Linear explainer with Impute masker fails

[sbushmanov]

Linear explainer with Impute masker will fail due to dimension misalignment in the transform matrices.

To reproduce error:

from shap import Explainer
from shap.datasets import iris
from sklearn.linear_model import LogisticRegression

model = LogisticRegression(max_iter=1000)
model.fit(*iris())

masker = shap.maskers.Impute(data=X_test)

explainer = shap.Explainer(
    model, masker=masker, feature_names=X_train.columns, algorithm="linear"
)

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-15-82cb4b1256dc> in <module>
      9 
     10 explainer = shap.Explainer(
---> 11     model, masker=masker, feature_names=X_train.columns, algorithm="linear"
     12 )

~/anaconda3/lib/python3.7/site-packages/shap/explainers/_explainer.py in __init__(self, model, masker, link, algorithm, output_names, feature_names, **kwargs)
    165             elif algorithm == "linear":
    166                 self.__class__ = explainers.Linear
--> 167                 explainers.Linear.__init__(self, self.model, self.masker, link=self.link, feature_names=self.feature_names, **kwargs)
    168             else:
    169                 raise Exception("Unknown algorithm type passed: %s!" % algorithm)

~/anaconda3/lib/python3.7/site-packages/shap/explainers/_linear.py in __init__(self, model, masker, link, nsamples, feature_perturbation, **kwargs)
    145             self.mean = self.mean[self.valid_inds]
    146             self.cov = self.cov[:,self.valid_inds][self.valid_inds,:]
--> 147             self.coef = self.coef[self.valid_inds]
    148 
    149             # group perfectly redundant variables together

IndexError: index 3 is out of bounds for axis 0 with size 3

[github-actions]

This issue has been inactive for two years, so it's been automatically marked as 'stale'.

We value your input! If this issue is still relevant, please leave a comment below. This will remove the 'stale' label and keep it open.

If there's no activity in the next 90 days the issue will be closed.

[github-actions]

This issue has been automatically closed due to lack of recent activity.

Your input is important to us! Please feel free to open a new issue if the problem persists or becomes relevant again.