Core Module Documentation

neuralprophet.plot_utils.check_if_configured(m, components, error_flag=False)

Check if components were set in the model configuration by the user.

Parameters

• m (NeuralProphet) – Fitted NeuralProphet model

• components (str or list, optional) –

  name or list of names of components to check

  • trend

  • trend_rate_change

  • seasonality

  • autoregression

  • lagged_regressors`

  • events

  • ``future_regressors`

  • uncertainty

• error_flag (bool) – Activate to raise a ValueError if component has not been configured

Returns

list of components only including the components set in the model configuration

Return type

components

neuralprophet.plot_utils.get_valid_configuration(m, components=None, df_name=None, valid_set=None, validator=None, forecast_in_focus=None, quantile=0.5)

Validate and adapt the selected components to be plotted.

Parameters

• m (NeuralProphet) – Fitted NeuralProphet model

• components (str or list, optional) – name or list of names of components to validate and adapt

• df_name (str) – ID from time series that should be plotted

• valid_set (str or list, optional) –

  name or list of names of components that are defined as valid option

  • (default)``None``: All components the user set in the model configuration are validated and adapted

  • trend

  • seasonality

  • autoregression

  • lagged_regressors

  • future_regressors

  • events

  • uncertainty

• validator (str) –

  specifies the validation purpose to customize

  • plot_parameters: customize for plot_parameters() function

  • plot_components: customize for plot_components() function

• forecast_in_focus (int) –

  optinal, i-th step ahead forecast to plot

  Note

  None (default): plot self.highlight_forecast_step_n by default

• quantile (float) –

  The quantile for which the model parameters are to be plotted

  Note

  0.5 (default): Parameters will be plotted for the median quantile.

Returns

valid_configuration – dict of validated components and values to be plotted

Return type

dict

neuralprophet.plot_utils.is_notebook()

Determine if the code is being executed in a Jupyter notebook environment.

Returns

True if the code is being executed in a Jupyter notebook, False otherwise.

Return type

bool

neuralprophet.plot_utils.predict_one_season(m, quantile, name, n_steps=100, df_name='__df__')

Predicts the seasonal component given a number of time steps.

Parameters

• m (NeuralProphet) – Fitted NeuralProphet model

• quantile (float) – The quantile for which the season is predicted

• name (str) – Name of seasonality component

• n_steps (int) – number of prediction steps related to the season frequency

• df_name – Name of dataframe to refer to data params from original keys of train dataframes

neuralprophet.plot_utils.predict_season_from_dates(m, dates, name, quantile, df_name='__df__')

Predicts the seasonal component given a date range.

mNeuralProphet

Fitted NeuralProphet model

dates: pd.datetime

date range for prediction

name: str

Name of seasonality component

quantile: float

The quantile for which the season is predicted

df_name: str

Name of dataframe to refer to data params from original keys of train dataframes

Returns

predicted – presdicted seasonal component

Return type

OrderedDict

neuralprophet.plot_utils.select_plotting_backend(model, plotting_backend)

Automatically selects the plotting backend based on the global plotting_backend and plotting_backend set by the user. If the plotting backend is selected as “plotly-resampler”, triggers warning message.

Parameters

• model (NeuralProphet) – The configured model.

• plotting_backend (str) – The plotting backend to use.

Returns

The new plotting backend.

Return type

str

neuralprophet.plot_utils.set_y_as_percent(ax)

Set y axis as percentage

Parameters

ax (matplotlib axis) – Respective y axis element

Returns

Manipulated axis element

Return type

matplotlib axis

neuralprophet.plot_utils.validate_current_env_for_resampler(auto: bool = False) → Optional[bool]

Validate the current environment to check if it is a valid environment for plotly-resampler and if invalid trigger warning message.

Parameters

auto (bool, optional) – If True, the function will automatically switch to a valid environment if the current environment is not valid. If False, the function will return None if the current environment is not valid.

Returns

True if the current environment is a valid environment to run the code, False if the current environment is not a valid environment to run the code. None if the current environment is not a valid environment to run the code and the function did not switch to a valid environment.

Return type

bool