Refactor unit mapping in prediction process by replacing UnitMapper with UnitSimilarityMapper for improved similarity calculations and error handling.

data/cached_similar_items_bygroup_abstractsimilaritymapper.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8547d21d9847e0191da9528f627c36fdbbf46fae340de39757fd37fa978a1fa
+size 98091

data/cached_similar_items_bygroup_namesimilaritymapper.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5aeb712d1a1ae09dd07d53e5415eb4dd17647c4927972897455db956f44adba
+size 400757

data/cached_similar_items_bygroup_subsubjectsimilaritymapper.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a090da26e03a6aca5526c6f4c41050c8b5a6c83a01943cece7384d9ddb6d048e
+size 13311

data/cached_similar_items_subjectsimilaritymapper.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231bd962fe784389cefac613f0597e26510501506e434355668dce03da620560
+size 4116

data/cached_similar_items_unitsimilaritymapper.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27482a66588006f51733369ca6dd41065669318b5f845439d80437695644a142
+size 2301

routes/predict.py

@@ -20,7 +20,7 @@ from mapping_lib.name_similarity_mapper import NameSimilarityMapper
 from mapping_lib.sub_subject_and_name_data_mapper import SubSubjectAndNameDataMapper
 from mapping_lib.abstract_similarity_mapper import AbstractSimilarityMapper
 from mapping_lib.name_and_abstract_mapper import NameAndAbstractDataMapper
-from mapping_lib.unit_mapper import UnitMapper
+from mapping_lib.unit_similarity_mapper import UnitSimilarityMapper
 from mapping_lib.standard_name_mapper import StandardNameMapper
 
 from config import UPLOAD_DIR, OUTPUT_DIR
@@ -227,7 +227,7 @@ async def predict(
         try:
             # Unit mapping
             if sentence_service.df_unit_map_data is not None:
-                unit_mapper = UnitMapper(
+                unit_mapper = UnitSimilarityMapper(
                     cached_embedding_helper=sentence_service.unit_cached_embedding_helper,
                     df_map_data=sentence_service.df_unit_map_data,
                 )
@@ -505,14 +505,14 @@ async def predict_raw(
         try:
             # Unit mapping
             if sentence_service.df_unit_map_data is not None:
-                unit_mapper = UnitMapper(
+                unit_mapper = UnitSimilarityMapper(
                     cached_embedding_helper=sentence_service.unit_cached_embedding_helper,
                     df_map_data=sentence_service.df_unit_map_data,
                 )
                 unit_mapper.predict_input(df_input_data=df_input_data)
 
         except Exception as e:
-            print(f"Error processing UnitMapper: {e}")
+            print(f"Error processing UnitSimilarityMapper: {e}")
             raise HTTPException(status_code=500, detail=str(e))
 
         # Ensure required columns exist