Closed iamDecode closed 3 years ago
Merging #24 (04b9993) into master (bb2fc93) will not change coverage. The diff coverage is
100.00%
.
@@ Coverage Diff @@
## master #24 +/- ##
=========================================
Coverage 100.00% 100.00%
=========================================
Files 12 12
Lines 559 624 +65
=========================================
+ Hits 559 624 +65
Impacted Files | Coverage Δ | |
---|---|---|
sklearn_pmml_model/base.py | 100.00% <100.00%> (ø) |
|
sklearn_pmml_model/linear_model/__init__.py | 100.00% <100.00%> (ø) |
|
sklearn_pmml_model/linear_model/base.py | 100.00% <100.00%> (ø) |
|
sklearn_pmml_model/linear_model/implementations.py | 100.00% <100.00%> (ø) |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update bb2fc93...04b9993. Read the comment docs.
So far only linear regression was supported, but the step towards supporting logistic regression is trivial. This PR implements this.
There is unfortunately a bit of code duplication (
PMMLLinearModel
/PMMLLinearClassifier
andPMMLGeneralizedLinearRegressor
/PMMLGeneralizedLinearClassifier
). IdeallyPMMLLinearModel
should be a generic class that can be eitherPMMLBaseRegressor
orPMMLBaseClassifier
. However, I was not able to usetyping.Generic
and also callsuper.__init__()
on the generic class. This should be revisited later.