Upload 4 files

app.py

@@ -181,7 +181,7 @@ def load_model_components(file_path):
     
     return model_components
 # Load all components at the start
-tf_idf_components = load_model_components('tf_idf_files_418.joblib')
+tf_idf_components = load_model_components('tf_idf_files_420.joblib')
     
 # Load the model and data once at startup
 with h5py.File('complete_artist_data.hdf5', 'r') as f:
@@ -670,24 +670,30 @@ def find_similar_artists(original_tags_string, top_n, similarity_weight, allow_n
         suggested_tags_html_content = "<div class=\"scrollable-content\" style='display: inline-block; margin: 20px; text-align: center;'>"
 
         suggested_tags_html_content += "<h1>Suggested Tags</h1>"  # Heading for the table
-        suggested_tags = get_tfidf_reduced_similar_tags([item["tf_idf_matrix_tag"] for item in tag_data], allow_nsfw_tags)
+        suggested_tags = get_tfidf_reduced_similar_tags([item["tf_idf_matrix_tag"] for item in tag_data] + removed_tags, allow_nsfw_tags)
         
         # Create a set of tags that should be filtered out
         filter_tags = {entry["original_tag"].strip() for entry in tag_data}
         # Use this set to filter suggested_tags
         suggested_tags_filtered = OrderedDict((k, v) for k, v in suggested_tags.items() if k not in filter_tags)
-       
-        topnsuggestions = list(islice(suggested_tags_filtered.items(), 100))
+        
+        # Splitting the dictionary into two based on the condition
+        suggested_artist_tags_filtered = OrderedDict((k, v) for k, v in suggested_tags_filtered.items() if k.startswith("by "))
+        suggested_non_artist_tags_filtered = OrderedDict((k, v) for k, v in suggested_tags_filtered.items() if not k.startswith("by ") and k not in special_tags)
+
+        topnsuggestions = list(islice(suggested_non_artist_tags_filtered.items(), 100))
         suggested_tags_html_content += create_html_tables_for_tags("Suggested Tag", topnsuggestions, find_similar_tags.tag2count, find_similar_tags.tag2idwiki)
 
         #Artist stuff
-        artist_matrix_tags = [tag_info['artist_matrix_tag'] for tag_info in tag_data if tag_info['node_type'] == "tag"]
-        X_new_image = vectorizer.transform([','.join(artist_matrix_tags + removed_tags)])
-        similarities = cosine_similarity(X_new_image, X_artist)[0]
-
-        top_artist_indices = np.argsort(similarities)[-(top_n + 1):][::-1]
-        top_artists = [(artist_names[i], similarities[i]) for i in top_artist_indices if artist_names[i].lower() != "by conditional dnp"][:top_n]
-        
+        #artist_matrix_tags = [tag_info['artist_matrix_tag'] for tag_info in tag_data if tag_info['node_type'] == "tag"]
+        #X_new_image = vectorizer.transform([','.join(artist_matrix_tags + removed_tags)])
+        #similarities = cosine_similarity(X_new_image, X_artist)[0]
+        #
+        #top_artist_indices = np.argsort(similarities)[-(top_n + 1):][::-1]
+        #top_artists = [(artist_names[i], similarities[i]) for i in top_artist_indices if artist_names[i].lower() != "by conditional dnp"][:top_n]
+
+        excluded_artists = ["by conditional dnp", "by unknown artist"]
+        top_artists = [(key, value) for key, value in  suggested_artist_tags_filtered.items() if key.lower() not in excluded_artists][:top_n]
         top_artists_str = create_top_artists_table(top_artists)
         dynamic_prompts_formatted_artists = "{" + "|".join([artist for artist, _ in top_artists]) + "}"
 
@@ -712,7 +718,7 @@ with gr.Blocks(css=css) as app:
             with gr.Column(scale=1):
                 #image_path = os.path.join("https://huggingface.co/spaces/FoodDesert/Prompt_Squirrel/resolve/main", "transparentsquirrel.png")
                 #gr.Image(label=" ", value=image_path, height=155, width=140)
-                #gr.HTML('<div style="text-align: center;"><img src={image_path} alt="Cute Mascot" style="max-height: 100px; background: transparent;"></div><br>')
+                gr.HTML('<div style="text-align: center;"><img src="https://huggingface.co/spaces/FoodDesert/Prompt_Squirrel/resolve/main/mascotimages/transparentsquirrel.png" alt="Cute Mascot" style="max-height: 180px; background: transparent;"></div><br>')
                 #gr.HTML("<br>" * 2)  # Adjust the number of line breaks ("<br>") as needed to push the button down
                 #image_path = os.path.join('mascotimages', "transparentsquirrel.png") 
                 #random_image_path = os.path.join('mascotimages', random.choice([f for f in os.listdir('mascotimages') if os.path.isfile(os.path.join('mascotimages', f))]))
@@ -720,7 +726,7 @@ with gr.Blocks(css=css) as app:
                 #    gr.Image(value=img,show_label=False, show_download_button=False, show_share_button=False, height=200)
                 #gr.Image(value="https://huggingface.co/spaces/FoodDesert/Prompt_Squirrel/resolve/main/mascotimages/transparentsquirrel.png",show_label=False, show_download_button=False, show_share_button=False, height=200)
                 #I posted the image to discord, and that's where this link came from.  This is a very ugly way to do this, but I could not, no matter what I tried, get it to display an image from within the space itself.  The galleries work fine for some reason, but not this.
-                gr.Image(value="https://res.cloudinary.com/dnse84ol6/image/upload/v1713538125/transparentsquirrel_zhou7f.png",show_label=False, show_download_button=False, show_share_button=False, height=200)
+                #gr.Image(value="https://res.cloudinary.com/dnse84ol6/image/upload/v1713538125/transparentsquirrel_zhou7f.png",show_label=False, show_download_button=False, show_share_button=False, height=200)
                 submit_button = gr.Button(variant="primary")
     with gr.Row():
         with gr.Column(scale=3):    

tf_idf_files_420.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3d2a7d71a6ca70cb7012885e6102bd13530872726320ba6798365089f16b3e
+size 108548478