Duration:
100 hours
 
Project Overview
In this project, you’ll build and deploy a machine learning model using a simple dataset. The project emphasizes deployment skills, covering the entire ML lifecycle from model training to API development, CI/CD, and cloud deployment on Azure.
 
Key Learning Outcomes
Experiment Tracking with MLflow: Track experiments, visualize results, and centrally store models.
API Development with FastAPI: Build a RESTful API for real-time predictions from your model.
CI/CD Automation: Automate deployment with GitHub Actions, using Git for version control.
Cloud Deployment on Azure: Deploy your API to Azure Web App, creating a scalable, accessible solution.
User Interface Integration: Develop an interactive front end with Streamlit to connect users to your API.
Presentation Skills: Prepare and defend your project, focusing on model selection and feature importance.
 
Tools & Technologies
Programming Language: Python
Libraries: scikit-learn, pandas, numpy, MLflow, FastAPI, Streamlit
Cloud Platform: Azure Web App
Deployment & CI/CD: Docker, Git, GitHub Actions
 
Deliverables
Cloud-Hosted API: A production-ready, accessible API that returns predictions in real time.
Source Code: Well-documented Python scripts for model training, API, and deployment.
Deployment Workflow: CI/CD pipeline with GitHub Actions and a Dockerized application.
Interactive Front End: A user interface built with Streamlit for real-time interactions.
 
Who Should Enroll
Data scientists and machine learning enthusiasts wanting to gain practical deployment experience.
Developers interested in expanding their skills with machine learning APIs and cloud platforms.
Professionals aiming to master CI/CD workflows for ML in production environments.
 
Why This Project?
This project provides a hands-on introduction to the deployment side of machine learning, allowing you to create a real-world application with Azure and FastAPI. It's ideal for those looking to build end-to-end ML projects and gain confidence in handling the deployment process.