edited.mp4
9 mins
ppp_intro_to_pymc3_4 Edited.mp4
7 mins
ppp_intro_to_pymc3_5 Edited.mp4
10 mins
What is MCMC?
2. Markov Chain Monte Carlo.ipynb
23.1 KB
ppp_mcmc_1 Edited.mp4
5 mins
ppp_mcmc_2 Edited.mp4
8 mins
ppp_mcmc_3 Edited.mp4
7 mins
ppp_mcmc_4 Edited.mp4
5 mins
ppp_mcmc_5 Edited.mp4
7 mins
ppp_mcmc_6 Edited.mp4
4 mins
Introduction to Theano
3. Theano.ipynb
403 KB
ppp_intro_to_theano_1 Edited.mp4
7 mins
ppp_intro_to_theano_2 Edited.mp4
7 mins
ppp_intro_to_theano_3 Edited.mp4
7 mins
ppp_intro_to_theano_4 Edited.mp4
8 mins
ppp_intro_to_theano_5 Edited.mp4
5 mins
Hierarchical Models (Multilevel models)
7 mins
12 mins
3 mins
19 mins
Model building with PyMC3
Model Building with PyMC3.ipynb
310 KB
ppp_model_building_1 Edited.mp4
9 mins
ppp_model_building_2 Edited.mp4
10 mins
ppp_model_building_3 Edited.mp4
9 mins
ppp_model_building_4 Edited.mp4
16 mins
Other Probabilistic Programming Languages and Tools
17 mins
14 mins
15 mins


What is the target audience with this course?

My target audience is people with some statistics background or machine learning background. If you know some Python (or another suitable language like Scala, R, Java) and some Machine Learning you should be fine. 

My aim is to present things in a 'hacker' friendly way. 

What applications in the real world are there for Probabilistic Programming?

In my own career I've applied Bayesian Statistics (Probabilistic Programming) in Marketing, Financial Services, Sports Analytics and Energy markets.

Some use cases I can imagine my audience being interested in 
  • Modelling risk of financial or insurance products
  • Anomaly detection in time series data - this could be for fraud, identity modelling, overloads in systems, manufacturing, causal models in marketing.
  • Modelling the safety of self driving cars (which has applications in many policy use cases)
  • Sports Analytics
  • Modelling the inherent uncertainty in any measurement process - for example in a two sided recruitment market you might have scores assigned by job seekers to companies and by companies to job seekers

In summary - anywhere that uncertainty matters to you, or you have domain specific expertise that can be part of the modelling process could be amenable to Bayesian Statistics. 

How many hours of video is in this course?

There's over 3 and half hours of video in this course.

Including the first ever screencasts of new tools such as Arviz and Rainier in any course.

Do you have a github? Or use Binder?

Yes! You can either use Binder or download the code and install it from Github.

If you want less hassle - use Binder.

Why should I buy this course over a book?

While I agree you can learn from some of the excellent books out there. This showcases me talking through different examples, which is much like pair programming. It's based on real-life experience of teaching this to over 400 Data Scientists, and you won't find material like this anywhere else. I think screencasts are an excellent way to level up your skills. 

Does this course have an expiry date?

No, the price gets you lifetime access to the course, especially as I add more content. It's a one-time-fee. 

How much will this course cost?

The course will be fixed price cost for 150 GBP - that'll include several hours of videos, notebooks and all other content we add to this product over the lifetime of the product. 

Alternatively you can pay 5 payments of 35 GBP - the extra cost being because I want to incentivise people to pay up front. 

Will there be course support?

There is a Slack community and you get to join an exclusive network consisting of other Bayesian Statisticians. 

Is there a money back guarantee?

We'll offer 60 day money back guarantee under the provision that you show some evidence of attempting some of the homework exercises. 

Just email me and we'll sort out a refund. 

Can I get an invoice for work?

Often customers want to use company training budget to pay. If you pay upfront, you can get an invoice from the billing page in your dashboard, which you can then expense back to your employer.

What are good other courses and other books for learning Bayesian thinking

You may get more out of this course if you've looked at Fundamentals of Bayesian Data Analysis, and I've done my best to add in introductory material.

Other good books include Statistical Rethinking

Build better, interpretable models and incorporate domain knowledge

Learn how to enhance your modelling abilities and better communicate risk.