Getting ready

In this recipe, we will use the Appliances energy prediction dataset from the UCI Machine Learning Repository. We will work with the Appliances and lights variables, which contain records of the electricity that's consumed by appliances or lights in a single household at intervals of 10 minutes for a period of 5 months. To become familiar with the dataset, visit the Jupyter Notebook that accompanies this recipe in this book's GitHub repository (, where you will find visualizations so that you can understand the values, seasonality, and trends of these time series.

Get Python Feature Engineering Cookbook now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.