Update app.py

app.py

@@ -0,0 +1,79 @@
+#The libraries used
+import gradio as gr
+import pandas as pd
+from transformers import pipeline
+
+
+#Implementing the Hugging Face NER model
+
+ner = pipeline('ner', model = 'FacebookAI/xlm-roberta-large-finetuned-conll03-english', grouped_entities = True)
+
+#Conveting the NER output into a DataFrame:
+
+def entities_to_df(text):
+  all_entities = []
+  #the NER model will be used on the input text
+  entities = ner(text) 
+
+  for entity in entities:
+    all_entities.append({
+          "Entity": entity['word'],
+          "Type" : entity['entity_group'],
+          "Score": float((entity['score'])),
+          "Start": entity['start'],
+          "End": entity['end'],
+          "Sentence": text,
+      })
+
+  df = pd.DataFrame(all_entities)
+  
+  #the df in the output did not round the score above so I rounded it after creating the df
+  df['Score'] = df['Score'].round(4)
+
+  return df
+
+
+#a function to highlight the entitties of the Dataframe using HTML
+def highlight_entities(text):
+    df = entities_to_df(text)
+    highlighted_text = ""
+    last_idx = 0
+    
+    # Iterating between the entities in the DF in order
+    for i, entity in df.iterrows(): #iterrows is a function in the df to iterate by rows
+        # Add the text before the entity
+        highlighted_text += text[last_idx:entity['Start']]
+        
+        #highlighting the entities in RED by using HTML div and css and thiers types(per, org,loc or misc) 
+
+        highlighted_text += f"<div style='background-color: red; display: inline;'>{entity['Entity']} ({entity['Type']})</div>"
+        
+        #updating the index after the current entity
+        last_idx = entity['End']
+    
+    # add the text after the last entity
+    highlighted_text += text[last_idx:]
+    
+    # again we will use an HTML div to make the output looks better :)
+    return f"<div>{highlighted_text}</div>"
+
+# The last function which will combine the two previous functions and will be used in the interface
+def NER_output(text):
+    html = highlight_entities(text)  
+    df = entities_to_df(text)
+    return html,df
+
+#a defualt value that will be used in the gradio interface input
+default_value ="J.K. Rowling wrote the Harry Potter series, which was published by Bloomsbury Publishing."
+
+# Gradio Interface
+demo = gr.Interface(
+    fn=NER_output, 
+    inputs=gr.Textbox(label="Enter text:", lines=6, value = default_value),  
+    outputs=[gr.HTML(label="Entity Visualization"), gr.Dataframe(label="Entities in DataFrame format"),]
+    #above, we used the NER_output, and since that function return the html and the df there will be two outputs
+    #The first is gr.HTML and the second gr.Datagrame
+)
+
+
+demo.launch()