Upload app.py

app.py

@@ -101,10 +101,6 @@ plain: /([^,\\\[\]():|]|\\.)+/
 # Initialize the parser
 parser = Lark(grammar, start='start')
 
-
-special_tags = ["score:0", "score:1", "score:2", "score:3", "score:4", "score:5", "score:6", "score:7", "score:8", "score:9"]
-
-
 # Function to extract tags
 def extract_tags(tree):
     tags = []
@@ -118,6 +114,14 @@ def extract_tags(tree):
     _traverse(tree)
     return tags
 
+
+special_tags = ["score:0", "score:1", "score:2", "score:3", "score:4", "score:5", "score:6", "score:7", "score:8", "score:9"]
+def remove_special_tags(original_string):
+    tags = [tag.strip() for tag in original_string.split(",")]
+    remaining_tags = [tag for tag in tags if tag not in special_tags]
+    removed_tags = [tag for tag in tags if tag in special_tags]
+    return ", ".join(remaining_tags), removed_tags
+    
     
 # Load the model and data once at startup
 with h5py.File('complete_artist_data.hdf5', 'r') as f:
@@ -283,6 +287,8 @@ def find_similar_tags(test_tags, similarity_weight):
 def find_similar_artists(new_tags_string, top_n, similarity_weight):
     try:
         new_tags_string = new_tags_string.lower()
+        new_tags_string, removed_tags = remove_special_tags(new_tags_string)
+        
         # Parse the prompt
         parsed = parser.parse(new_tags_string)
         # Extract tags from the parsed tree
@@ -292,7 +298,7 @@ def find_similar_artists(new_tags_string, top_n, similarity_weight):
         ###unseen_tags = list(set(OrderedDict.fromkeys(new_image_tags)) - set(vectorizer.vocabulary_.keys()))   #We may want this line again later.  These are the tags that were not used to calculate the artists list.
         unseen_tags_data = find_similar_tags(new_image_tags, similarity_weight)
 
-        X_new_image = vectorizer.transform([','.join(new_image_tags)])
+        X_new_image = vectorizer.transform([','.join(new_image_tags + removed_tags)])
         similarities = cosine_similarity(X_new_image, X_artist)[0]
 
         top_artist_indices = np.argsort(similarities)[-top_n:][::-1]