Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] fix seasonality estimators for candidate_sp being int #4360

Merged
merged 1 commit into from Mar 19, 2023

Conversation

fkiraly
Copy link
Collaborator

@fkiraly fkiraly commented Mar 18, 2023

This fixes an unreported bug when candidate_sp in two seasonality estimators would be int. According to the docstring, this should be treated as a one-element iterable, but instead led to error.

This is fixed by coercing to one-element iterable, and covered by an additional test case.

The estimators concerned are SeasonalityACF and SeasonalityACFqstat.

@fkiraly fkiraly added bugfix Fixes a known bug or removes unintended behavior module:parameter-estimators parameter fitters and estimators labels Mar 18, 2023
@fkiraly
Copy link
Collaborator Author

fkiraly commented Mar 19, 2023

Factored out of #4248 which was open for a while

@fkiraly fkiraly merged commit 08359f2 into main Mar 19, 2023
20 checks passed
@fkiraly fkiraly deleted the fix_seasonality_coerce_cand branch March 19, 2023 13:56
fkiraly added a commit that referenced this pull request Mar 19, 2023
See #4249

This adds a transformer compositor which executes a transform conditionally, e.g., deseasonalizes if seasonality is detected, or differences if stationarity is detected. The condition can be specified flexibly based on any estimator (with a `fit` interface), and the if/else transformation can also be configured.

Relies on #4360 for the seasonality example.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bugfix Fixes a known bug or removes unintended behavior module:parameter-estimators parameter fitters and estimators
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant