[CentralOH] June talk needed

[Jeff Klukas]

Hi Eric - I had a talk accepted for PyOhio, and it would be good discipline
for me to get prepped by presenting for COhPy and gathering feedback.

I hope you get a wealth of other options for the June meeting as well, so
no worries if we're not able to make this one fit.

Title: Machine learning in production with scikit-learn

Short description: The Python data ecosystem provides amazing tools to
quickly get up and running with machine learning models, but the path to
stably serving them in production is not so clear. We'll discuss details of
wrapping a minimal REST API around scikit-learn, training and persisting
models in batch, and logging decisions, then compare to some other common
approaches to productionizing models.


Long description:

We'll be discussing Simple's implementation of a Python microservice for
classifying incoming chat messages by subject category, enabling our
customer relations agents to develop specializations and onboard more
quickly.

We'll walk through a bit of the code for our model and what the interface
looks like in scikit-learn for training a model, persisting it to disk, and
requesting a prediction.

Once we understand the shape of interacting with scikit-learn, we'll take a
look at wrapping it in a Flask app and the concerns about understanding how
that application is behaving in production. This includes performance
metrics, logging results to a database, and degrading gracefully when
things go wrong.

We'll then switch gears to talk about all the work that needs to happen
outside of the application itself. We use a separate framework to execute
scheduled jobs, periodically retraining the model on new records in our
data warehouse or testing out a new iteration of the model code. We
evaluate the performance of the models based on historical data, and then
update the model running in production when we find a better-performing
configuration.

Finally, we'll discuss how other companies approach the problem of serving
predictive models in production. Varying concerns around performance needs,
security constraints, and technical expertise can vastly change the shape
of the solution.


|| Jeff Klukas
|| http://jeff.klukas.net

On Tue, Jun 6, 2017 at 9:03 PM, Eric Floehr <eric at intellovations.com> wrote:

> PyOhio talk acceptances have gone out.
>
>
> If your talk got accepted, the June COhPy meeting would be the perfect
> place to practice it! Please let me know soon!
>
>
> If your talk was not accepted, COhPy is STILL a perfect place to give
> it... it'll give you a chance to practice, get feedback, and then submit
> your talk proposal to another conference (or PyOhio next year!). We have
> openings the rest of the year!
>
>
> Please let me know... COhPy only is valuable when people contribute.
>
> Thanks!
> Eric
>
>
> _______________________________________________
> CentralOH mailing list
> CentralOH at python.org
> https://mail.python.org/mailman/listinfo/centraloh
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/centraloh/attachments/20170606/13973725/attachment.html>