def test_get_sample_data_larger_1k(self):
""" Get sample when data is larger than 1k """
X = pd.DataFrame(np.random.uniform(size=(5763, 31)))
y = pd.Series(np.random.randint(0, 2, size=(5763, )))
X_, y_ = PlotSHAP.get_sample(X, y)
self.assertEqual(X_.shape[0], 1000)
self.assertEqual(y_.shape[0], 1000)
def test_get_sample_data_smaller_1k(self):
""" Get sample when data is smaller than 1k """
SAMPLES = 100
X = pd.DataFrame(np.random.uniform(size=(SAMPLES, 31)))
y = pd.Series(np.random.randint(0, 2, size=(SAMPLES, )))
X_, y_ = PlotSHAP.get_sample(X, y)
self.assertEqual(X_.shape[0], SAMPLES)
self.assertEqual(y_.shape[0], SAMPLES)
def interpret(
self,
X_train,
y_train,
X_validation,
y_validation,
model_file_path,
learner_name,
target_name=None,
class_names=None,
metric_name=None,
ml_task=None,
explain_level=2,
):
# do not produce feature importance for Baseline
if self.algorithm_short_name == "Baseline":
return
if explain_level > 0:
PermutationImportance.compute_and_plot(
self,
X_validation,
y_validation,
model_file_path,
learner_name,
metric_name,
ml_task,
self.params.get("n_jobs", -1)
)
if explain_level > 1:
PlotSHAP.compute(
self,
X_train,
y_train,
X_validation,
y_validation,
model_file_path,
learner_name,
class_names,
ml_task,
)