WeatherEnergyAnalytics

Overview

WeatherEnergyAnalytics is a web application that explores how weather patterns influence commodity prices and energy demand. Built with Streamlit, it fetches real weather data via the Open-Meteo API, pairs it with commodity price trends (mocked for now), and delivers interactive visualizations. Traders and analysts can select commodities (e.g., Natural Gas) and locations (e.g., New York) to uncover insights and forecast demand.

Data Sources

• Weather Data: Open-Meteo API (hourly temperature, precipitation)
• Commodity Prices: Mock data via NumPy (replaceable with financial APIs)
• Locations: 10 U.S. cities with hardcoded coordinates (e.g., New York: 40.7128, -74.0060)

Technologies Used

• Framework: Streamlit (interactive UI)
• Data Handling: Pandas (merging), NumPy (mock data)
• Visualization: Plotly Express (charts)
• API: Requests (weather data)
• Logic: Python, Datetime (time management)

Key Features

• Select commodities (Natural Gas, Crude Oil, Electricity) and locations (e.g., Chicago, Houston)
• Analyze historical weather (temperature, precipitation) vs. commodity prices
• Visualize trends with interactive Plotly charts
• Forecast 7-day energy demand based on weather trends
• Calculate correlations (e.g., temperature vs. price)

Data Analysis Process

• Fetch Data: Pull weather from Open-Meteo API using lat/long and date range
• Generate Prices: Mock commodity prices with NumPy (random $50-$100)
• Merge & Analyze: Combine datasets with Pandas, compute correlation (corr())
• Visualize: Plot temperature/precipitation vs. price, forecast demand with Plotly

Performance

• Correlation: Varies (e.g., ~0.2 to 0.5 with mock data; real data TBD)
• Response Time: Fast Streamlit rendering (~1-2s with API call)
• Scalability: Lightweight for demo; needs database for scale

Challenges Overcome

• Integrated real-time weather API with mock financial data seamlessly
• Handled time-series alignment with Pandas merges
• Delivered interactive UI with minimal code using Streamlit

Benefits

• Decision Support: Insights for traders on weather-driven price shifts
• Forecasting: Predicts energy demand for planning
• Accessibility: Simple UI for non-technical users

Future Improvements

• Integrate real commodity price APIs (e.g., Quandl, Bloomberg)
• Add ML models (e.g., regression) for price prediction
• Store data in a database (e.g., SQLite) with caching
• Allow custom locations and commodities

Demo

Try It

Clone the repo, install dependencies, and run streamlit run app.py! See GitHub for setup.