{"id":27170,"library":"neuralprophet","title":"NeuralProphet","description":"NeuralProphet is a Python framework for interpretable time series forecasting built on PyTorch, combining Prophet's simplicity with neural networks. Current stable beta version is 0.9.0 (Python 3.9-3.12), with a 1.0.0 release candidate series in progress. Active development, monthly releases.","status":"active","version":"0.9.0","language":"python","source_language":"en","source_url":"https://github.com/ourownstory/neural_prophet","tags":["time-series","forecasting","prophet","pytorch","interpretable"],"install":[{"cmd":"pip install neuralprophet","lang":"bash","label":"Install from PyPI"}],"dependencies":[{"reason":"Core deep learning engine","package":"torch","optional":false},{"reason":"Training loop abstraction (>=2.0)","package":"pytorch-lightning","optional":false},{"reason":"Lunar calendar holiday support","package":"lunarcalendar","optional":true}],"imports":[{"note":"Hyphen in PyPI name, underscore in module","wrong":"from neural_prophet import NeuralProphet","symbol":"NeuralProphet","correct":"from neuralprophet import NeuralProphet"}],"quickstart":{"code":"import pandas as pd\nfrom neuralprophet import NeuralProphet\n\ndf = pd.read_csv('https://raw.githubusercontent.com/ourownstory/neural_prophet/main/example_data/air_passengers.csv')\nm = NeuralProphet()\nm.fit(df, freq='MS')\nfuture = m.make_future_dataframe(df, periods=12)\nforecast = m.predict(future)\nprint(forecast)","lang":"python","description":"Basic forecast with NeuralProphet"},"warnings":[{"fix":"Create a new model instance for each fit, or use m = NeuralProphet() again.","message":"NeuralProphet uses PyTorch Lightning 2.0+. Fitting a model a second time without reinitialization raises a RuntimeError.","severity":"breaking","affected_versions":">=0.9.0"},{"fix":"Manually set batch_size and epochs if you rely on previous defaults.","message":"Default batch size and epochs changed in 1.0.0rc5 (increased batch size, reduced epochs). Models may need retuning.","severity":"breaking","affected_versions":">=1.0.0rc5"},{"fix":"Upgrade Python to 3.9+.","message":"Python 3.8 support dropped in 0.8.0/1.0.0rc9. Minimum required Python is 3.9.","severity":"breaking","affected_versions":">=0.8.0"},{"fix":"Use m.set_epochs(n) or pass parameters in NeuralProphet(epochs=n).","message":"The 'epochs' parameter in fit() is deprecated in favor of controlling via trainer config.","severity":"deprecated","affected_versions":">=0.9.0"},{"fix":"Rename columns: df = df.rename(columns={'date': 'ds', 'value': 'y'})","message":"Input DataFrame must have columns 'ds' (timestamp) and 'y' (value). Column name mismatches cause silent errors.","severity":"gotcha","affected_versions":"all"},{"fix":"Pass freq='D', 'MS', etc. Inferred freq may be incorrect.","message":"Frequency (freq) must be provided in fit() for proper seasonality and future dates.","severity":"gotcha","affected_versions":"all"},{"fix":"Upgrade to >=1.0.0rc6. If not possible, force map_location in your load code.","message":"Loading a saved model on a different accelerator (e.g., GPU vs CPU) may fail.","severity":"gotcha","affected_versions":"<1.0.0rc6"}],"env_vars":null,"last_verified":"2026-04-27T00:00:00.000Z","next_check":"2026-07-26T00:00:00.000Z","problems":[{"fix":"Create a new NeuralProphet instance before calling fit again.","cause":"Trying to refit an already fitted model. This is by design in PyTorch Lightning 2.0+.","error":"RuntimeError: Cannot fit the model twice. Please create a new instance."},{"fix":"Use 'from neuralprophet import NeuralProphet' (no underscore).","cause":"Wrong import path: using underscore instead of the correct module name.","error":"ModuleNotFoundError: No module named 'neural_prophet'"},{"fix":"Check the documentation for the correct parameter name (e.g., 'seasonality_mode' was deprecated).","cause":"Parameter was renamed or removed in newer versions.","error":"TypeError: __init__() got an unexpected keyword argument 'seasonality_mode'"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"install_tag":null,"quickstart_score":null,"quickstart_tag":null}