Use available (or newly created) constants to refer to SSSOM slots.

Author: gouttegd

src/sssom/constants.py

@@ -89,6 +89,7 @@
 MAPPING_SET_SOURCE = "mapping_set_source"
 MAPPING_SOURCE = "mapping_source"
 MAPPING_CARDINALITY = "mapping_cardinality"
+CARDINALITY_SCOPE = "cardinality_scope"
 MAPPING_TOOL = "mapping_tool"
 MAPPING_TOOL_VERSION = "mapping_tool_version"
 MAPPING_DATE = "mapping_date"
@@ -109,6 +110,10 @@
 SUBJECT_SOURCE_ID = "subject_source_id"
 OBJECT_SOURCE_ID = "object_source_id"
 
+# Special value for "unmapped" entities
+# see <https://mapping-commons.github.io/sssom/spec-model/#representing-unmapped-entities>
+NO_TERM_FOUND = "sssom:NoTermFound"
+
 # PREDICATES
 OWL_EQUIVALENT_CLASS = "owl:equivalentClass"
 OWL_EQUIVALENT_PROPERTY = "owl:equivalentProperty"

src/sssom/util.py

@@ -23,12 +23,15 @@
 from sssom_schema import MappingSet, slots
 
 from .constants import (
+    CARDINALITY_SCOPE,
     COLUMN_INVERT_DICTIONARY,
     COMMENT,
     CONFIDENCE,
+    MAPPING_CARDINALITY,
     MAPPING_JUSTIFICATION,
     MAPPING_SET_ID,
     MAPPING_SET_SOURCE,
+    NO_TERM_FOUND,
     OBJECT_CATEGORY,
     OBJECT_ID,
     OBJECT_LABEL,
@@ -437,10 +440,7 @@ def _to_string(row, side):
         # We iterate over the records a first time to collect the different
         # objects mapped to each subject and vice versa
         for _, row in self.df.iterrows():
-            if (
-                row.get("subject_id") == "sssom:NoTermFound"
-                or row.get("object_id") == "sssom:NoTermFound"
-            ):
+            if row.get(SUBJECT_ID) == NO_TERM_FOUND or row.get(OBJECT_ID) == NO_TERM_FOUND:
                 # Mappings to sssom:NoTermFound are ignored for cardinality computations
                 continue
 
@@ -456,12 +456,12 @@ def _to_string(row, side):
         cards = []
         for _, row in self.df.iterrows():
             # Special cases involving sssom:NoTermFound on either side
-            if row.get("subject_id") == "sssom:NoTermFound":
-                if row.get("object_id") == "sssom:NoTermFound":
+            if row.get(SUBJECT_ID) == NO_TERM_FOUND:
+                if row.get(OBJECT_ID) == NO_TERM_FOUND:
                     cards.append("0:0")
                 else:
                     cards.append("0:1")
-            elif row.get("object_id") == "sssom:NoTermFound":
+            elif row.get(OBJECT_ID) == NO_TERM_FOUND:
                 cards.append("1:0")
             else:
                 # General case
@@ -480,12 +480,12 @@ def _to_string(row, side):
                         cards.append("n:n")
 
         # Add the computed values to the dataframe
-        self.df["mapping_cardinality"] = cards
+        self.df[MAPPING_CARDINALITY] = cards
         if len(scope) > 0:
-            self.df["cardinality_scope"] = "|".join(scope)
+            self.df[CARDINALITY_SCOPE] = "|".join(scope)
         else:
             # No scope, so remove any pre-existing "cardinality_scope" column
-            self.df.drop(columns="cardinality_scope", inplace=True, errors="ignore")
+            self.df.drop(columns=CARDINALITY_SCOPE, inplace=True, errors="ignore")
 
 
 def _standardize_curie_or_iri(curie_or_iri: str, *, converter: Converter) -> str:

tests/test_utils.py

@@ -13,6 +13,7 @@
 
 from sssom.constants import (
     CREATOR_ID,
+    MAPPING_CARDINALITY,
     OBJECT_ID,
     OBJECT_LABEL,
     PREDICATE_ID,
@@ -602,10 +603,10 @@ def test_infer_cardinality(self) -> None:
         def _check_against_precomputed_values(filename):
             msdf = parse_sssom_table(f"{data_dir}/{filename}")
             # Expected values are already contained in the test file
-            expected = list(msdf.df["mapping_cardinality"].values)
-            msdf.df.drop(columns="mapping_cardinality", inplace=True)
+            expected = list(msdf.df[MAPPING_CARDINALITY].values)
+            msdf.df.drop(columns=MAPPING_CARDINALITY, inplace=True)
             msdf.infer_cardinality()
-            self.assertEqual(expected, list(msdf.df["mapping_cardinality"].values))
+            self.assertEqual(expected, list(msdf.df[MAPPING_CARDINALITY].values))
 
         _check_against_precomputed_values("cardinality.sssom.tsv")
         _check_against_precomputed_values("cardinality-with-NoTermFound.sssom.tsv")
@@ -617,8 +618,8 @@ def test_infer_scoped_cardinality(self) -> None:
 
         msdf.infer_cardinality(["predicate_id"])
         expected = ["1:n", "1:n", "1:n", "1:n", "1:1", "1:1"]
-        self.assertEqual(expected, list(msdf.df["mapping_cardinality"].values))
+        self.assertEqual(expected, list(msdf.df[MAPPING_CARDINALITY].values))
 
         msdf.infer_cardinality(["object_source"])
         expected = ["1:1", "1:1", "1:1", "1:1", "1:1", "1:1"]
-        self.assertEqual(expected, list(msdf.df["mapping_cardinality"].values))
+        self.assertEqual(expected, list(msdf.df[MAPPING_CARDINALITY].values))