Calibration: data_to_model_domain call base_model's function

Author: PrimozGodec

Orange/classification/calibration.py

@@ -1,14 +1,19 @@
+from collections import Callable
+
 import numpy as np
 from sklearn.isotonic import IsotonicRegression
 from sklearn.calibration import _SigmoidCalibration
 
 from Orange.classification import Model, Learner
+from Orange.data import Table
 from Orange.evaluation import TestOnTrainingData
 from Orange.evaluation.performance_curves import Curves
 
 __all__ = ["ThresholdClassifier", "ThresholdLearner",
            "CalibratedLearner", "CalibratedClassifier"]
 
+from Orange.util import dummy_callback
+
 
 class ThresholdClassifier(Model):
     """
@@ -31,6 +36,11 @@ def __init__(self, base_model, threshold):
         self.base_model = base_model
         self.threshold = threshold
 
+    def data_to_model_domain(
+            self, data: Table, progress_callback: Callable = dummy_callback
+    ) -> Table:
+        return self.base_model.data_to_model_domain(data, progress_callback)
+
     def __call__(self, data, ret=Model.Value):
         probs = self.base_model(data, ret=Model.Probs)
         if ret == Model.Probs:
@@ -104,6 +114,11 @@ def __init__(self, base_model, calibrators):
         self.calibrators = calibrators
         self.name = f"{base_model.name}, calibrated"
 
+    def data_to_model_domain(
+            self, data: Table, progress_callback: Callable = dummy_callback
+    ) -> Table:
+        return self.base_model.data_to_model_domain(data, progress_callback)
+
     def __call__(self, data, ret=Model.Value):
         probs = self.base_model(data, Model.Probs)
         cal_probs = self.calibrated_probs(probs)

Orange/classification/tests/test_calibration.py

@@ -4,6 +4,7 @@
 import numpy as np
 
 from Orange.base import Model
+from Orange.classification import LogisticRegressionLearner
 from Orange.classification.calibration import \
     ThresholdLearner, ThresholdClassifier, \
     CalibratedLearner, CalibratedClassifier
@@ -65,6 +66,18 @@ def test_non_binary_base(self):
         base_model.domain.class_var.is_discrete = False
         self.assertRaises(ValueError, ThresholdClassifier, base_model, 0.5)
 
+    @staticmethod
+    def test_np_data():
+        """
+        Test ThresholdModel with numpy data.
+        When passing numpy data to model they should be already
+        transformed to models domain since model do not know how to do it.
+        """
+        data = Table('heart_disease')
+        base_learner = LogisticRegressionLearner()
+        model = ThresholdLearner(base_learner)(data)
+        model(model.data_to_model_domain(data).X)
+
 
 class TestThresholdLearner(unittest.TestCase):
     @patch("Orange.evaluation.performance_curves.Curves.from_results")
@@ -166,6 +179,18 @@ def test_calibrated_probs(self):
         calprobs = self.model.calibrated_probs(self.probs)
         np.testing.assert_almost_equal(calprobs, expprobs)
 
+    @staticmethod
+    def test_np_data():
+        """
+        Test CalibratedClassifier with numpy data.
+        When passing numpy data to model they should be already
+        transformed to models domain since model do not know how to do it.
+        """
+        data = Table('heart_disease')
+        base_learner = LogisticRegressionLearner()
+        model = CalibratedLearner(base_learner)(data)
+        model(model.data_to_model_domain(data).X)
+
 
 class TestCalibratedLearner(unittest.TestCase):
     @patch("Orange.classification.calibration._SigmoidCalibration.fit")
@@ -201,3 +226,7 @@ def test_fit_storage(self, test_on_training, sigmoid_fit):
         for call, cls_probs in zip(sigmoid_fit.call_args_list,
                                    res.probabilities[0].T):
             np.testing.assert_equal(call[0][0], cls_probs)
+
+
+if __name__ == "__main__":
+    unittest.main()