#174174th of 214 in ML frameworks and librariesFor data and documents, data analysis
neural_prophet
PyTorch time series forecasting library inspired by Facebook Prophet and AR-Net
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Jun 2024
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
NeuralProphet is a Python library for interpretable time series forecasting, built on PyTorch. It combines Prophet-style components (piecewise linear trend, Fourier seasonality, holidays and events) with autoregression and lagged or future regressors that can be linear or neural networks. It supports multiple series with global or 'glocal' components and quantile-based uncertainty.
Who it is for: Data scientists building interpretable time series forecasts in Python
Strengths
- Prophet-like API: fit, predict and plot forecasts and components in a few lines
- Autoregression and lagged or future regressors can be linear or neural (AR-Net)
- Global and 'glocal' modelling across multiple series, plus quantile regression
- Includes cross-validation utility, checkpointing and regularization of components
Weaknesses
- README says it is still in beta and may not be most accurate out of the box
- Docs page may be out of date; README points to docstrings instead
- README recommends higher-frequency data covering at least two full periods
- Last release is 2024-06-21; logistic growth trend still listed as coming soon
What it needs
- Needs PyTorch, Python 3.9+
- Models: Prophet-style trend and seasonality, AR-Net autoregression, Quantile regression
Also in ML frameworks and libraries
See all 214| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 94 out of 100 |
| #4 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |