Update app.py

app.py

@@ -188,39 +188,39 @@ if file_text:
     with st.expander("📑 Context Table"):
         display_context_table(context_words)
 
-        with st.expander("📝 Sentence Clustering", expanded=True):
-            sentences = [line.strip() for line in text_without_timestamps.split('\n') if len(line.strip()) > 10]
-    
-            num_sentences = len(sentences)
-            st.write(f"Total Sentences: {num_sentences}")
-    
-            num_clusters = st.slider("Number of Clusters", min_value=2, max_value=10, value=5)
-            clustered_sentences = cluster_sentences(sentences, num_clusters)
-    
-            col1, col2 = st.columns(2)
-    
-            with col1:
-                st.subheader("Original Text")
-                original_text = "\n".join(sentences)
-                st.text_area("Original Sentences", value=original_text, height=400)
-    
-            with col2:
-                st.subheader("Clustered Text")
-                clustered_text = ""
-                cluster_high_info_words = get_high_info_words_per_cluster(clustered_sentences)
-    
-                for i, cluster in enumerate(clustered_sentences):
-                    cluster_text = "\n".join(cluster)
-                    high_info_words = ", ".join(cluster_high_info_words[i])
-                    clustered_text += f"Cluster {i+1} (High Info Words: {high_info_words}):\n{cluster_text}\n\n"
-    
-                st.text_area("Clustered Sentences", value=clustered_text, height=400)
-    
-                # Verify that all sentences are accounted for in the clustered output
-                clustered_sentences_flat = [sentence for cluster in clustered_sentences for sentence in cluster]
-                if set(sentences) == set(clustered_sentences_flat):
-                    st.write("✅ All sentences are accounted for in the clustered output.")
-                else:
-                    st.write("❌ Some sentences are missing in the clustered output.")
+    with st.expander("📝 Sentence Clustering", expanded=True):
+        sentences = [line.strip() for line in text_without_timestamps.split('\n') if len(line.strip()) > 10]
+
+        num_sentences = len(sentences)
+        st.write(f"Total Sentences: {num_sentences}")
+
+        num_clusters = st.slider("Number of Clusters", min_value=2, max_value=10, value=5)
+        clustered_sentences = cluster_sentences(sentences, num_clusters)
+
+        col1, col2 = st.columns(2)
+
+        with col1:
+            st.subheader("Original Text")
+            original_text = "\n".join(sentences)
+            st.text_area("Original Sentences", value=original_text, height=400)
+
+        with col2:
+            st.subheader("Clustered Text")
+            clustered_text = ""
+            cluster_high_info_words = get_high_info_words_per_cluster(clustered_sentences)
+
+            for i, cluster in enumerate(clustered_sentences):
+                cluster_text = "\n".join(cluster)
+                high_info_words = ", ".join(cluster_high_info_words[i])
+                clustered_text += f"Cluster {i+1} (High Info Words: {high_info_words}):\n{cluster_text}\n\n"
+
+            st.text_area("Clustered Sentences", value=clustered_text, height=400)
+
+            # Verify that all sentences are accounted for in the clustered output
+            clustered_sentences_flat = [sentence for cluster in clustered_sentences for sentence in cluster]
+            if set(sentences) == set(clustered_sentences_flat):
+                st.write("✅ All sentences are accounted for in the clustered output.")
+            else:
+                st.write("❌ Some sentences are missing in the clustered output.")
 
 st.markdown("For more information and updates, visit our [help page](https://huggingface.co/awacke1).")