Spam_Detection_LSTM / README.md
RebKip's picture
Update README.md
ce58313 verified
|
Raw History Blame Contribute Delete
3.53 kB
metadata
title: Spam Detection LSTM
emoji: 🚫
colorFrom: red
colorTo: red
sdk: docker
app_file: src/streamlit_app.py
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: AI-powered Spam vs. Ham classifier built with an LSTM RNN
license: mit
description: >-
  AI-powered Spam vs. Ham classifier built with an LSTM Recurrent Neural Network
  and Streamlit.

🚫 LSTM Spam Email & SMS Detector

An interactive, production-ready web application that utilizes a Long Short-Term Memory (LSTM) recurrent neural network to classify text messages as Spam or Ham (Legitimate).

This project demonstrates an end-to-end Machine Learning pipeline: from raw text preprocessing and tokenization to model training, evaluation calibration, and containerized deployment via Docker.


πŸš€ Interactive Demo

  1. Type or paste any suspicious message or email into the text area.
  2. Click Predict.
  3. The app will return a classification badge (SPAM or HAM) alongside the model's precise internal probability score.

πŸ“Š Model Performance & Calibration

During evaluation on the test split (1,032 samples), the model was calibrated to prioritize a High-Precision Strategy to minimize irritating False Positives (marking a critical legitimate email as spam).

Using an optimized decision threshold of 0.80, the model achieves the following metrics:

πŸ“ˆ Metrics Summary

  • Accuracy: 97.67%
  • Precision: 95.61% (High precision ensures safe filtering)
  • Recall: 85.16%
  • F1-Score: 90.08%

πŸ“ Classification Report

              precision    recall  f1-score   support

Negative (0)       0.98      0.99      0.99       904
Positive (1)       0.96      0.85      0.90       128

    accuracy                           0.98      1032
   macro avg       0.97      0.92      0.94      1032
weighted avg       0.98      0.98      0.98      1032

🧠 Technical Architecture & Pipeline

  1. Text Preprocessing: User input strings are automatically normalized to lowercase and stripped of redundant structural padding characters.
  2. Tokenization: Text sequences are mapped to numerical vector keys using a pre-saved training vocabulary tokenizer (spam_tokenizer.pickle).
  3. Sequence Padding: Sequences are bound to a strict maximum token length of 50 using a post-padding structure.
  4. Deep Learning Model: A Keras/TensorFlow architecture utilizing dense Word Embedding layers followed by sequential LSTM memory layers to capture contextual long-term text dependencies.

πŸ› οΈ Tech Stack & Engineering Details

  • Frontend UI: Streamlit
  • Deep Learning Runtime: TensorFlow / Keras
  • Data Processing: NumPy & Pandas
  • Deployment Container: Docker (Python 3.13-slim optimized environment)

πŸ“ Repository Directory Layout

β”œβ”€β”€ Dockerfile              # Container building directives & environment exposure
β”œβ”€β”€ requirements.txt        # Managed Python dependencies
└── src/
    β”œβ”€β”€ streamlit_app.py    # Main UI dashboard and inference logic
    β”œβ”€β”€ best_lstm_model.keras # Pre-trained network layers and model weights
    └── spam_tokenizer.pickle # Binary serialized vocabulary tokenizer asset

Welcome to Streamlit!

Edit /src/streamlit_app.py to customize this app to your heart's desire. :heart:

If you have any questions, checkout our documentation and community forums.