| # 🌸 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 | |
| ```bash | |
| # 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 | |