From Lab to Factory

Lessons learned developing Data Products


Keynote PyCon Colombia

Feb 2017

peadarcoyle@googlemail.com


All opinions my own


Who am I?


  • Data Scientist at Elevate (Recruitment Startup) and Author
  • @springcoil
  • About 5 years in Machine Learning/Data Science
  • OSS contributor (mostly PyMC3)
  • Built Ad-hoc analysis, Data Products and Data Pipelines at


Why talk about this?

 

Data Moats 


Roadmap

  • What is Data Science?

  • Type of Data Scientists

  • Deploying Data Science (tech/culture)

  • Success stories and recommendations

  • Bigger idea (Change)

What IS a Data Scientist?

 




There's a Data Science Spectrum


HT: Sean J. Taylor (Facebook Research Scientist)

Data Science to Value

  • Data doesn't do anything!



  • People need to make decisions (strategic/ tactical)



  • Or the product needs to alter someones decision making (Spotify Discover Weekly, Amazon Recommendations, etc)


(Taken from Josh Wills talk - Lab to Factory 2014)
or https://hbr.org/2013/04/two-departments-for-data-succe


 Expectations and reality






 

Data is the new oil...

But. Data isn't a product. It needs to be turned into one!


Data Science is hard




  • Data and technical problems

  • Skill set (emotional and tech)

  • Machine Learning Ops

Data Science projects are risky!


Many stakeholders think that data science is just an engineering problem, but research is high risk and high reward



De-risking the project - how? Send me examples :) 




Success with Data Science



1. People

2. Ideas

3. Things


Source: USAF







R and D needs cultural support


Your culture needs to avoid the HiPPO (highest paid persons opinion) to be data-informed or data-driven. 

Good cultures

  • Data democratization


  • Clear objectives and metrics against objectives


  • Financial metrics don't always win - sometimes brand wins


  • See http://bit.ly/cultureanddata by Martin Goodson


Some data scientists do experiments and build prototypes


Production  





(HT: The Yhat people - www.yhathq.com

Deploying Data Products is hard


  • Monitoring and Alerting

  • Deployment 

  • Real world data is tricky (training/ testing)

  • Interpretability (explaining fraud detection/ad tech)

  • Feature engineering

  • Models decay over time

What projects work?


  • Explain existing data (visualization!)

  • Automate repetitive/ slow processes

  • Augment data to make new data (Search engines, ML models)

  • Predict the future (do something more accurately than gut feel )

  • Simulate using statistics :) (Sports analytics models) 

"You need data first" - Peadar Coyle

  • Copying and pasting PDF/PNG data 
  • Getting data in some areas is hard!!
  • Some tools for web data extraction
  • Messy APIs without documentation :(
                               

Visualise ALL THE THINGS!!

  • (Relay foods dataset - HT Greg Reda)
  • Consumer behaviour at a Fast Food Restaurant per year in the USA


 


 

Augmenting data and using API's


 


 Machine Learning

Production data/ Real world

HT: Andrew Ng

Everyone ETLS

  • Only 1% of your time will be spent modelling
  • Data pipelines and your infrastructure matters - Eoin Brazil Talk
  • Tools such as Spark, Luigi, Airflow or Dask are important
  • Monitoring of pipelines. Scalability. Machine provision
    


Success Story (1)

  1. Ad Tech project (Media company) -
    original process took 10 hours per week of analyst time.

  2. Broke down process and produced simple predictive model

  3. Data type challenges (unicode in Python 2.7) and business expectations

  4. Now takes less than 30 minutes each week.                               

                               

Success Story (2)

  • Elevate is a Total Talent Management platform (tools for streamlining recruitment)

  • Several models in production - microservices (recommenders, job type prediction)

  • Data pipeline (Luigi) necessary for producing features

  • Lots of challenges about Docker, time, updated data.

  • Works: MyPy (Python 3.5), code review, testing - http://hypothesis.works/

  • Next: Moving to PySpark for ETL, more pair programming

Failure


1. Lack of support from tech teams


2. Lack of clearly defined customer


3. No culture of DevOps


4. Management had no clear vision

Lessons learned from Lab to Factory


1. Monitoring - data products need evaluation in production

2. Lack of a shared language between software engineers and data scientists. Pair programming/ Code review are some solutions.

3. To help data scientists and analysts succeed your business needs to be prepared to invest in tooling. (Pipelines, DevOps, Reproducible)

4. Often you're working with other teams who use different languages - so micro services can be a good idea (example C#.net app and Python microservice)

How to deploy a model?

  • Palladium (Otto Group)
  • Azure
  • Flask Microservice (DIY) and Docker


         


 Dev Ops



We need each other!





Use small data where possible!!

  • Small problems with clean data are more important - (Ian Ozsvald)
  • Amazon machine with many Xeons and 244GB of RAM is less than 3 euros per hour. - (Ian Ozsvald) 
  • Blaze, Xray, Dask, Ibis, etc etc - PyData Bikeshed
  • "The mean size of a cluster will remain 1" - Matt Rocklin    

Focus on the real problem


Closing remarks

  • Dirty data stops projects


  • Change happens, we need to help businesses adapt or be agile


  • There are some good projects like Icy, Luigi, etc for transforming data and improving data extraction


  • http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf - Google paper on rule for building ML systems

Closing Remarks (2)

A New World



Simulate: Rugby games with MCMC

(PyMC3) 


What is the Data Science process?


Obtain

Scrub

Explore

Model

Interpret

Communicate (or Deploy)


Some NLP on the Interviews!


What do Data Scientists talk about?

Based on my Dataconomy Interview series!

A famous 'data product' - Recommendation engines


Credits



From Lab to Factory - Deploying Data Science

By springcoil

From Lab to Factory - Deploying Data Science

The last mile problem of data science going from data to value.

  • 4,108