Welcome to epftoolbox’s documentation!

This is the documentation of the epftoolbox, the first open-access library for driving research in electricity price forecasting. Its main goal is to make available a set of tools that ensure reproducibility and establish research standards in electricity price forecasting research.

The library contrain three main components:

• The data management subpackage, which comprises a module for processing data and another module for dataset extraction.
• The models subpackage, which provides two state of the art forecasting models for electricity price forecasting. The contains a module for the LEAR model and another module for the DNN model.
• The evaluation subpackage, which includes a module for evaluating the performance of the models in terms of accuracy metrics, and another module to compare the forecasts of the models via statistical testing.

The library is distributed under the AGPL-3.0 License and it is built on top of scikit-learn, tensorflow, keras, hyperopt, statsmodels, numpy, and pandas.

Using the index on the navigation bar or the index below you can navigate through the different library components.

• Getting started
• Data management
• Forecasting models
• Model evaluation
• Examples
• Citation