Update app.py

app.py

@@ -237,6 +237,30 @@ def format_emotions(emotion_counts):
 def process_and_summarize(df, bert_tokenizer, bert_model, emotion_classifier, top_n=50, topic_strategy="Auto", n_topics=None, min_topic_size=3):
     summaries = []
     
+    topic_model_params = {
+        "language": "arabic",
+        "calculate_probabilities": True,
+        "min_topic_size": min_topic_size,
+        "n_gram_range": (1, 1),
+        "top_n_words": 15,
+        "verbose": True,
+    }
+    
+    if topic_strategy == "Manual":
+        topic_model_params["nr_topics"] = n_topics
+    else:
+        topic_model_params["nr_topics"] = "auto"
+    
+    topic_model = BERTopic(
+        embedding_model=bert_model,
+        **topic_model_params
+    )
+    
+    vectorizer = CountVectorizer(stop_words=list(ARABIC_STOP_WORDS),
+                               min_df=1,
+                               max_df=1.0)
+    topic_model.vectorizer_model = vectorizer
+    
     # Create a placeholder for the progress bar
     progress_placeholder = st.empty()
     progress_bar = progress_placeholder.progress(0)
@@ -286,8 +310,30 @@ def process_and_summarize(df, bert_tokenizer, bert_model, emotion_classifier, to
             except Exception as e:
                 st.warning(f"Error classifying emotion for poem {i+1} in {country}: {str(e)}")
                 continue
-        
-        # Rest of your existing processing code...
+
+        try:
+            if len(texts) < min_topic_size:
+                st.warning(f"Not enough documents for {country} to generate meaningful topics (minimum {min_topic_size} required)")
+                continue
+            
+            topics, probs = topic_model.fit_transform(texts, embeddings)
+            
+            topic_counts = Counter(topics)
+            
+            top_topics = format_topics(topic_model, topic_counts.most_common(top_n))
+            top_emotions = format_emotions(Counter(all_emotions).most_common(top_n))
+            
+            summaries.append({
+                'country': country,
+                'total_poems': len(texts),
+                'top_topics': top_topics,
+                'top_emotions': top_emotions
+            })
+            progress_bar.progress(1.0, text="Processing complete!")
+            
+        except Exception as e:
+            st.warning(f"Could not generate topics for {country}: {str(e)}")
+            continue
         
         # Clear progress for next country
         progress_placeholder.empty()