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,
)
def test_compute_and_plot(self):
rows = 20
X = np.random.rand(rows, 3)
X = pd.DataFrame(X, columns=[f"f{i}" for i in range(3)])
y = np.random.randint(0, 2, rows)
model = XGBClassifier(n_estimators=1, max_depth=2)
model.fit(X, y)
with tempfile.TemporaryDirectory() as tmpdir:
PermutationImportance.compute_and_plot(
model,
X_validation=X,
y_validation=y,
model_file_path=tmpdir,
learner_name="learner_test",
metric_name=None,
ml_task="binary_classification",
)
self.assertTrue(
os.path.exists(
os.path.join(tmpdir, "learner_test_importance.csv")))