This project operationalizes a Machine Learning Microservice API.
Given 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. This project could be extended to any pre-trained machine learning model, such as those for image recognition and data labeling.
The following tasks were performed:
- Test project code using linting
- Complete Dockerfile to containerize the application
- Deploy the containerized application using Docker and make a prediction
- Improve the log statements in the source code
- Configure Kubernetes and create a Kubernetes cluster
- Deploy a container using Kubernetes and make a prediction
- Upload a complete Github repo with CircleCI to indicate that your code has been tested
- run python app.py
- run ./run_docker.sh
- run ./make_prediction.sh
- run ./upload_docker.sh
- run ./run_kubernetes.sh
- run ./make_prediction.sh
- .circleci: For the CircleCI build server
- model_data : this folder contains the pretrained
sklearnmodel and housing csv files - output_txt_files: folder contains sample output logs from running
./run_docker.shand./run_kubernetes.sh - app.py : contains the flask app
- Dockerfile: contains instructions to containerize the application
- Makefile : contains instructions for environment setup and lint tests
- requirements.txt: list of required dependencies
- run_docker.sh: bash script to build Docker image and run the application in a Docker container
- upload_docker.sh: bash script to upload the built Docker image to Dockerhub
- run_kubernetes.sh: bash script to run the application in a Kubernetes cluster
- make_prediction.sh: bash script to make predictions against the Docker container and k8s cluster
- README.md: this README file