STL Decomposer#3741
Conversation
Codecov Report
@@ Coverage Diff @@
## main #3741 +/- ##
=======================================
- Coverage 99.7% 99.7% -0.0%
=======================================
Files 341 343 +2
Lines 35287 35681 +394
=======================================
+ Hits 35155 35545 +390
- Misses 132 136 +4
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
43ba31b to
e38c45e
Compare
…different classes. Moved the test to project the seasonal signal up to the parent Decomposer class. Moved the testing for the seasonal projection to the decomposer test module.
… to move that up to the base Decomposer class.
* Updated get_trend_df() to work out of sample. * Fixed transform() to work with in sample, but not spanning the sample. * Fixed inverse_transform to work with smaller than sample, in sample data.
…ple. Also updated test for transform to return same if y is None and moved that to parent class.
…etter reflect what's going on. Docstring changes.
…e seasonal sample to match the STLDecomposer.
b7c65ef to
a13b547
Compare
… bug in forecasting the trend
…ynomialDecomposer.
eccabay
left a comment
There was a problem hiding this comment.
Fantastic 🚢 What beasts of tests these are.
| if not isinstance(X.index, pd.DatetimeIndex): | ||
| raise TypeError("Provided X should have datetimes in the index.") |
There was a problem hiding this comment.
Do we need to continue enforcing this? We can set it within this function relatively easily.
| dec.set_seasonal_period(X, y) | ||
|
|
||
| assert 0.95 * period <= dec.seasonal_period <= 1.05 * period | ||
| assert dec.parameters["seasonal_period"] |
There was a problem hiding this comment.
Is this purposely just checking that the parameter exists? Should we be checking its value?
There was a problem hiding this comment.
OK, yes, this one is a bug. For some reason, parameters dict value is not being set. I tried fixing it, but for some reason cannot get it to set. I filed this to look at it later given that we don't even use set_seasonal_period.
| assert stl.seasonal_period == 5 | ||
|
|
||
|
|
||
| def build_test_target(subset_y, seasonal_period, transformer_fit_on_data, to_test): |
There was a problem hiding this comment.
Worth it to move to conftest?
There was a problem hiding this comment.
It is! This is actually handled in this parity PR and will shift up to the test_decomposer.py class.
jeremyliweishih
left a comment
There was a problem hiding this comment.
LGTM - amazing effort!
* cap featuretools * RL * Cap nlp primitives as well * Fix conda
|
I got the chance to play around with it and I think it looks and works great, fantastic job! |
|
praise god |
Decompose things...STL'ly!