Technical requirements

This chapter requires the following Python libraries:

• numpy (1.26.3)
• pandas (2.0.3)
• scikit-learn (1.4.0)
• sktime (0.26.0)
• torch (2.2.0)
• pytorch-forecasting (1.0.0)
• pytorch-lightning (2.1.4)
• gluonts (0.14.2)
• ray (2.9.2)

You can install these libraries in one go using pip:

pip install -U pandas numpy scikit-learn sktime torch pytorch-forecasting pytorch-lightning gluonts

The recipes in this chapter will follow a design philosophy based on PyTorch Lightning that provides a modular and flexible way of building and deploying PyTorch models. The code for this chapter can be found at the following GitHub URL: https://github.com/PacktPublishing/Deep-Learning-for-Time-Series-Data-Cookbook.