This is a Python flask app that serves out predictions (inference) about housing prices in Boston through API calls.

The app 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. The data was initially taken from Kaggle, on the data source site.

1. Open a terminal and clone the project repository, then navigate to the project folder.

git clone https://github.com/softveda/udacity-microservices.git
cd udacity-microservices/project-ml-microservice-kubernetes

2. Create (and activate) a new virtual environment with Python

make setup

3. Install dependencies

make install

4. Run the app

 python3 app.py

This should write some logs to terminal like

* Serving Flask app "app" (lazy loading)
 * Environment: production
   WARNING: Do not use the development server in a production environment.
   Use a production WSGI server instead.
 * Debug mode: on
 * Running on http://0.0.0.0:8000/ (Press CTRL+C to quit)
 * Restarting with stat
 * Debugger is active!
 * Debugger PIN: 202-879-013

Note: You have to change the hosting port of the app from 80 to 8000

5. Make a prediction
   Open another terminal and run

./make_prediction.sh

This should log the Prediction value returned from the app

Port: 8000
{
  "prediction": [
    20.35373177134412
  ]
}

• Makefile - This is Makefile that has the setup and installation tasks that can be run using the make utility
• requirments.txt - This is the list of dependencies (Python libraies) that are isntalled using the pip utility
• app.py - This is the Python Flask web application
• Dockerfile - This is thr docker build file to containerize the app inside Docker
• Shell scripts
  • run_docker.sh - This script will build the Docker image of the app and run the app inside the container
  • upload_docker.sh - This script upload the Docker image to Docker hub repository
  • run_kubernetes.sh - This script deploys the Docker image to a Kubernetes cluster and runs the app in pods.