Neural Prophet - 0.5.0

What's Changed

  • Lightning Migration by @karl-richter in
  • [lightning] remove rich progress bar by @karl-richter in
  • Improvement/type annotations by @noxan in
  • Commented out test_progress_display in by @Kevin-Chen0 in
  • Added plot param of the NeuralProphet fit() and uncomment test_progress_display in by @Kevin-Chen0 in
  • [lightning] refactored Trainer args by @karl-richter in
  • refactored test failure by @karl-richter in
  • Update to 0.5.0 by @Kevin-Chen0 in
  • Remove support for df dict as an input by @judussoari in
  • Add alias function plot_last_forecast() for plot_latest_forecast() and give deprecation warning by @judussoari in
  • Mask seasonality on Sat/Sun when data frequency is Business days by @judussoari in
  • [bug] Forecast output dataframe contains all float dtypes instead of having some objects by @Kevin-Chen0 in
  • Fix labels of yhatx and origin-x in plots by @judussoari in
  • Improve github action speed for docs test by @noxan in
  • Remove residuals in forecast dataframe returned by m.predict() by @judussoari in
  • Resolved discontinuous trend when changepoints are not sorted chronologically by @leoniewgnr in
  • Address small tech debt to use a conditional instead of try/except for Python 3.7 support by @kapoor1992 in
  • [dev-ops] Collapsible metrics reports by @noxan in
  • Cleanup document files by @noxan in
  • Rename and to xxx_matplotliโ€ฆ by @SaumyaBhushan in
  • [lightning] GPU support by @karl-richter in
  • [naming] Renamed tutorial notebooks by @karl-richter in
  • [feature] Support plotting of only specific panels in plot_parameters and plot_components by @LeonieFreisinger in
  • Labels in by @karl-richter in
  • [enhancement] add pytests for matplotlib by @LeonieFreisinger in
  • [devops] Improve codecov threshold by @noxan in
  • [devops] Upgrade GitHub action versions by @noxan in
  • [typing] Add type annotations for main NeuralProphet class by @noxan in
  • change deprecation message to switch plotting backend to plotly by @LeonieFreisinger in
  • [feature] Plot components of averaged df (and quants) if multiple IDs, but no df_name specified in plot_components() by @judussoari in
  • [devops] Code coverage threshold fix by @noxan in
  • Time in model training benchmark by @karl-richter in
  • Unified the naming of variables - num and nb by @SaumyaBhushan in
  • [tests] Add tests for configure by @noxan in
  • [cleanup] Remove unused from_kwargs config function by @noxan in
  • [devops] Add shell script to setup basic development environment by @noxan in
  • [lightning] Speed-up by @karl-richter in
  • Update progress bar only every epoch by @karl-richter in
  • [typing] Resolve type annotation issues in configure file by @noxan in
  • [typing] Add ConfigEvents type annotations by @noxan in
  • [refactor] Extract plot utils into dedicated file by @LeonieFreisinger in
  • [website] Fix typo in preview of website description by @noxan in
  • Move tensors to correct device by @karl-richter in
  • [docs] New tutorials section for docs by @noxan in
  • Meta name bool by @alfonsogarciadecorral in
  • Uncertainty: Conformal Prediction V1 by @Kevin-Chen0 in
  • Change plotting_backend deprecation warning for implicit and explicit matplotlib use by @LeonieFreisinger in
  • [feature] Add a main script to print neuralprophet version by @noxan in
  • [dev-ops] Type annotation validation GitHub action by @noxan in
  • Add pull request template for Github by @karl-richter in
  • [typing] fix typings and constructor super call for pinnball loss by @noxan in
  • Follow-up tensors on wrong device by @karl-richter in
  • Fix string Interpolation by @poweroftrue in
  • Fix label links in contributing guidelines by @noxan in
  • bump version number to 0.5.0rc2 by @noxan in
  • [bugfix] enable events while predicting into known future by @judussoari in
  • [fix] Replace all deprecated plot_last_forecast with plot_latest_forecast by @noxan in
  • [refactor] Rename config_seasonality and add typings by @noxan in
  • [refactor] Remove duplicate season reg lambda by @noxan in
  • [fix] Renamed reamining self.config_season variables to self.config_seasonality in by @Kevin-Chen0 in
  • Removed commented tests in by @Kevin-Chen0 in
  • [refactor] Rename uncertainty_estimation.ipynb to uncertainty_quantile_regression.ipynb by @Kevin-Chen0 in
  • Normalize training speed metric by @karl-richter in
  • Improved system performance tracker by @karl-richter in
  • Update metrics.yml by @karl-richter in
  • [devops] Cleanup and limit CodeQL Github action to main branch by @noxan in
  • Support for holidays of multiple countries by @leoniewgnr in
  • [docs] Tuturials use prepared dataset by @noxan in
  • Refactored dataloader by @karl-richter in
  • [model] Deep model parameter interpretation by @karl-richter in
  • Normalize training time metric by @karl-richter in
  • Uncertainty: Conformal Prediction V2 - add .conformal_predict() and remove .conformalize() in by @Kevin-Chen0 in
  • Removed unnecessary if statement in predict_season_from_dates by @judussoari in
  • Refactored fit() interface by @karl-richter in

New Contributors

  • @leoniewgnr made their first contribution in
  • @SaumyaBhushan made their first contribution in
  • @poweroftrue made their first contribution in

Full Changelog:


Dec. 8, 2022, 12:04 a.m.
Beta 0.5.0
Register or login to:
  • ๐Ÿ”View and search all Neural Prophet releases.
  • ๐Ÿ› ๏ธCreate and share lists to track your tools.
  • ๐ŸšจSetup notifications for major, security, feature or patch updates.
  • ๐Ÿš€Much more coming soon!
Continue with GitHub
Continue with Google