While this article is a nice read, and provides what may be useful tips, "guide to deploy" feels misleading. I thought it was going to be a guide on deploying ML to production.
Where would I find such an article, something that explains how I might go from
"I've got a Jupyter notebook that gives me results I like"
to
'I'm running those calculations in a production system'?
Take a look at Google's "Best Practices for ML Engineering" [1] and "Machine Learning: The High Interest Credit Card of Technical Debt" [2]. They are not tutorials, but cover a number of interesting topics related to deployment of machine learning models to production.
7 comments
[ 1.3 ms ] story [ 27.5 ms ] thread[1] https://news.ycombinator.com/item?id=13414776
[2] https://news.ycombinator.com/item?id=10338575
1. pip install scikit-learn
2. call model inside flask request
3. docker build && docker push
Joking aside, following articles are good: http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf https://research.google.com/pubs/pub43146.html