ENH: Add other forecasting methods similar to STLForecast for seasonal_decompose and/or HP filter

[gsamaras]

I am using STL to forecast like this:

import matplotlib.pyplot as plt
from statsmodels.datasets import elec_equip as ds
from statsmodels.tsa.arima.model import ARIMA
from statsmodels.tsa.forecasting.stl import STLForecast

elec_equip = ds.load().data
elec_equip.index.freq = 'MS'
stlf = STLForecast(elec_equip, ARIMA, model_kwargs=dict(order=(1, 1, 0), trend="t"))
stlf_res = stlf.fit()

forecast = stlf_res.forecast(24)
plt.plot(elec_equip)
plt.plot(forecast)
plt.show()

Is there something similar to STLForecast(), but for seasonal_decompose?
Same question for Hodrick-Prescott filter.

I checked https://www.statsmodels.org/devel/tsa.html#module-statsmodels.tsa.forecasting, and I can't see any - to be exact I can only see a Theta model and an STLForecast, so I should assume that these two wrappers only exist?

[bashtage]

These are no other methods. You could, of course, roll your own, at least for seasonal decompose. For HP it isn't clear what value you would use for the forecast cycle, although it has a state-space representation so it should be doable.

[gsamaras]

Thanks a lot @bashtage, got it! I don't have any time to implement something, so from my side you can close this issue, unless if you want to keep it open for future contributors - up to you!