Update src/streamlit_app.py

src/streamlit_app.py

@@ -243,7 +243,7 @@ category_mapping = {
 def load_ner_model():
     """Loads the GLiNER model and caches it."""
     try:
-        return GLiNER.from_pretrained("E3-JSI/gliner-multi-pii-domains-v1", nested_ner=True, num_gen_sequences=2, gen_constraints= labels)
+        return GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0", nested_ner=True, num_gen_sequences=2, gen_constraints= labels)
     except Exception as e:
         st.error(f"Failed to load NER model. Please check your internet connection or model availability: {e}")
         st.stop()
@@ -342,7 +342,20 @@ if st.button("Results"):
                     )
                     st.plotly_chart(fig_bar)
                 
-                
+                # Most Frequent Entities
+                st.subheader("Most Frequent Entities", divider="gray")
+                word_counts = df['text'].value_counts().reset_index()
+                word_counts.columns = ['Entity', 'Count']
+                repeating_entities = word_counts[word_counts['Count'] > 1]
+                if not repeating_entities.empty:
+                    st.dataframe(repeating_entities, use_container_width=True)
+                    fig_repeating_bar = px.bar(repeating_entities, x='Entity', y='Count', color='Entity')
+                    fig_repeating_bar.update_layout(xaxis={'categoryorder': 'total descending'},
+                        paper_bgcolor='#F5F5F5',
+                        plot_bgcolor='#F5F5F5')
+                    st.plotly_chart(fig_repeating_bar)
+                else:
+                    st.warning("No entities were found that occur more than once.")
                 
                 # Download Section
                 st.divider()