TusharKoli8/Spam-Detection-using-NLP ? reverse-engineered prompt

Build me a simple SMS spam detector that can tell the difference between spam and normal messages.

I want the app to clean and preprocess text, turn the messages into TF IDF features, and then use a machine learning model or a simple rule based approach to make predictions. It should also show basic spam keyword analysis so I can see why a message was flagged. Please include a small interactive Streamlit screen where I can paste an SMS and get an instant spam or ham result.

Use the existing data and keep it easy to run from the command line, with a main script for the core model and a separate app for the UI. If you need anything from current docs or best practices, look it up online and keep the code simple and readable. I’d like the whole thing to feel like a complete end to end project that I can launch locally and test right away.