Lab | Flask for Data Science Deployment

In this lab, you will deploy a pre-trained machine learning model (regression/classification) using Flask. Create a web interface that allows users to make predictions through their browser.

Lab Instructions

Step 1: Find and Prepare Your Data

1. Search for an interesting dataset online (Kaggle, UCI ML Repository, etc.)
2. Choose a regression or classification problem that interests you
3. Train and save your model as a .pkl file

Step 3: Create Flask Application

1. Set up your Flask app and load your saved model
2. Create routes for home page (/) and predictions (/predict)
3. Handle POST requests and return predictions
4. Add proper error handling for invalid inputs

Step 4: Build Creative Web Interface

1. Create a templates/ folder with HTML files
2. Design an engaging and creative interface that fits your data theme
3. Build input forms that match your model's features
4. Create attractive result displays that clearly show predictions
5. Make it visually appealing and user-friendly

Step 5: Test and Deploy

1. Test your application locally
2. Ensure all functionality works properly
3. Verify error handling and edge cases

Deliverables

Your Flask application should demonstrate creativity in both data choice and interface design while maintaining professional functionality.

Submission

• Upon completion, add your deliverables to git.
• Then commit git and push your branch to the remote.
• Make a pull request and paste the PR link in the submission field in the Student Portal.

Good luck!