NeuralProphet bridges the gap between traditional time-series models and deep learning methods. It's based on PyTorch and can be installed using pip. A Neural Network based Time-Series model, inspired by Facebook Prophet and AR-Net, built on PyTorch. You can find the datasets used in the tutorials, including data preprocessing examples, in our neuralprophet-data repository. The documentation page may not we entirely up to date. Docstrings should be reliable, please refer to those when in doubt. We are working on an improved documentation. We appreciate any help to improve and update the docs. Lagged regressors (measured features, e.g temperature sensor). Future regressors (in advance known features, e.g. temperature forecast). Country holidays & recurring special events. Sparsity of coefficients through regularization. Plotting for forecast components, model coefficients as well as final predictions. Automatic selection of training-related hyperparameters.
Features
- After importing the package, you can use NeuralProphet in your code
- You can visualize your results with the inbuilt plotting functions
- If you want to forecast into the unknown future, extend the dataframe before predicting
- You can now install neuralprophet directly with pip
- Piecewise linear trend with optional automatic changepoint detection
- Autocorrelation modelling through AR-Net
- Fourier term Seasonality at different periods such as yearly, daily, weekly, hourly