How lakshyaraj-singh-rao/email-spam-detector works
This is a small Streamlit message-classification app with a separate notebook-based training workflow. The runtime path is user input → app → saved classifier → displayed label. The README documents dataset cleaning, model comparison and tuning, held-out evaluation, and visualizations; these are represented as notebook responsibilities. The notebook source was not sampled, so its internal execution links reflect README documentation rather than verified calls.
Main entry points: app.py Streamlit app · spam_detection_model.pkl Saved classifier · spam_classifier.ipynb Training notebook · spam.csv Labelled messages
Components 7
Runtime classification
- Streamlit app
app.py - Saved classifier
spam_detection_model.pkl - Spam label
Model training
- Training notebook
spam_classifier.ipynb
Training assets
- Labelled messages
spam.csv - Evaluation charts
IMAGES
Other components
- Message sender
Connections 8
- Message sender → Streamlit app: enters message
- Streamlit app → Saved classifier: loads model
- Streamlit app → Saved classifier: requests prediction
- Saved classifier → Streamlit app: returns prediction
- Streamlit app → Spam label: displays result
- Training notebook → Labelled messages: reads data
- Training notebook → Saved classifier: saves pipeline
- Training notebook → Evaluation charts: produces visualizations