This repository contains code to containerize a machine learning, Python application; it uses a pre-trained sklearn
model that has been trained to predict housing prices in Boston according to several features, such as average rooms in a home and data about highway access, teacher-to-pupil ratios, and so on. You can read more about the data, which was initially taken from Kaggle, on the data source site.
app.py
serves out predictions about housing prices through API calls. This code could be extended to any pre-trained machine learning model, such as those for image recognition and data labeling.
Instructions for running the app using Docker or Kubernetes can be found below.
- Create a virtualenv and activate it
- Run
make install
to install the necessary dependencies
- Standalone:
python app.py
- Run in Docker:
./run_docker.sh
- Run in Kubernetes:
./run_kubernetes.sh
- Setup and Configure Docker locally
- Setup and Configure Kubernetes locally
- Create a Flask app in a Container
- Run via kubectl
- You can choose to run one cluster locally with Minikube