Update app.py

app.py

@@ -5,20 +5,12 @@ from gensim import corpora, models
 from PIL import Image
 
 # Load the saved models and data
-dictionary = joblib.load('doc2bow.sav')  # Load the dictionary
-lda_model = joblib.load('ldamodel.sav')  # Load the LDA model
+dictionary = joblib.load('doc2bow.sav')
+lda_model = joblib.load('ldamodel.sav')
 
 # Function to preprocess input text and get topic distribution
-def preprocess(text):
-    # Define your preprocessing logic here, as it was in your original code
-    result = []
-    for token in gensim.utils.simple_preprocess(text):
-        if token not in gensim.parsing.preprocessing.STOPWORDS and token not in newStopWords and len(token) > 3:
-            result.append(lemmatize_stemming(token))
-    return result
-
 def get_topics(text):
-    bow_vector = dictionary.doc2bow(preprocess(text))
+    bow_vector = dictionary(text.split())
     topics = lda_model[bow_vector]
     return topics
 
@@ -42,25 +34,20 @@ def main():
     # Submit button
     if st.button("Submit"):
         if user_input:
-            zkata =[]
-            # Masukkan user input ke dalam zkata
-            zkata.append(user_input)
-    
-            # Gabungkan zkata menjadi satu string
-            string = ' '.join([str(item) for item in zkata])
-            tampung_kata = string
-    
-            # Lakukan pemrosesan pada `tampung_kata` dan dictionary
-            bow_vector = dictionary.doc2bow(preprocess(tampung_kata))
-    
-            # Analisis topik
+            # Process the user's input and get topic distribution
+            topics = get_topics(user_input)
+            
+            # Display the top topics
             st.subheader("🔥Top Topics🔥")
-            for index, score in sorted(lda_model[bow_vector], key=lambda tup: -1 * tup[1]):
-                st.write(f"Score: {score}\t Topic: {index + 1} | {lda_model.print_topic(index, 10)}")
+            for topic in topics:
+                st.write(f"**📍Topic {topic[0] + 1}** (Score: {topic[1]:.4f})")
+                top_keywords = get_top_keywords(topic[0])
+                st.markdown(", ".join(top_keywords))
+                st.write("---")
 
     # Add a footer
     st.sidebar.markdown("---")
     st.sidebar.write("© 2023 Web Berita Topic Clustering")
 
 if __name__ == "__main__":
-    main()
+    main()