Update app.py

app.py

@@ -6,7 +6,7 @@ classifier = pipeline("text-classification", model='Ryleeeee/CustomSentimentMode
 
 # Streamlit application title and background image
 st.image("./header.png", use_column_width=True)
-st.title("Step 1: Sentiment Analysis")
+st.title("Step 1: Sentiment Analysis", use_column_width=True)
 
 st.write("Sentiment classification: positive, neutral, negative")
 
@@ -16,16 +16,16 @@ text = st.text_area("Enter the customer review", "")
 # Perform sentiment analysis when the user clicks the "Classify sentiment" button
 if st.button("Classify sentiment"):
     # Perform sentiment analysis on the input text
-    results = classifier(text)[0]['scores']
+    results = classifier(text)[0]
 
     # Display the classification result
     max_score = float('-inf')
     max_label = ''
 
     for result in results:
-        if result > max_score:
-            max_score = result
-            max_label = classifier.model.config.id2label[results.index(result)]
+        if result['score'] > max_score:
+            max_score = result['score']
+            max_label = result['label']
 
     st.write("This review sentiment is:", max_label)
     st.write("Accuracy rate is:", max_score)
@@ -33,23 +33,20 @@ if st.button("Classify sentiment"):
     if max_label == "negative":
         # Streamlit application title
         st.title("Product categories of negative review")
-        st.write("Product classification of this negative review: smartTv, books, mobile, mobile accessories, and refrigerators")
+        st.write("Product classification of this negative review: smartTv, books, mobile, mobile accessories and refrigerators")
+
+        # Load the product classification model pipeline
+        product_classifier = pipeline("text-classification", model='model_name', return_all_scores=True)
 
         # Perform product classification analysis when the user clicks the "Classify product" button
         if st.button("Classify product"):
             # Perform product classification analysis on the input text
-            results_1 = classifier(text)[0]['scores_1']
+            results_1 = product_classifier(text)
 
             # Display the classification result
             max_score_1 = float('-inf')
             max_label_1 = ''
 
             for result_1 in results_1:
-                if result_1 > max_score_1:
-                    max_score_1 = result_1
-                    max_label_1 = classifier.model.config.id2label_1[results_1.index(result_1)]
-
-            st.write("This negative review blongs to:", max_label_1)
-            st.write("Accuracy rate is:", max_score_1)
-            
-    
+                if result_1['score'] > max_score_1:
+                    max_score_1