EsiorBma/Gender-Detection

Modele de ML entraine pour détecter le genre d'une personne à partir de son nom complet. # 🎯 Gender Detection for Togolese Names A machine learning system for predicting gender from Togolese names, optimized for Ewe, Kabyé, and Arabic naming conventions. ## 📋 Table of Contents - Features - Demo - Installation - Quick Start - Usage - Project Structure - Development - Testing - Deployment - Performance - Contributing - License ## ✨ Features - **🎯 High Accuracy**: 93% overall accuracy on Togolese names - **🌍 Multi-Ethnic Support**: Recognizes Ewe, Kabyé, and Arabic naming patterns - **🔄 Continuous Learning**: Improves from user feedback - **🚀 Production Ready**: Flask web app with admin dashboard - **📊 Detailed Analytics**: Performance metrics and feature importance tracking - **🔐 Secure Authentication**: Admin panel with user management - **📱 Responsive UI**: Modern, mobile-friendly interface ## 🎥 Demo ```bash # Try a prediction curl -X POST localhost \ -H "Content-Type: application/json" \ -d '{"full_name": "AMEGANVI Koffi Ama"}' # Response { "gender": "Femme", "predicted_value": 0, "surname": "AMEGANVI", "first_names": ["KOFFI", "AMA"], "main_first_name": "AMA" } ``` ## 📦 Installation ### Prerequisites - Python 3.8 or higher - pip (Python package manager) - Virtual environment (recommended) ### Option 1: Using Make (Recommended) ```bash # Clone the repository git clone github.com cd gender-detection # Initialize project (installs dependencies, creates .env) make init # Train the model make train # Run the application make run ``` ### Option 2: Manual Installation ```bash # Create virtual environment python3 -m venv env source env/bin/activate # On Windows: env\Scripts\activate # Install dependencies pip install -r requirements.txt pip install -e . # Setup environment cp .env.example .env # Train the model python -c "from gender_detection.model import train_model; train_model()" # Run the application cd src && python -m gender_detection.app ``` ## 🚀 Quick Start ### …