All our content, organized by the Four Competencies of a Data Professional.
Automation techniques for testing & deploying infrastructure driven by changes to code.
Downloading, cleaning & joining UK electricity grid data with pandas, requests and pydantic.
How Git enables version control and code collaboration.
A simple guide to data provided by AEMO for the Australia's National Electricity Market (NEM).
Concise practical details about the two most common forms of gas based combined heat and power systems.
Berlin Machine Learning Group: Reinforcement learning for energy systems with energy-py
Explaining the relationship between gas turbines and ambient temperature.
Energy efficiency is not so simple.
Being careful and consistent when dealing with kilowatts and kilowatt-hours is a basic for all energy professionals.
Using optimization of a battery to measure forecast accuracy.
A Python library for optimizing batteries, EVs, CHP and renewable generators using mixed-integer linear programming.
The equation I used the most as an energy engineer.
A Python framework for training reinforcement learning agents on energy systems using Gymnasium and Stable Baselines 3.
Improve your energy project modelling with this simple & flexible forecasting technique.
Explaining the conventions for quantifying the heat of combustion.
An introduction to how the UK recovers electricity grid balancing costs.
Explaining the fully connected, convolution, LSTM and attention deep learning layer architectures.
Find interesting data with rules, distance and machine learning based anomaly detection.
Attention and Multi-Head Attention in NumPy.
Introduction to Q-Learning reinforcement learning algorithm
Overview of artificial intelligence, machine learning, and deep learning concepts
Demo day presentation at Data Science Retreat
Tuning hyperparameters of the new energy-py DDQN reinforcement learning agent.
Finally - stable learning.
Debugging the new energy-py DQN reinforcement learning agent.
Thirteen data science tools setting the standard in 2025.
Common mistakes made by data scientists and how to avoid them
Why this new feature is a game changer for developers.
Getting control using a stateful and stateless LSTM.
Ha & Schmidhuber's World Models reimplemented in Tensorflow 2.0.
I've been learning Python for around eleven months - it's been a wonderful journey!
Ten Python tools setting the standard in 2023.
Twelve Python tools setting the standard in 2025.
Introduction to distributed computation in Python, covering tools and techniques for parallel processing
Using the defaultdict store results from temporal simulations in Python.
The default programming language for working with data.
Three tips to write better function signatures with positional & keyword parameters, generic functions and function overloads.
Make your data science projects presentable, reproducible, accessible and extensible.
Find your next role as a a data professional.
Learn how to use a shell, write shell scripts, and configure your shell environment.
How to setup custom keyboard shortcuts for Jupyter Lab.
And never back again.
A guide to the next generation of notebook tooling.
Five patterns to guide your Git workflows.
Seventeen terminal, shell and command-line tools setting the standard in 2023.
Make your data science workflows better with this classic UNIX tool.
