How to use SHAP with a linear SVC model from sklearn using Pipeline? - scikit-learn

Question

I am doing text classification using a linear SVC model from sklearn. Now I want to visualize which words/tokens have the highest impact on the classification decision by using SHAP (https://github.com/slundberg/shap).
Right now this does not work because I am getting an error that seems to originate from the vectorizer step in the pipeline I have defined - whats wrong here?
Is my general approach on how to use SHAP in this case correct?
x_Train, x_Test, y_Train, y_Test = train_test_split(df_all['PDFText'], df_all['class'], test_size = 0.2, random_state = 1234)
pipeline = Pipeline([
(
'tfidv',
TfidfVectorizer(
ngram_range=(1,3),
analyzer='word',
strip_accents = ascii,
use_idf = True,
sublinear_tf=True,
max_features=6000,
min_df=2,
max_df=1.0
)
),
(
'lin_svc',
svm.SVC(
C=1.0,
probability=True,
kernel='linear'
)
)
])
pipeline.fit(x_Train, y_Train)
shap.initjs()
explainer = shap.KernelExplainer(pipeline.predict_proba, x_Train)
shap_values = explainer.shap_values(x_Test, nsamples=100)
shap.force_plot(explainer.expected_value[0], shap_values[0][0,:], x_Test.iloc[0,:])
This is the error message I get:
Provided model function fails when applied to the provided data set.
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-81-4bca63616b3b> in <module>
3
4 # use Kernel SHAP to explain test set predictions
----> 5 explainer = shap.KernelExplainer(pipeline.predict_proba, x_Train)
6 shap_values = explainer.shap_values(x_Test, nsamples=100)
7
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\shap\explainers\kernel.py in __init__(self, model, data, link, **kwargs)
95 self.keep_index_ordered = kwargs.get("keep_index_ordered", False)
96 self.data = convert_to_data(data, keep_index=self.keep_index)
---> 97 model_null = match_model_to_data(self.model, self.data)
98
99 # enforce our current input type limitations
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\shap\common.py in match_model_to_data(model, data)
80 out_val = model.f(data.convert_to_df())
81 else:
---> 82 out_val = model.f(data.data)
83 except:
84 print("Provided model function fails when applied to the provided data set.")
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\utils\metaestimators.py in <lambda>(*args, **kwargs)
116
117 # lambda, but not partial, allows help() to work with update_wrapper
--> 118 out = lambda *args, **kwargs: self.fn(obj, *args, **kwargs)
119 # update the docstring of the returned function
120 update_wrapper(out, self.fn)
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\pipeline.py in predict_proba(self, X)
379 for name, transform in self.steps[:-1]:
380 if transform is not None:
--> 381 Xt = transform.transform(Xt)
382 return self.steps[-1][-1].predict_proba(Xt)
383
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\feature_extraction\text.py in transform(self, raw_documents, copy)
1631 check_is_fitted(self, '_tfidf', 'The tfidf vector is not fitted')
1632
-> 1633 X = super(TfidfVectorizer, self).transform(raw_documents)
1634 return self._tfidf.transform(X, copy=False)
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\feature_extraction\text.py in transform(self, raw_documents)
1084
1085 # use the same matrix-building strategy as fit_transform
-> 1086 _, X = self._count_vocab(raw_documents, fixed_vocab=True)
1087 if self.binary:
1088 X.data.fill(1)
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\feature_extraction\text.py in _count_vocab(self, raw_documents, fixed_vocab)
940 for doc in raw_documents:
941 feature_counter = {}
--> 942 for feature in analyze(doc):
943 try:
944 feature_idx = vocabulary[feature]
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\feature_extraction\text.py in <lambda>(doc)
326 tokenize)
327 return lambda doc: self._word_ngrams(
--> 328 tokenize(preprocess(self.decode(doc))), stop_words)
329
330 else:
c:\users\s.p\appdata\local\programs\python\python37\lib\site-packages\sklearn\feature_extraction\text.py in <lambda>(x)
254
255 if self.lowercase:
--> 256 return lambda x: strip_accents(x.lower())
257 else:
258 return strip_accents
AttributeError: 'numpy.ndarray' object has no attribute 'lower'

Answer 1

KernelExplainer expects to receive a classification model as the first argument. Please check the use of Pipeline with Shap following the link.
In your case, you can use the Pipeline as follows:
x_Train = pipeline.named_steps['tfidv'].fit_transform(x_Train)
explainer = shap.KernelExplainer(pipeline.named_steps['lin_svc'].predict_proba, x_Train)