HoltWinters alias parameters not supported and some other problems about statsforecast HOT 6 CLOSED

Hey @numomcmc, thanks for using statsforecast.

1. The season length is the length of the seasonal period, so if you have hourly data it can be 24 (same hour every day) or 24 * 7 (same hour, same day of the week), etc.
2. The alias is in the constructor, so maybe you installed an older version. Can you check your installed version?

   statsforecast/statsforecast/models.py

   Lines 2580 to 2608 in 89f2e02

   	class HoltWinters(AutoETS):
   	"""Holt-Winters' method.
   	Also known as triple exponential smoothing, Holt-Winters' method is an extension of exponential smoothing for series that contain both trend and seasonality.
   	This implementation returns the corresponding `ETS` model with additive (A) or multiplicative (M) errors (so either 'AAA' or 'MAM').
   	References
   	----------
   	[Rob J. Hyndman and George Athanasopoulos (2018). "Forecasting principles and practice, Methods with seasonality"](https://otexts.com/fpp3/holt-winters.html).
   	Parameters
   	----------
   	season_length : int
   	Number of observations per unit of time. Ex: 12 Monthly data.
   	error_type : str
   	The type of error of the ETS model. Can be additive (A) or multiplicative (M).
   	alias : str
   	Custom name of the model.
   	prediction_intervals : Optional[ConformalIntervals]
   	Information to compute conformal prediction intervals.
   	By default, the model will compute the native prediction
   	intervals.
   	"""
   	def __init__(
   	self,
   	season_length: int = 1, # season length
   	error_type: str = "A", # error type
   	alias: str = "HoltWinters",

3. Not sure what you mean by "I am stuck with having no model name/alias to pass into the call"
4. That's not a call, it's the output of the fit method (it returns self).
5. The fitted_ attribute stores the trained models, so it should be there after you call fit (assuming you're storing the forecast object in sf).
6. I don't think you installed a recent version, since the alias has been there since last year

If you're just starting out I recommend a more general guide, like the quick start.

from statsforecast.

from statsforecast.

Since there's no way to print out the version of StatsForecat

You can run:

import statsforecast

print(statsforecast.__version__)

or in a terminal:

conda list statsforecast

or

pip show statsforecast

Maybe you already had it installed, that way conda install would do nothing but tell you that you already have it.

Have your problems been addressed? Can we close this issue?

from statsforecast.

from statsforecast.

The install from conda works fine, you can see the files here and both 1.5.0 and 1.6.0 have been downloaded thousands of times. Also you can run docker run --rm mambaorg/micromamba:1.5-focal micromamba install -c conda-forge statsforecast and see that it pulls statsforecast 1.6.0.

The error you're getting is because that's not a cell you should run, that's the output in the documentation. Feel free to join our slack to ask specific questions. I'm closing this since we didn't find any issues.

from statsforecast.

from statsforecast.