🌸 IrisAI — Flask ML Web Application
A machine learning web app that classifies Iris flowers using a Random Forest model, built with Flask.
📁 Project Structure
ml_flask_app/
├── app.py # Main Flask application
├── train_model.py # Model training script
├── requirements.txt # Python dependencies
├── users.db # SQLite database (auto-created)
├── model/
│ ├── iris_model.pkl # Trained Random Forest model
│ ├── scaler.pkl # StandardScaler
│ └── class_names.pkl # Class label names
└── templates/
├── base.html # Shared layout
├── login.html # Login page
├── register.html # Registration page
└── predict.html # Prediction form & results
🚀 Setup & Run
# 1. Install dependencies
pip install -r requirements.txt
# 2. (Optional) Retrain the model
python train_model.py
# 3. Run the app
python app.py
Then open http://127.0.0.1:5000 in your browser.
🔑 Default Login
- Username:
admin - Password:
password123
Or register your own account at /register.
🤖 Model Details
| Item | Value |
|---|---|
| Dataset | UCI Iris (150 samples, 4 features) |
| Algorithm | Random Forest (100 trees) |
| Accuracy | 90% on held-out test set |
| Classes | setosa, versicolor, virginica |
| Source | https://archive.ics.uci.edu/dataset/53/iris |
✨ Features
- 🔐 Login & registration with SHA-256 password hashing
- 📊 Real-time flower classification with confidence scores
- 📋 Prediction history per user (stored in SQLite)
- 💡 Quick-fill example inputs for each species
- 📱 Responsive design