# 🚀 HDD Solution Predictor - Deployment Package

Ready-to-deploy package for the HDD Solution Predictor application.

## 📦 Package Contents

### **Application Files**
- `app.py` - Main Streamlit application (recommended)
- `mobile_app.py` - Mobile-optimized version
- `requirements.txt` - Python dependencies

### **Model Files**
- `decision_tree_model.pkl` - Trained Decision Tree model (100% accuracy)
- `dt_soil_encoder.pkl` - Soil type label encoder
- `dt_water_encoder.pkl` - Water table label encoder  
- `dt_solution_encoder.pkl` - Solution label encoder

### **Assets**
- `logo2.e8c5ff97.png` - MEA (Metropolitan Electricity Authority) logo
- `HDD_result.xlsx` - Training dataset

### **Documentation**
- `README.md` - This deployment guide

## 🔧 Quick Deployment

### **1. Install Dependencies**
```bash
pip install -r requirements.txt
```

### **2. Run Application**
```bash
# Main application (recommended)
streamlit run app.py

# Or mobile version
streamlit run mobile_app.py
```

### **3. Access Application**
- Local: `http://localhost:8501`
- Network: Will be shown in terminal

## 🌐 Deployment Options

### **Option A: Local Development**
```bash
git clone <repository>
cd deploy
pip install -r requirements.txt
streamlit run app.py
```

### **Option B: Streamlit Cloud**
1. Upload all files to GitHub repository
2. Connect to Streamlit Cloud
3. Deploy from `deploy/app.py`

### **Option C: Docker Deployment**
Create `Dockerfile`:
```dockerfile
FROM python:3.11-slim

WORKDIR /app
COPY . .

RUN pip install -r requirements.txt

EXPOSE 8501

CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
```

### **Option D: Heroku Deployment**
Create `Procfile`:
```
web: streamlit run app.py --server.port=$PORT --server.address=0.0.0.0
```

## 📊 Application Features

### **Core Functionality**
- **Input Parameters**: Pipe diameter, soil type, water table
- **ML Prediction**: Decision Tree with 100% training accuracy
- **Solution Types**: A, B, C, D, E (different protection levels)

### **Technical Specifications**
- **Framework**: Streamlit
- **ML Model**: Scikit-learn Decision Tree
- **Design**: Canva-style responsive UI
- **Branding**: MEA institutional logo

### **Supported Solutions**
- **Solution A**: Enhanced Protection (Sheetpile + Trench + Grouting)
- **Solution B**: Maximum Protection (+ Casing)
- **Solution C**: Moderate Protection (Sheetpile + Trench)
- **Solution D**: Basic Protection (Grouting Only)
- **Solution E**: Minimal Intervention (No Additional Measures)

## 🔍 System Requirements

### **Python Version**
- Python 3.8 or higher (recommended: 3.11)

### **Dependencies**
- streamlit
- pandas
- numpy
- scikit-learn
- joblib
- plotly
- openpyxl
- Pillow

### **Resources**
- **RAM**: Minimum 512MB, Recommended 1GB
- **Storage**: ~50MB for all files
- **Network**: Internet connection for initial setup

## 🔧 Configuration

### **Environment Variables** (Optional)
```bash
export STREAMLIT_SERVER_PORT=8501
export STREAMLIT_SERVER_ADDRESS=0.0.0.0
```

### **Streamlit Config** (Create `.streamlit/config.toml`)
```toml
[server]
port = 8501
address = "0.0.0.0"

[theme]
primaryColor = "#6c5ce7"
backgroundColor = "#ffffff"
secondaryBackgroundColor = "#f0f2f6"
```

## 🚨 Troubleshooting

### **Model Loading Issues**
- Ensure all `.pkl` files are in the same directory
- Check Python/scikit-learn version compatibility

### **Logo Not Displaying**
- Verify `logo2.e8c5ff97.png` exists in directory
- App will show MEA text fallback if logo missing

### **Port Already in Use**
```bash
streamlit run app.py --server.port=8502
```

### **Permission Issues**
```bash
chmod +x app.py
pip install --user -r requirements.txt
```

## 📱 Mobile Access

The application is fully responsive and works on:
- ✅ Desktop browsers
- ✅ Mobile phones  
- ✅ Tablets
- ✅ Touch devices

## 🔒 Security Notes

- Application runs locally by default
- No external API calls
- Model predictions processed locally
- Training data included for reference only

## 📞 Support

### **Common Issues**
1. **Dependencies**: Run `pip install -r requirements.txt`
2. **Port conflicts**: Use different port with `--server.port=XXXX`
3. **File paths**: Ensure all files are in same directory

### **Performance**
- **Model loading**: ~1-2 seconds on first run
- **Predictions**: Instant (<100ms)
- **UI rendering**: <1 second

---

## 🎯 Ready to Deploy!

1. **Install requirements**: `pip install -r requirements.txt`
2. **Run application**: `streamlit run app.py`
3. **Open browser**: Navigate to displayed URL
4. **Start predicting**: Enter parameters and get solutions!

**🏢 Powered by MEA (Metropolitan Electricity Authority)**