How sri-raj-2222/spam_detection__system works
This is a Streamlit SMS spam detector. A user enters a message and requests a check; the app cleans, removes stop words, and stems the text, transforms it with the saved TF-IDF vectorizer, then predicts and displays Spam or Not Spam. The graph reflects the sampled runtime in app.py; the CSV and notebook are present, but their role in training or runtime is not established by the available evidence.
Main entry points: app.py Streamlit App · vectorizer.pkl Saved Vectorizer · model.pkl Spam Classifier
Components 11
User Interface
- Streamlit App
app.py - Message Input
app.py - Result Display
app.py
Text Preprocessing
- Text Cleaning
app.py - Stopword Removal
app.py - Word Stemming
app.py - English Stopwords
Classification
- TF-IDF Transform
app.py - Saved Vectorizer
vectorizer.pkl - Spam Classifier
model.pkl
Other components
- User
Connections 13
- User → Message Input: enters message
- Message Input → Streamlit App: provides message
- Streamlit App → Text Cleaning: cleans text
- Streamlit App → Stopword Removal: removes words
- Stopword Removal → English Stopwords: reads list
- Streamlit App → Word Stemming: stems text
- Streamlit App → TF-IDF Transform: transforms text
- Streamlit App → Saved Vectorizer: loads vectorizer
- TF-IDF Transform → Saved Vectorizer: vectorizes text
- Streamlit App → Spam Classifier: loads model
- Streamlit App → Spam Classifier: predicts class
- Streamlit App → Result Display: shows prediction
- Result Display → User: displays result