Make similarity cutoff stricter

bioinfodlsu · Sep 5, 2023 · be73b66 · be73b66
1 parent 5f80d28
commit be73b66
Showing 1 changed file with 1 addition and 4 deletions.
diff --git a/callbacks/text_mining/util.py b/callbacks/text_mining/util.py
@@ -10,8 +10,7 @@
 
 
 COLNAMES = ['Gene', 'PMID', 'Title', 'Sentence', 'Score']
-SIMILARITY_CUTOFF = 75
-MAX_NUM_RESULTS = 100
+SIMILARITY_CUTOFF = 85
 
 
 def sanitize_text(text):
@@ -177,8 +176,6 @@ def text_mining_query_search(query_string):
                         df.loc[len(df.index)] = [Entity, PMID,
                                                  Title, Sentence, similarity.score]
 
-                        if df.shape[0] == MAX_NUM_RESULTS:
-                            break
             except:
                 pass