Update app.py

app.py

@@ -108,7 +108,6 @@ def load_example_files():
     
     return None
 
-
 def cluster_sentences(sentences, num_clusters):
     # Filter sentences with length over 10 characters
     sentences = [sentence for sentence in sentences if len(sentence) > 10]
@@ -142,7 +141,6 @@ def cluster_sentences(sentences, num_clusters):
     # Return the ordered clustered sentences without similarity scores for display
     return [[sentence for _, sentence in cluster] for cluster in clustered_sentences]
 
-    
 # Function to convert text to a downloadable file
 def get_text_file_download_link(text_to_download, filename='Output.txt', button_label="💾 Save"):
     buffer = BytesIO()
@@ -152,6 +150,14 @@ def get_text_file_download_link(text_to_download, filename='Output.txt', button_
     href = f'<a href="data:file/txt;base64,{b64}" download="{filename}" style="margin-top:20px;">{button_label}</a>'
     return href
 
+def get_high_info_words_per_cluster(cluster_sentences, num_words=5):
+    cluster_high_info_words = []
+    for cluster in cluster_sentences:
+        cluster_text = " ".join(cluster)
+        high_info_words = extract_high_information_words(cluster_text, num_words)
+        cluster_high_info_words.append(high_info_words)
+    return cluster_high_info_words
+
 # Main code for UI
 uploaded_file = st.file_uploader("📁 Choose a .txt file", type=['txt'])
 
@@ -188,17 +194,23 @@ if file_text:
         num_clusters = st.slider("Number of Clusters", min_value=2, max_value=10, value=5)
         clustered_sentences = cluster_sentences(sentences, num_clusters)
 
-        for i, cluster in enumerate(clustered_sentences):
-            st.subheader(f"Cluster {i+1}")
-            cluster_text = "\n".join(cluster)
-            st.text_area(f"Cluster {i+1} Sentences", value=cluster_text, height=200)
-            
-            # Input for custom filename
-            default_filename = f"Cluster_{i+1}_Output.txt"
-            filename = st.text_input("Enter filename for download:", value=default_filename, key=f"filename_{i}")
-            
-            # Download button
-            download_link = get_text_file_download_link(cluster_text, filename, f"💾 Save Cluster {i+1}")
-            st.markdown(download_link, unsafe_allow_html=True)
+        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)
 
 st.markdown("For more information and updates, visit our [help page](https://huggingface.co/awacke1).")