Deploying Machine Learning Models to Production

Nawfal Tachfine

Data Scientist

Typical Data Science Workflow



get data

build and clean dataset

study dataset

train model

+ feature selection

+ algorithm selection

+ hyperparameter optimization

Then what?

Enter Industrialization...

goal = "automatically serve predictions to any given information system"

philosophy = "start from final use case and work your way back to data-prep"

potential_constraints = [








The Data Dependency Problem

Design Patterns

  • Think about your production use-case as early as possible.

  • Your data pre-processing pipelines must be deterministic and reproduce the same conditions as in training.
    • make your transformations robust against abnormal values
    • variable order matters (cf. scikit-learn)
  • Log as much as you can.
  • Write clean code: your models will evolve (re-training, new features, ... etc)
  • Keep things simple: stability trumps complexity.

Building a Prediction API

  • Web app framework: Flask
    • simple,
    • lightweight,
    • powerful

This approach is  based on serialization and can be used for models trained with librairies other than scikit-learn.

@app.route('/api/v1.0/aballone', methods=['POST'])

def index():
    query = request.get_json()['inputs']
    data = prepare(query)
    output = model.predict(data)
    return jsonify({'outputs': output})

if __name__ == '__main__':'')


Building a Prediction API

  • I/O: JSON
    • universal support
  • Virtualization: Docker
    • no more dependency problems,
    • run (almost) anywhere
  • Deployment: AWS Elastic Beanstalk
    • ​(very) easy to use,
    • (relatively) cheap,
    • provides auto-scaling and load-balancing.


Demo Time!

Deploying Machine Learning Models to Production - PyParis 2017

By Nawfal Tachfine

Deploying Machine Learning Models to Production - PyParis 2017

  • 3,762