Operationalized a fault tolerant machine learning microservice API using AWS and Kubernetes.
Deployed a containerized Python/Flask application to serve out predictions (inference) about housing prices through API calls. My Flask microservice uses a a pre-trained, sklearn model that has been trained to predict housing prices in Boston according to several features.
Deployed my Kubernetes cluster, configured my Kubernetes autoscale and load tested my Kubernetes application.
AWS Lambda, Docker, Flask, Kubernetes (Container Orchestration), NumPy, Pandas, PyLint, Python, Scikit-Learn.
Create a virtualenv and activate it python3 -m venv <your_venv> source <your_venv>/bin/activate
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 Flask app in Container
- Run via kubectl