lowered bound on noisy count noise

Author: yoid2000

syndiffix/tree.py

@@ -117,7 +117,8 @@ def noisy_count(self) -> int:
             for row in self._matching_rows():
                 row_counter.add(self.context.pid_data[row])
 
-            min_count = anon_context.anonymization_params.low_count_params.low_threshold
+            # min_count = anon_context.anonymization_params.low_count_params.low_threshold
+            min_count = 1
             self._noisy_count_cache = max(row_counter.noisy_count(anon_context), min_count)
 
         return self._noisy_count_cache

tests/clustering/test_measures.py

@@ -20,15 +20,12 @@ def test_measure_all() -> None:
         np.array(
             [
                 [1.00, 0.2, 0.15, 0.02, 0.05],
-                [0.2, 1.00, 0.18, 0.02, 0.05],
+                [0.2, 1.00, 0.18, 0.02, 0.06],
                 [0.15, 0.18, 1.00, 0.04, 0.07],
-                [0.02, 0.02, 0.04, 1.00, 0],
-                [0.05, 0.05, 0.07, 0, 1.00],
+                [0.02, 0.02, 0.04, 1.00, 0.01],
+                [0.05, 0.06, 0.07, 0.01, 1.00],
             ]
         ),
     )
 
-    assert np.array_equal(
-        np.round(measures.entropy_1dim, 3),
-        np.array([16.042, 15.886, 5.398, 0.118, 1.350]),
-    )
+    assert np.array_equal(np.round(measures.entropy_1dim, 3), np.array([9.214, 9.207, 5.160, 0.118, 1.350]))