Skip to content

README.md

Latest commit

 

History

History
124 lines (91 loc) · 3.58 KB

README.md

File metadata and controls

124 lines (91 loc) · 3.58 KB

Time Series Analysis - Customised Dashboard

A comprehensive web-based dashboard for time series forecasting using ARIMA, SARIMA, and Prophet models with a modern, immersive UI.

🚀 Features

  • 📊 Multiple Data Sources:

    • Real-time stock data (Yahoo Finance)
    • CSV file upload
    • Sample data generation

  • 🤖 Advanced Forecasting Models:

    • ARIMA (Auto-Regressive Integrated Moving Average)
    • SARIMA (Seasonal ARIMA)
    • Prophet (Facebook's forecasting tool)
    • Model comparison functionality

  • 📈 Comprehensive Analysis:

    • Interactive charts with Plotly.js
    • Model performance metrics (RMSE, MAE, MAPE, AIC, BIC, R²)
    • Confidence intervals
    • Residual analysis

  • 🎨 Modern UI/UX:

    • Glass morphism design
    • Dark theme with blue accents
    • Responsive design
    • Particle effects and animations
    • Sound effects and notifications

🛠️ Technologies Used

  • Backend: Python, Flask, Pandas, NumPy
  • Forecasting: Statsmodels, Prophet
  • Frontend: HTML5, CSS3, JavaScript, Bootstrap 5
  • Charts: Plotly.js
  • Data Sources: Yahoo Finance API, CSV processing

📦 Installation

  1. Clone the repository

    git clone https://github.com/rk-python5/time_series-analysis-customised-dashboard.git
cd time_series-analysis-customised-dashboard

  2. Install dependencies

    pip install -r requirements.txt

  3. Run the application

    python app_flask.py

  4. Open your browser and navigate to http://localhost:5001

🎯 Usage

  1. Load Data: Choose your data source (Stock, CSV, or Sample)
  2. Select Model: Pick ARIMA, SARIMA, Prophet, or Compare All Models
  3. Configure Parameters: Set forecast periods and confidence intervals
  4. Run Forecasting: Click "RUN FORECASTING" to generate predictions
  5. Analyze Results: View interactive charts and performance metrics

📊 Sample Data

Try these popular stock tickers:

  • Tech: AAPL, MSFT, GOOGL, AMZN, TSLA
  • Finance: JPM, BAC, WFC, GS
  • Indices: ^GSPC (S&P 500), ^DJI (Dow Jones)
  • Crypto: BTC-USD, ETH-USD

🔧 Configuration

  • Forecast Periods: 1-1000 periods
  • Confidence Intervals: 50-99%
  • Auto Parameters: Automatic model parameter optimization
  • Manual Parameters: Custom ARIMA/SARIMA parameters

📈 Model Comparison

The dashboard includes a powerful model comparison feature that:

  • Runs multiple models simultaneously
  • Displays side-by-side forecasts
  • Compares performance metrics
  • Helps select the best model for your data

🎨 UI Features

  • Immersive Design: Glass morphism with particle effects
  • Interactive Elements: Hover effects, animations, sound feedback
  • Responsive Layout: Works on desktop and mobile
  • Theme Support: Dark theme with customizable accents
  • Keyboard Shortcuts: Quick access to common functions

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

👨‍💻 Author

Rehaan Khatri

🙏 Acknowledgments

  • Yahoo Finance for providing free stock data
  • Plotly for interactive charting
  • Bootstrap for responsive design components
  • The open-source community for various Python libraries

⭐ Star this repository if you found it helpful!