NeuralProphet is an open-source time series forecasting library built on top of PyTorch. It combines the simplicity of Facebook’s Prophet with deep learning extensions, enabling accurate and interpretable forecasts. NeuralProphet supports autoregression, custom seasonality, lagged covariates, and future events, making it suitable for both research and real-world applications.

Features of NeuralProphet:

• Extends Facebook Prophet with deep learning capabilities.
• Built on top of PyTorch, supporting GPU acceleration for faster training.
• Handles autoregression, custom seasonality, and lagged regressors.
• Supports event-based forecasting and future covariates.
• Provides easy-to-use APIs for data scientists and engineers.
• Open-source, actively developed, and widely used in research and industry.

To check the installed version of NeuralProphet on Ubuntu 24.04, run these commands in your environment:

$ sudo su
$ sudo apt update
$ cd /opt/neuralprophet
$ source venv/bin/activate
$ pip show neuralprophet

Disclaimer: NeuralProphet is released under the MIT License and maintained by the open-source community. Users are responsible for correct usage in their specific applications. The developers are not liable for any consequences arising from its use. Always refer to the official NeuralProphet documentation for the most accurate and up-to-date information.