def test_local_contrib_w_discretize(self):
row = self.frame.iloc[0, :]
explainer = LIMEExplainer(training_frame=self.frame,
X=self.X,
model=self.model,
discretize=self.discretize)
local_sample = explainer._generate_local_sample(row)
scored_local_sample = \
explainer._score_local_sample(local_sample,
row[local_sample.columns])
weighted_scored_local_sample = \
explainer._calculate_distance_weights(0,
scored_local_sample)
discretized_weighted_scored_local_sample = \
explainer._discretize_numeric(weighted_scored_local_sample)
disc_row = pd.DataFrame(columns=self.X)
for name in self.discretize:
disc_row[name] = pd.cut(pd.Series(row[name]),
bins=explainer.bins_dict[name])
not_in = list(set(self.X) - set(self.discretize))
disc_row[not_in] = row[not_in].values
explainer.lime = \
explainer._regress(discretized_weighted_scored_local_sample,
h2o.H2OFrame(disc_row))
self.assertEqual(explainer.reason_code_values.shape, (21, 2))
del explainer
def test_local_contrib_w_o_discretize(self):
row = self.frame.iloc[0, :]
explainer = LIMEExplainer(training_frame=self.frame,
X=self.X,
model=self.model)
local_sample = explainer._generate_local_sample(row)
scored_local_sample = \
explainer._score_local_sample(local_sample,
row[local_sample.columns])
weighted_scored_local_sample = \
explainer._calculate_distance_weights(0,
scored_local_sample)
explainer.lime = \
explainer._regress(weighted_scored_local_sample,
h2o.H2OFrame(pd.DataFrame(row).T))
self.assertEqual(explainer.reason_code_values.shape, (26, 2))
del explainer