Update app.py

app.py

@@ -2,19 +2,19 @@ import streamlit as st
 from transformers import pipeline
 
 # Load the sentiment analysis model pipeline
-sentiment_classifier = pipeline("text-classification", model='Ryleeeee/CustomSentimentModel', return_all_scores=True)
+sentiment_classifier = pipeline("text-classification",model='Ryleeeee/CustomSentimentModel', return_all_scores=True)
 
 # Load the text summarization model pipeline
-summarizer = pipeline("summarization", model="MurkatG/review-summarizer-en")
+product_categorizer = pipeline("zero-shot-classification", model="MoritzLaurer/deberta-v3-xsmall-zeroshot-v1.1-all-33")
 
 # Streamlit application title and background image
 st.image("./header.png", use_column_width=True)
 st.markdown("<h1 style='text-align: center;'>Customer Review Analysis</h1>", unsafe_allow_html=True)
 
-st.write("Sentiment classification: positive, neutral, negative")
+st.write("Setiment classification: positive, netural, negative")
 
 # User can enter the customer review
-text = st.text_area("Enter the customer review", "")
+review = st.text_area("Enter the customer review", "")
 
 def sentiment_class(text):
     results = sentiment_classifier(text)[0]
@@ -26,22 +26,23 @@ def sentiment_class(text):
             max_label = result['label']
     return max_score, max_label
 
-def summarize_text(text):
-    results = summarizer(text, max_length=100, min_length=5, do_sample=False)
-    return results[0]['summary_text']
+def product_category(text):
+    results = product_categorizer(text)[0]['summary_text']
+    return results
+
 
 # Perform sentiment analysis when the user clicks the "Classify Sentiment" button
 if st.button("Classify Sentiment"):
     # Check if the user has entered review
-    if text is None or text.strip() == '':
+    if review is None or review.strip() == '':
         st.warning("Please enter a customer review first.")
     else:
         # Perform sentiment analysis on the input text
-        sentiment_result = sentiment_class(text)
+        sentiment_result = sentiment_class(review)
         st.write("This review sentiment is ", sentiment_result[1])
         st.write("Prediction score is ", sentiment_result[0])
 
-        # Perform text summarization when the review sentiment is classified as negative
-        if sentiment_result[1] == 'LABEL_2':  # Change this to match the negative label in your model
-            summary = summarize_text(text)
-            st.write("Review summary: ", summary)
+        # Perform text summarization when the review sentiment is classified as negative           
+        if sentiment_result[1] == 'negative':
+            category = product_category(review)
+            st.write("Product category: ", category)