Update app.py

app.py

@@ -61,7 +61,7 @@ def find_exact_match(df1, df2, column_name):
     matches = pd.merge(df1, df2, on=column_name, how='inner')
     return matches
 
-def find_similar_texts(df1, df2, column_name, threshold=0.3):
+def find_similar_texts(df1, df2, column_name, threshold=0.4):
     # Find rows with similar texts in the specified column, including exact matches
     similar_texts = []
     exact_matches = []
@@ -92,7 +92,7 @@ def find_similar_texts(df1, df2, column_name, threshold=0.3):
                 if similarity_score >= threshold:
                     if similarity == 1:  # Exact match
                         exact_matches.append((i, j, row1[column_name], row2[column_name]))
-                    if  similarity >= threshold and similarity < 1:
+                    if  similarity >= threshold and similarity < 1: #remove same
                         similar_texts.append((i, j, row1[column_name], row2[column_name]))
     
     return similar_texts, exact_matches