v0.4.0
v0.4.0 (2020-03-20)
NB: This is the last version supporting Python 3.5.
Added
- New feature
KernelSHAP
explainer for black-box model SHAP scores - Documentation for the
LinearityMeasure
algorithm
Changed
- Breaking change New API for explainer and explanation objects. Explainer objects now inherit from
Explainer
base class as a minimum. When calling.explain
method, anExplanation
object is returned (previously a dictionary). This contains two dictionariesmeta
anddata
accessed as attributes of the object, detailing the metadata and the data of the returned explanation. The common interfaces are underapi.interfaces
and default return metadata and data for each explainer are underapi.defaults
. - Complete refactoring of the Anchors algorithms, many code improvements
- Explainer tests are now more modular, utilizing scoped fixtures defined in
explainers.tests.conftest
and various utility functions - Tests are now run sequentially insted of in parallel due to overhead of launching new processes