Python for Energy — Advanced
Build predictive models for energy prices, detect market anomalies, and deploy ML pipelines. AI agents as programming assistants, scikit-learn, SHAP, and end-to-end ML engineering.
Jesús LópezWhat you'll learn
AI programming agents
Use LLMs as technical copilots for code generation, optimization and validation
Predictive models
Random Forest, Gradient Boosting and time series applied to day-ahead market prices
Pattern detection & anomalies
Clustering, Isolation Forest and correlation analysis on market data
ML in production
Export pipelines, automate daily predictions, integrate with PostgreSQL
Course curriculum
Estimated schedule — dates confirmed when an edition launches
- What is an LLM and how it works
- Using AI for code generation and optimization
- Crafting technical prompts and best practices
- Validating AI-generated results
- Practice: generate a deviation calculation function with AI
- ML applied to energy: price and deviation prediction
- Train/test split and evaluation metrics
- Temporal features, lags and rolling means
- Linear Regression baseline
- Random Forest for price prediction
- Gradient Boosting (conceptual + practical)
- Metrics: MAE, RMSE, R²
- Building reproducible pipelines
- Automated preprocessing in pipelines
- Practice: end-to-end pipeline for day-ahead prices
- Feature importance
- SHAP: explain individual predictions
- Sensitivity to key variables: forward price, renewables, demand
- Overfitting and underfitting
- Saving trained models with joblib
- Automating daily predictions
- Integration with PostgreSQL and Excel export
- Hour, day, month features
- Lags and rolling means
- Conceptual introduction to ARIMA
- Correlation matrix, multicollinearity and heatmaps
- K-Means: day types, consumption patterns, price behavior
- Anomaly detection with Isolation Forest
- Practice: detect atypical days and anomalous prices
- Data extraction and feature engineering
- Model training and evaluation
- Interpretation and SHAP analysis
- Excel export: predictions, error estimates, key variables
Who is this course for?
Energy professionals
Looking to apply Machine Learning to market data and forecasting
Analysts
Who want to build predictive models for prices and renewable production
Teams
Needing to automate predictions and deploy models in production
Prerequisites
Requires basic Python knowledge
Frequently asked questions
What's included
Dedicated PostgreSQL database
With real energy market data from OMIE and e·sios
Interactive notebooks
Exercises and solutions for each module
Session recordings
Access recordings to review at your own pace
AI agents as copilots
Use LLMs for code generation, optimization and validation
Price
Contact us
Your instructor
Jesús López
Instructor & Tool Builder
Jesús López builds tools that automate daily tasks—from processing thousands of Excel files to organizing entire projects. With over 54,000 students on LinkedIn Learning, he has a passion for teaching others how to create their own solutions, no programming background needed.
54,000+ students · 3 LinkedIn Learning courses
Choose your format
Same content, adapted to your pace
Need a customized training?
We adapt the content, schedule and exercises to your team's needs. In-person or online.
Interested in this course?
Leave your details and we'll contact you with pricing and availability.