Add suggestions from code review

* Rename 'true' parameter to 'data' in 'target_func' method.
* Remove setting random_state in run function during tests.
* Add explicit haz_type to tests to avoid warnings.

Author: peanutfun

climada/test/test_util_calibrate.py

@@ -63,6 +63,7 @@ def setUp(self) -> None:
                     mdd=np.array([0, 10 * slope]),
                     paa=np.ones(2),
                     id=1,
+                    haz_type="TEST",
                 )
             ]
         )
@@ -106,6 +107,7 @@ def test_multiple_constrained(self):
                     mdd=np.array([0, 1, 3]),
                     paa=np.ones(3),
                     id=1,
+                    haz_type="TEST",
                 )
             ]
         )
@@ -155,6 +157,7 @@ def setUp(self) -> None:
                     mdd=np.array([0, 10 * slope]),
                     paa=np.ones(2),
                     id=1,
+                    haz_type="TEST",
                 )
             ]
         )
@@ -170,8 +173,8 @@ def setUp(self) -> None:
     def test_single(self):
         """Test with single parameter"""
         self.input.bounds = {"slope": (-1, 3)}
-        optimizer = BayesianOptimizer(self.input)
-        output = optimizer.run(init_points=10, n_iter=20, random_state=1)
+        optimizer = BayesianOptimizer(self.input, random_state=1)
+        output = optimizer.run(init_points=10, n_iter=20)
 
         # Check result (low accuracy)
         self.assertAlmostEqual(output.params["slope"], 1.0, places=2)
@@ -189,6 +192,7 @@ def test_multiple_constrained(self):
                     mdd=np.array([0, 1, 3]),
                     paa=np.ones(3),
                     id=1,
+                    haz_type="TEST",
                 )
             ]
         )
@@ -199,8 +203,8 @@ def test_multiple_constrained(self):
         )
         self.input.bounds = {"intensity_1": (-1, 4), "intensity_2": (-1, 4)}
         # Run optimizer
-        optimizer = BayesianOptimizer(self.input)
-        output = optimizer.run(n_iter=200, random_state=1)
+        optimizer = BayesianOptimizer(self.input, random_state=1)
+        output = optimizer.run(n_iter=200)
 
         # Check results (low accuracy)
         self.assertEqual(output.p_space.dim, 2)
@@ -230,8 +234,8 @@ def test_multiple_constrained(self):
     def test_plots(self):
         """Check if executing the default plots works"""
         self.input.bounds = {"slope": (-1, 3)}
-        optimizer = BayesianOptimizer(self.input)
-        output = optimizer.run(init_points=10, n_iter=20, random_state=1)
+        optimizer = BayesianOptimizer(self.input, random_state=1)
+        output = optimizer.run(init_points=10, n_iter=20)
 
         output_eval = OutputEvaluator(self.input, output)
         output_eval.impf_set.plot()

climada/util/calibrate/base.py

@@ -379,16 +379,16 @@ class Optimizer(ABC):
 
     input: Input
 
-    def _target_func(self, true: pd.DataFrame, predicted: pd.DataFrame) -> Number:
+    def _target_func(self, data: pd.DataFrame, predicted: pd.DataFrame) -> Number:
         """Target function for the optimizer
 
         The default version of this function simply returns the value of the cost
         function evaluated on the arguments.
 
         Parameters
         ----------
-        true : pandas.DataFrame
-            The "true" data used for calibration. By default, this is
+        data : pandas.DataFrame
+            The reference data used for calibration. By default, this is
             :py:attr:`Input.data`.
         predicted : pandas.DataFrame
             The impact predicted by the data calibration after it has been transformed
@@ -398,7 +398,7 @@ def _target_func(self, true: pd.DataFrame, predicted: pd.DataFrame) -> Number:
         -------
         The value of the target function for the optimizer.
         """
-        return self.input.cost_func(true, predicted)
+        return self.input.cost_func(data, predicted)
 
     def _kwargs_to_impact_func_creator(self, *_, **kwargs) -> Dict[str, Any]:
         """Define how the parameters to :py:meth:`_opt_func` must be transformed

climada/util/calibrate/bayesian_optimizer.py

@@ -249,9 +249,9 @@ def __post_init__(
             **bayes_opt_kwds,
         )
 
-    def _target_func(self, true: pd.DataFrame, predicted: pd.DataFrame) -> Number:
+    def _target_func(self, data: pd.DataFrame, predicted: pd.DataFrame) -> Number:
         """Invert the cost function because BayesianOptimization maximizes the target"""
-        return -self.input.cost_func(true, predicted)
+        return -self.input.cost_func(data, predicted)
 
     def run(self, **opt_kwargs) -> BayesianOptimizerOutput:
         """Execute the optimization

climada/util/calibrate/test/test_base.py

@@ -48,7 +48,9 @@ def hazard():
     centroids = Centroids.from_lat_lon(lat=lat, lon=lon)
     event_id = np.array([1, 3, 10])
     intensity = csr_matrix([[1, 0.1], [2, 0.2], [3, 2]])
-    return Hazard(event_id=event_id, centroids=centroids, intensity=intensity)
+    return Hazard(
+        event_id=event_id, centroids=centroids, intensity=intensity, haz_type="TEST"
+    )
 
 
 def exposure():
@@ -58,7 +60,7 @@ def exposure():
             longitude=[0, 1, 100],
             latitude=[1, 2, 50],
             value=[1, 0.1, 1e6],
-            impf_=[1, 1, 1],
+            impf_TEST=[1, 1, 1],
         )
     )
 
@@ -124,9 +126,8 @@ def test_post_init(self):
             impact_to_dataframe=self.impact_to_dataframe,
         )
 
-        # Check hazard and exposure
-        self.assertIn("centr_", input.exposure.gdf)
-        npt.assert_array_equal(input.exposure.gdf["centr_"], [0, 1, -1])
+        # Check centroids assignment
+        npt.assert_array_equal(input.exposure.gdf["centr_TEST"], [0, 1, -1])
 
     def test_align_impact(self):
         """Check alignment of impact and data"""
@@ -237,9 +238,7 @@ def test_init(self, mock):
         self.assertEqual(out_eval._impact_label, "Impact [my_unit]")
 
         self.input.impact_func_creator.assert_called_with(p1=1, p2=2.0)
-        mock.assert_called_with(
-            self.input.exposure, "impact_func", self.input.hazard
-        )
+        mock.assert_called_with(self.input.exposure, "impact_func", self.input.hazard)
 
 
 # Execute Tests

climada/util/calibrate/test/test_bayesian_optimizer.py

@@ -28,6 +28,7 @@
 
 from .test_base import hazard, exposure
 
+
 class TestBayesianOptimizer(unittest.TestCase):
     """Tests for the optimizer based on bayes_opt.BayesianOptimization"""
 

climada/util/calibrate/test/test_scipy_optimizer.py

@@ -140,6 +140,7 @@ def assert_bounds_in_call(bounds: Optional[List]):
         minimize_mock.assert_called_once()
         assert_bounds_in_call(bounds=[None, "a", (1, 2)])
 
+
 # Execute Tests
 if __name__ == "__main__":
     TESTS = unittest.TestLoader().loadTestsFromTestCase(TestScipyMinimizeOptimizer)