A practical tool for predicting how far your bus can travel based on current conditions. Upload your historical data, and get distance predictions along with efficiency insights for better fleet management.
Train models on your historical bus data to predict travel distances. The system automatically selects the best performing algorithm and provides accuracy metrics.
Simple interface for both individual predictions and bulk fleet analysis. Upload CSV files or enter data manually to get instant results.
- Distance predictions based on fuel, load, speed, and route type
- Fuel efficiency scoring and recommendations
- Route optimization insights
- Load impact analysis
Your CSV file should include these columns:
| Column | Description | Example |
|---|---|---|
| Fuel_Level_Percentage | Current fuel level (0-100%) | 75.5 |
| Vehicle_Load_kg | Total load in kilograms | 1200 |
| Speed_kmph | Average speed in km/h | 65 |
| Temperature_C | Outside temperature in Celsius | 22.5 |
| Route_Type | Highway, Urban, or Rural | "Highway" |
| distance | Actual distance traveled (for training) | 145.2 |
-
Start the dashboard
streamlit run bus.py
-
Train your model
- Upload your historical bus data CSV
- Click "Let's Train Your AI!"
- Wait for training to complete
-
Make predictions
- Enter individual bus details for quick checks
- Upload CSV files for fleet-wide analysis
-
Review results
- View efficiency metrics and recommendations
- Download detailed reports
- Use insights for route and fuel planning
- Fuel Efficiency: Distance per fuel percentage (km per % fuel)
- Load Impact: How vehicle weight affects performance
- Temperature Effects: Weather impact on fuel consumption
- Route Analysis: Performance differences between highway, urban, and rural routes
- Speed Optimization: Recommended speed ranges for best efficiency
The dashboard provides interactive charts and downloadable reports with performance insights and recommendations for fleet optimization.
Route Planning: Check if a bus can complete a specific route before departure based on current fuel and load conditions.
Fleet Optimization: Compare efficiency across multiple vehicles to identify top performers and buses that need attention.
Cost Management: Understand fuel consumption patterns to optimize scheduling and reduce operational costs.
- Scikit-learn: For machine learning algorithms
- Streamlit: For the amazing web framework
- Plotly: For interactive visualizations
- Pandas & NumPy: For data manipulation