Update app.py

app.py

@@ -53,6 +53,11 @@ def print_topics(lda, vectorizer, num_words=10):
         topics.append(f"Topic #{index + 1}: {', '.join(top_terms)}")
     return topics
 
+def display_document_topic_distribution(topic_proportions):
+    topic_df = pd.DataFrame(topic_proportions, columns=[f"Topic {i+1}" for i in range(topic_proportions.shape[1])])
+    topic_df['Dominant Topic'] = topic_df.idxmax(axis=1)
+    return topic_df
+
 # Streamlit UI
 st.title("Text Analysis and Topic Modeling")
 st.write("Upload a CSV file containing a column with text data.")
@@ -92,3 +97,8 @@ if uploaded_file:
     avg_topic_proportions = topic_proportions.mean(axis=0)
     st.subheader("Topic Proportions")
     plot_topic_proportions(avg_topic_proportions, lda.components_.shape[0])
+    
+    # Display document topic distribution
+    st.subheader("Document Topic Distribution")
+    document_topic_distribution = display_document_topic_distribution(topic_proportions)
+    st.write(document_topic_distribution.head())