Error when plotting confidence intervals with NeuralProphet

Question

I'm following the tutorial on quantile regression in NeuralProphet, but there is an issue when plotting the forecast.

confidence_lv = 0.9
quantile_list = [round(((1 - confidence_lv) / 2), 2), round((confidence_lv + (1 - confidence_lv) / 2), 2)]


m = NeuralProphet(
    yearly_seasonality=True,
    weekly_seasonality=True,
    daily_seasonality=False,  
    quantiles=quantile_list,
    n_lags=30,
    epochs=10,
    n_forecasts=30,
)

m.set_plotting_backend('plotly')
metrics = m.fit(df)

df_future = m.make_future_dataframe(
    df, 
    n_historic_predictions=True,   
    periods=30, 
)

forecast = m.predict(df_future)

m.plot(forecast, forecast_in_focus=30)

I'm getting the error below. I'm not finding the parameter they mentioned anywhere in these functions above (I'm using version 0.6.2).

in NeuralProphet.plot(self, fcst, df_name, ax, xlabel, ylabel, figsize, forecast_in_focus, plotting_backend)
   1886 if len(self.config_train.quantiles) > 1:
   1887     if (self.highlight_forecast_step_n) is None and (
   1888         self.n_forecasts > 1 or self.n_lags > 0
   1889     ):  # rather query if n_forecasts >1 than n_lags>1
-> 1890         raise ValueError(
   1891             "Please specify step_number using the highlight_nth_step_ahead_of_each_forecast function"
   1892             " for quantiles plotting when auto-regression enabled."
   1893         )
   1894     if (self.highlight_forecast_step_n or forecast_in_focus) is not None and self.n_lags == 0:
   1895         log.warning("highlight_forecast_step_n is ignored since auto-regression not enabled.")

ValueError: Please specify step_number using the highlight_nth_step_ahead_of_each_forecast function for quantiles plotting when auto-regression enabled.

Answer 1

If I understand correctly the error is stating you are missing a step in your code. When you are initiating:

m = NeuralProphet(
    yearly_seasonality=True,
    weekly_seasonality=True,
    daily_seasonality=False,  
    quantiles=quantile_list,
    n_lags=30,
    epochs=10,
    n_forecasts=30,
)

You are setting n_forecasts=30. Doing so triggers the following if statement:

if (self.highlight_forecast_step_n) is None and (
    self.n_forecasts > 1 or self.n_lags > 0

You failed to set highlight_forecast_step_n and have set n_forecasts=30. Thus the if statement is True because highlight_forecast_step_n equals None and n_forecasts is higher then 1. T

To fix this you need to set the highlight_forecast_step_n attribute of your model. This can be done by using the class function highlight_nth_step_ahead_of_each_forecast.

Something like this will work:

m.highlight_nth_step_ahead_of_each_forecast(step_number=10)

Reference: highlight_nth_step_ahead_of_each_forecast