Update app.py

app.py

@@ -1,13 +1,9 @@
 import streamlit as st
-from sklearn.decomposition import NMF
-from sklearn.feature_extraction.text import CountVectorizer
-from sklearn.pipeline import Pipeline
 from bertopic import BERTopic
 import streamlit.components.v1 as components
 from sentence_transformers import SentenceTransformer
 from umap import UMAP
 from hdbscan import HDBSCAN
-from sklearn.feature_extraction.text import CountVectorizer
 
 # Initialize BERTopic model
 model = BERTopic()
@@ -56,12 +52,14 @@ if button and (uploaded_file is not None or input_text != ""):
 
     # Display top N most representative topics and their documents
     num_topics = st.sidebar.slider("Select number of topics to display", 1, 20, 5, 1)
-    topic_words, topic_docs = model.get_topics(num_topics=num_topics, with_documents=True)
-    for i, topic in enumerate(topic_words):
-        st.write(f"## Topic {i}")
-        st.write("Keywords:", ", ".join(topic))
+    topic_words, topic_docs = model.get_topics(with_documents=True)
+    for i, topic in enumerate(topic_words.items()):
+        if i >= num_topics:
+            break
+        st.write(f"## Topic {topic[0]}")
+        st.write("Keywords:", ", ".join(topic[1]))
         st.write("Documents:")
-        for doc in topic_docs[i][:5]:
+        for doc in topic_docs[topic[0]][:5]:
             st.write("-", texts[doc])
 
     # Display topic clusters