Skip to content

Latest commit

 

History

History
32 lines (27 loc) · 866 Bytes

README.md

File metadata and controls

32 lines (27 loc) · 866 Bytes
Raw

ML in prod

A python predictive system design.

Article: https://medium.com/contentsquare-engineering-blog/machine-learning-in-production-c53b43283ab1

Building the pipeline

$ cd training
$ python3 -m venv venv
$ source venv/bin/activate
$ pip install -r requirements.txt
$ python training.py

Running the server

  • If you did the previous steps then:
$ cd ../; deactivate
$ cd server
$ python3 -m venv venv
$ source venv/bin/activate
$ pip install -r requirements.txt
$ python run_server.py

Making online predictions

Once the server is up and running you can send features via POST requests and then receive the corresponding prediction (0 or 1). You can find an example of the request body in server/post.json:

$ curl -H "Content-Type: application/json" -X POST --data @post.json http://localhost:5000/predict