CU-2exy49p: Make sure the cdb.add_concept really adds a concept or somehow make it clear

medcat/cat.py

@@ -834,7 +834,7 @@ def add_and_train_concept(self,
         names = prepare_name(name, self.pipe.spacy_nlp, {}, self.config)
         # Only if not negative, otherwise do not add the new name if in fact it should not be detected
         if do_add_concept and not negative:
-            self.cdb.add_concept(cui=cui, names=names, ontologies=ontologies, name_status=name_status, type_ids=type_ids, description=description,
+            self.cdb._add_concept(cui=cui, names=names, ontologies=ontologies, name_status=name_status, type_ids=type_ids, description=description,
                                  full_build=full_build)
 
         if spacy_entity is not None and spacy_doc is not None:

medcat/cdb.py

@@ -12,6 +12,7 @@
 from medcat.utils.hasher import Hasher
 from medcat.utils.matutils import unitvec
 from medcat.utils.ml_utils import get_lr_linking
+from medcat.utils.decorators import deprecated
 from medcat.config import Config, weighted_average, workers
 from medcat.utils.saving.serializer import CDBSerializer
 
@@ -213,8 +214,9 @@ def add_names(self, cui: str, names: Dict, name_status: str = 'A', full_build: b
             # Name status must be one of the three
             name_status = 'A'
 
-        self.add_concept(cui=cui, names=names, ontologies=set(), name_status=name_status, type_ids=set(), description='', full_build=full_build)
+        self._add_concept(cui=cui, names=names, ontologies=set(), name_status=name_status, type_ids=set(), description='', full_build=full_build)
 
+    @deprecated("Use `cdb._add_concept` as this will be removed in a future release.")
     def add_concept(self,
                     cui: str,
                     names: Dict,
@@ -223,6 +225,43 @@ def add_concept(self,
                     type_ids: Set[str],
                     description: str,
                     full_build: bool = False) -> None:
+        """
+        Deprecated: Use `cdb._add_concept` as this will be removed in a future release.
+
+        Add a concept to internal Concept Database (CDB). Depending on what you are providing
+        this will add a large number of properties for each concept.
+
+        Args:
+            cui (str):
+                Concept ID or unique identifier in this database, all concepts that have
+                the same CUI will be merged internally.
+            names (Dict[str, Dict]):
+                Names for this concept, or the value that if found in free text can be linked to this concept.
+                Names is a dict like: `{name: {'tokens': tokens, 'snames': snames, 'raw_name': raw_name}, ...}`
+                Names should be generated by helper function 'medcat.preprocessing.cleaners.prepare_name'
+            ontologies (Set[str]):
+                ontologies in which the concept exists (e.g. SNOMEDCT, HPO)
+            name_status (str):
+                One of `P`, `N`, `A`
+            type_ids (Set[str]):
+                Semantic type identifier (have a look at TUIs in UMLS or SNOMED-CT)
+            description (str):
+                Description of this concept.
+            full_build (bool):
+                If True the dictionary self.addl_info will also be populated, contains a lot of extra information
+                about concepts, but can be very memory consuming. This is not necessary
+                for normal functioning of MedCAT (Default Value `False`).
+        """
+        self._add_concept(cui, names, ontologies, name_status, type_ids, description, full_build)
+
+    def _add_concept(self,
+                    cui: str,
+                    names: Dict,
+                    ontologies: set,
+                    name_status: str,
+                    type_ids: Set[str],
+                    description: str,
+                    full_build: bool = False) -> None:
         """Add a concept to internal Concept Database (CDB). Depending on what you are providing
         this will add a large number of properties for each concept.
 
@@ -232,7 +271,8 @@ def add_concept(self,
                 the same CUI will be merged internally.
             names (Dict[str, Dict]):
                 Names for this concept, or the value that if found in free text can be linked to this concept.
-                Names is an dict like: `{name: {'tokens': tokens, 'snames': snames, 'raw_name': raw_name}, ...}`
+                Names is a dict like: `{name: {'tokens': tokens, 'snames': snames, 'raw_name': raw_name}, ...}`
+                Names should be generated by helper function 'medcat.preprocessing.cleaners.prepare_name'
             ontologies (Set[str]):
                 ontologies in which the concept exists (e.g. SNOMEDCT, HPO)
             name_status (str):

medcat/cdb_maker.py

@@ -173,7 +173,7 @@ def prepare_csvs(self,
                             if len(raw_name) >= self.config.cdb_maker['remove_parenthesis']:
                                 prepare_name(raw_name, self.pipe.spacy_nlp, names, self.config)
 
-                    self.cdb.add_concept(cui=cui, names=names, ontologies=ontologies, name_status=name_status, type_ids=type_ids,
+                    self.cdb._add_concept(cui=cui, names=names, ontologies=ontologies, name_status=name_status, type_ids=type_ids,
                                          description=description, full_build=full_build)
                     # DEBUG
                     logger.debug("\n\n**** Added\n CUI: %s\n Names: %s\n Ontologies: %s\n Name status: %s\n Type IDs: %s\n Description: %s\n Is full build: %s",

tests/archive_tests/test_cdb_maker_archive.py

@@ -108,7 +108,7 @@ def test_concept_similarity(self):
         for i in range(500):
             cui = "C" + str(i)
             type_ids = {'T-' + str(i%10)}
-            cdb.add_concept(cui=cui, names=prepare_name('Name: ' + str(i), self.maker.pipe.get_spacy_nlp(), {}, self.config), ontologies=set(),
+            cdb._add_concept(cui=cui, names=prepare_name('Name: ' + str(i), self.maker.pipe.get_spacy_nlp(), {}, self.config), ontologies=set(),
                             name_status='P', type_ids=type_ids, description='', full_build=True)
 
             vectors = {}

tests/utils/test_hashing.py

@@ -90,7 +90,7 @@ class CATHashingTestsWithChange(CATHashingTestsWithFakeHash):
 
     def test_when_changes_do_calc(self):
         with unittest.mock.patch.object(CDB, 'calculate_hash', return_value='abcd1234') as patch_method:
-            self.undertest.cdb.add_concept(**self.concept_kwargs)
+            self.undertest.cdb._add_concept(**self.concept_kwargs)
             hash = self.undertest.get_hash()
         self.assertIsInstance(hash, str)
         patch_method.assert_called()
@@ -106,10 +106,10 @@ def test_default_cdb_not_dirty(self):
         self.assertFalse(self.undertest.cdb.is_dirty)
 
     def test_after_add_concept_is_dirty(self):
-        self.undertest.cdb.add_concept(**self.concept_kwargs)
+        self.undertest.cdb._add_concept(**self.concept_kwargs)
         self.assertTrue(self.undertest.cdb.is_dirty)
 
     def test_after_recalc_not_dirty(self):
-        self.undertest.cdb.add_concept(**self.concept_kwargs)
+        self.undertest.cdb._add_concept(**self.concept_kwargs)
         self.undertest.get_hash()
         self.assertFalse(self.undertest.cdb.is_dirty)