Flask template to productionize Machine learning models

Screenshot

Required python version

$ python --version
Python 3.5.5

Flask Library

Steps to setup

$ git clone https://<your-user-id>@bitbucket.org/productionize-ml-model.git

Create new virtual env using anaconda

$ conda create --name <proj_name35> python=3.5

Activate virtual env

$ source activate <proj_name35>

Model

Model link: https://1drv.ms/u/s!ArDo8DV9hhHCgTL-SFawrYAmU_DT?e=1TZYw6

Install libraries

$ pip install -r requirements.txt

Run the REST api in local with debug level

$ cd productionize-ml-model/
$ python app_server.py --debug

Run API in production mode

$ gunicorn --bind 0.0.0.0:5000 wsgi:application -w 1

Digitalocean has very good tutorial on deploying this to nginx, gunicorn so that it accepts multiple requests

https://www.digitalocean.com/community/tutorials/how-to-serve-flask-applications-with-gunicorn-and-nginx-on-ubuntu-16-04