update app layout

README.md

@@ -1,8 +1,8 @@
 ---
-title: Call2vec
-emoji: 🌖
+title: Call2Vec
+emoji: 📲📊
 colorFrom: blue
-colorTo: indigo
+colorTo: green
 sdk: gradio
 sdk_version: 3.0.24
 app_file: app.py

app.py

@@ -10,43 +10,40 @@ from gensim.models.fasttext import load_facebook_model
 
 ACCESS_KEY = os.environ.get('ACCESS_KEY')
 
-# download model from huggingface hub
+
+# Setup model
 url = hf_hub_url(repo_id="simonschoe/call2vec", filename="model.bin")
 cached_download(url)
-
-# load model via gensim
 model = load_facebook_model(cached_download(url))
 
-def process(_input, topn):
+def semantic_search(_input, n):
+    """ Perform semantic search """
 
-    # split by delimiting characters
     _input = re.split('[,;\n]', _input)
-
-    # convert input to lower, replace whitespaces by underscores
     _input = [s.strip().lower().replace(' ', '_') for s in _input if s]
 
     if _input[0] != ACCESS_KEY:
         with open('log.txt', 'a') as f:
             f.write(str(datetime.now()) + '+++' + '___'.join(_input) + '\n')
 
-    # apply model
-    if len(_input)>1:
-        # compute average seed embedding
+    if len(_input) > 1:
         avg_input = np.stack([model.wv[w] for w in _input], axis=0).mean(axis=0)
-        # find similarities
-        nearest_neighbors = model.wv.most_similar(positive=avg_input, topn=topn)
-        frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbors]
+        nearest_neighbours = model.wv.most_similar(positive=avg_input, topn=n)
+        frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbours]
     else:
-        # find similarities
-        nearest_neighbors = model.wv.most_similar(positive=_input[0], topn=topn)
-        frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbors]
-
-    result = pd.DataFrame([(a[0],a[1],b) for a,b in zip(nearest_neighbors, frequencies)], columns=['Token', 'Cosine Similarity', 'Frequency'])
+        nearest_neighbours = model.wv.most_similar(positive=_input[0], topn=n)
+        frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbours]
+    
     if _input[0] == ACCESS_KEY:
         with open('log.txt', 'r') as f:
             prompts = f.readlines()
             prompts = [p.strip().split('+++') for p in prompts]
-        result = pd.DataFrame(prompts, columns=['Time', 'Prompt'])
+        result = pd.DataFrame(prompts,
+                              columns=['Time', 'Prompt'])
+    else:
+        result = pd.DataFrame([(a[0],a[1],b) for a,b in zip(nearest_neighbours, frequencies)],
+                              columns=['Token', 'Cosine Similarity', 'Corpus Frequency'])
+    
     result.to_csv('result.csv')
     return result, 'result.csv', '\n'.join(_input)
 
@@ -58,14 +55,18 @@ demo = gr.Blocks()
 
 with demo:
     gr.Markdown("# Call2Vec")
-    gr.Markdown("## Earnings call transformation project")
+    gr.Markdown("## Subtitle")
     with gr.Row():
         with gr.Column():
-            gr.Markdown("""
+            gr.Markdown(
+                """
                 #### Project Description
-                Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.""")
+                Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
+                """
+            )
             gr.Markdown(
-                """#### App usage:
+                """
+                #### App usage:
                 Add your input prompts to the text field on the right. To use multiple input prompts at once separate
                 them by comma, semicolon or a new line
                 ##### Examples
@@ -74,13 +75,18 @@ with demo:
                 """
             )
         with gr.Column():
-            text_input = gr.Textbox(lines=1)
+            text_in = gr.Textbox(lines=1)
             with gr.Row():
-                n_output = gr.Slider(minimum=5, maximum=50, step=1)
-                compute_button = gr.Button("Compute")
-            df_output = gr.Dataframe(interactive=False)
-            file_out = gr.File(interactive=False)
-
-    compute_button.click(process, inputs=[text_input, n_output], outputs=[df_output, file_out, text_input])
+                n = gr.Slider(minimum=5, maximum=250, step=5)
+                compute_bt = gr.Button("Compute")
+            df_out = gr.Dataframe(interactive=False)
+            f_out = gr.File(interactive=False)
+    gr.Markdown(
+        """
+        <div style='text-align: center;'>Call2Vec by X and Y</center></div>
+        ![visitors](https://visitor-badge.glitch.me/badge?page_id=simonschoe.call2vec&left_color=green&right_color=red)
+        """
+    )
+    compute_bt.click(semantic_search, inputs=[text_in, n], outputs=[df_out, f_out, text_in])
 
 demo.launch()