-
Notifications
You must be signed in to change notification settings - Fork 87
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
Split STL seasonal_period
into separate seasonal_smoother
and period
#3896
Conversation
Codecov Report
@@ Coverage Diff @@
## main #3896 +/- ##
=======================================
+ Coverage 99.7% 99.7% +0.1%
=======================================
Files 346 346
Lines 36639 36640 +1
=======================================
+ Hits 36509 36510 +1
Misses 130 130
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
def test_stl_raises_warning_high_smoother(caplog, ts_data): | ||
X, _, y = ts_data() | ||
stl = STLDecomposer(seasonal_smoother=101) | ||
stl.fit(X, y) | ||
assert "STLDecomposer may perform poorly" in caplog.text |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I suspect the behavior we want here is actually to warn off the period
rather than the seasonal_smoother
parameter here.
Currently, in evalml/stl_decomposer.py at main · alteryx/evalml, the STLDecomposer mistakenly takes a value for seasonal and passes it to the seasonal parameters of the underlying STL algorithm. It seems that seasonal is actually a value for a window that does smoothing (possibly for the trend decomposition). This fixes that by splitting the
seasonal_period
parameter into separateseasonal_smoother
(ideally a clearer name for this parameter) andperiod