Duration:
60 hours
 
Project Overview:
Master the complete deployment lifecycle by building an interactive dashboard with Streamlit, powered by a machine learning API deployed on Azure. In this project, you will create a dashboard that allows users to classify iris flower species based on input characteristics, utilizing a pre-deployed FastAPI model to deliver real-time predictions.
 
Key Learning Outcomes:
API Integration: Connect your Streamlit dashboard to an API deployed on Azure for live predictions.
Streamlit Development: Design a responsive, user-friendly dashboard with Streamlit, featuring both data visualization and interactive prediction capabilities.
Experiment Tracking and Model Deployment: Track model experiments with MLflow, and deploy the API to Azure.
Continuous Integration & Deployment (CI/CD): Use GitHub Actions for streamlined version control and automated deployment.
 
Tools & Libraries:
Programming Language: Python
Libraries: Streamlit, FastAPI, scikit-learn, MLflow, Docker
Cloud Platform: Azure Web App
CI/CD Pipeline: GitHub Actions
 
Deliverables:
Deployed Streamlit Dashboard: A cloud-based interactive application for iris classification.
API Endpoint: A FastAPI model deployed on Azure for real-time predictions.
Documentation: Detailed guides for setting up the dashboard, integrating the API, and tracking model experiments.
 
Who Should Enroll:
Data science enthusiasts eager to gain hands-on experience with deployment.
Python developers interested in building cloud-based interactive applications.
Professionals and students aiming to expand their skills in model deployment and dashboarding.
 
Why This Project? Deploying an interactive dashboard offers practical experience in bridging machine learning with web development. This project empowers you to deliver real-time insights to users, making it ideal for building a portfolio in data science and cloud deployment.