Upload app.py

app.py

@@ -65,7 +65,7 @@ Both of these features are extracted from the tag wiki pages, but some valid e62
 
 Yes.  We normalized the favorite counts of each image to a range of 0-9, with 0 being the lowest favcount, and 9 being the highest.
 You can include any of these special tags: "score:0", "score:1", "score:2", "score:3", "score:4", "score:5", "score:6", "score:7", "score:8", "score:9"
-in your list to bias the output toward artists with higher or lower scoring images.  Since they are not real tags, the Unseen Tags section will complain, but you can ignore that.
+in your list to bias the output toward artists with higher or lower scoring images.
 
 ## Are there any other special tricks?
 
@@ -134,7 +134,8 @@ def extract_tags(tree):
     def _traverse(node):
         if isinstance(node, Token) and node.type == '__ANON_1':
             tag_position = node.start_pos
-            tag_text = node.value.strip()
+            #tag_text = node.value.strip()
+            tag_text = node.value
             tags_with_positions.append((tag_text, tag_position))
         elif not isinstance(node, Token):
             for child in node.children:
@@ -419,10 +420,8 @@ def find_similar_tags(test_tags, similarity_weight, allow_nsfw_tags):
         start_pos = tag_info['start_pos']
         end_pos = tag_info['end_pos']
         
+        #print(original_tag, modified_tag, start_pos, end_pos)
         
-        print(original_tag, modified_tag, start_pos, end_pos)
-        
-
         if modified_tag in special_tags:
             continue
             
@@ -464,7 +463,7 @@ def find_similar_tags(test_tags, similarity_weight, allow_nsfw_tags):
         result = sorted(result, key=lambda x: x[1], reverse=True)[:10]
         html_content += create_html_tables_for_tags(modified_tag, result, find_similar_tags.tag2count, find_similar_tags.tag2idwiki)
         
-        bad_entities.append({"entity":"UNKNOWN", "start":start_pos, "end":end_pos})
+        bad_entities.append({"entity":"*", "start":start_pos, "end":end_pos})
         
         tags_added=True
     # If no tags were processed, add a message
@@ -507,6 +506,7 @@ def find_similar_artists(original_tags_string, top_n, similarity_weight, allow_n
         unseen_tags_data, bad_entities = find_similar_tags(tag_data, similarity_weight, allow_nsfw_tags)
         
         bad_tags_illustrated_string = {"text":new_tags_string, "entities":bad_entities}
+        #bad_tags_illustrated_string = {"text":original_tags_string, "entities":bad_entities}
 
         modified_tags = [tag_info['modified_tag'] for tag_info in tag_data]
         X_new_image = vectorizer.transform([','.join(modified_tags + removed_tags)])
@@ -541,7 +541,7 @@ with gr.Blocks() as app:
             num_artists = gr.Slider(minimum=1, maximum=100, value=10, step=1, label="Number of artists")
             allow_nsfw = gr.Checkbox(label="Allow NSFW Tags", value=False)
     with gr.Row():
-        bad_tags_illustrated_string = gr.HighlightedText()
+        bad_tags_illustrated_string = gr.HighlightedText(label="Visual depiction of bad tags. Character offsets may be buggy.")
     with gr.Row():
         with gr.Column(scale=1):
             top_artists = gr.HTML(label="Top Artists", value=create_html_placeholder(title="Top Artists"))