Update app.py

app.py

@@ -10,6 +10,10 @@ import os
 from wordcloud import WordCloud
 import matplotlib.pyplot as plt
 import pkg_resources
+import folium
+from folium.plugins import HeatMap
+import country_converter as coco
+from streamlit_folium import folium_static
 
 current_dir = os.path.dirname(os.path.abspath(__file__))
 font_path = os.path.join(current_dir, "ArabicR2013-J25x.ttf")
@@ -89,6 +93,40 @@ def get_cached_embeddings(text, tokenizer, model):
     """Cache embeddings to avoid recomputation"""
     return get_embedding_for_text(text, tokenizer, model)
 
+def create_theme_map(summaries, topic_model):
+    """Create an interactive map showing theme distributions across countries"""
+    # Create a base map centered on the Arab world
+    m = folium.Map(location=[25, 45], zoom_start=4)
+    
+    # Convert country names to coordinates
+    cc = coco.CountryConverter()
+    
+    for summary in summaries:
+        try:
+            # Get country coordinates
+            country_iso = cc.convert(names=[summary['country']], to='ISO2')
+            country_data = cc.convert(names=[summary['country']], to='name_short')
+            
+            # Create popup content with theme information
+            popup_content = f"""
+                <h4>{summary['country']}</h4>
+                <b>Top Themes:</b><br>
+                {'<br>'.join([f"• {topic['topic']}: {topic['count']}" 
+                             for topic in summary['top_topics'][:5]])}
+            """
+            
+            # Add marker for each country
+            folium.CircleMarker(
+                location=[cc.convert(country_iso, to='latitude')[0],
+                         cc.convert(country_iso, to='longitude')[0]],
+                radius=20,
+                popup=folium.Popup(popup_content, max_width=300),
+                color='red',
+                fill=True,
+                fill_opacity=0.7
+            ).add_to(m)
+            
+    return m
 
 def split_text(text, max_length=512):
     """Split text into chunks of maximum token length while preserving word boundaries."""
@@ -430,7 +468,7 @@ if uploaded_file is not None:
                 if summaries:
                     st.success("Analysis complete!")
                     
-                    tab1, tab2 = st.tabs(["Country Summaries", "Global Topics"])
+                    tab1, tab2, tab3 = st.tabs(["Country Summaries", "Global Topics", "Theme Map"])
                     
                     with tab1:
                         for summary in summaries:
@@ -463,7 +501,10 @@ if uploaded_file is not None:
                                 words = topic_model.get_topic(row['Topic'])
                                 topic_name = " | ".join([word for word, _ in words[:5]])
                             st.write(f"• Topic {row['Topic']}: {topic_name} ({row['Count']} poems)")
-    
+                    with tab3:
+                        st.subheader("Thematic Distribution Map")
+                        theme_map = create_theme_map(summaries, topic_model)
+                        folium_static(theme_map)
     except Exception as e:
         st.error(f"Error processing file: {str(e)}")