Apppublic

Irannas/Masked_Email_Classification

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes

App README

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

📧 Email Classifier with PII Masking

An intelligent tool that classifies emails into categories like Work, Personal, Spam, etc., while protecting sensitive information through PII (Personally Identifiable Information) masking.

🔗 Live Demo: 🌐 Try it on Hugging Face Spaces 📁 GitHub Repo: GitHub Repository

🚀 Features

—🔐 PII Masking: Automatically detects and masks sensitive information such as names, phone numbers, email addresses, and more.
—🧠 Email Classification: Uses a fine-tuned transformer model to classify email content into predefined categories.
—⚡ Real-Time Inference: Deployed with Streamlit for fast and user-friendly web interaction.
—📂 Batch Upload Support: Upload multiple email files (TXT format) and process them in one go.

🧰 Tech Stack

—Language: Python 3.10+
—NLP Libraries: Transformers (Hugging Face), spaCy, scikit-learn
—Model: DistilBERT / Custom Transformer
—Deployment: Streamlit, Hugging Face Spaces
—PII Detection: Regex + spaCy NER

📁 Project Structure

EmailClassifierProject/ ├── app/ # Streamlit App │ └── app.py ├── model/ # Trained model and tokenizer │ └── classifiermodel/ ├── data/ # Sample email data │ └── sampleemails/ ├── utils/ # Helper functions (PII masking, preprocessing, etc.) │ └── preprocess.py ├── requirements.txt ├── Dockerfile └── README.md

⚙️ Installation

Clone the repository and install the requirements:

bash

git clone https://github.com/IrannaSS/Masked_Email_Classification
cd your-repo-name
pip install -r requirements.txt


Run the Streamlit app locally:

        streamlit run app/app.py