Update app.py

app.py

@@ -32,7 +32,7 @@ def load_keybert_model():
 
 
 def main():
-    st.title("📊 Review Sentiment & Keyword Analyzer + GPT Insights")
+    st.title("📊 Review Analyzer")
 
     review = st.text_area("Enter your review:")
     if not st.button("Analyze Review"):
@@ -41,13 +41,30 @@ def main():
         st.warning("Please enter a review to analyze.")
         return
 
+    # Initialize progress bar
+    progress = st.progress(0)
+
     # Load models
+    progress.text("Loading models...")
     sentiment_pipeline = load_sentiment_pipeline()
     kw_model = load_keybert_model()
+    progress.progress(20)
 
     # Run sentiment analysis
+    progress.text("Analyzing sentiment...")
     scores = sentiment_pipeline(review)[0]
     sentiment_results = {item['label']: float(item['score']) for item in scores}
+    progress.progress(40)
+
+    # Extract keywords
+    progress.text("Extracting keywords...")
+    keywords = kw_model.extract_keywords(
+        review,
+        keyphrase_ngram_range=(1, 2),
+        stop_words="english",
+        top_n=3
+    )
+    progress.progress(60)
 
     # Display scores and keywords side by side
     col1, col2 = st.columns(2)
@@ -56,26 +73,22 @@ def main():
         st.json({k: round(v, 4) for k, v in sentiment_results.items()})
     with col2:
         st.subheader("Top 3 Keywords")
-        keywords = kw_model.extract_keywords(
-            review,
-            keyphrase_ngram_range=(1, 2),
-            stop_words="english",
-            top_n=3
-        )
         for kw, score in keywords:
             st.write(f"• {kw} ({score:.4f})")
 
-    # Bar chart of sentiment scores
+    # Bar chart
+    progress.text("Rendering chart...")
     df_scores = pd.DataFrame.from_dict(sentiment_results, orient='index', columns=['score'])
     df_scores.index.name = 'label'
     st.bar_chart(df_scores)
+    progress.progress(80)
 
-    # Highlight highest sentiment without subheader
+    # Highlight highest sentiment
     max_label, max_score = max(sentiment_results.items(), key=lambda x: x[1])
     st.markdown(f"**Highest Sentiment:** **{max_label}** ({max_score:.4f})")
 
-    # GPT-Driven Analysis & Suggestions (detailed)
-    st.subheader("GPT Analysis & Seller Suggestions")
+    # GPT-Driven Analysis & Suggestions
+    progress.text("Generating insights...")
     prompt = f"""
 You are an analytical e-commerce feedback expert.
 Review: \"{review}\"
@@ -98,5 +111,9 @@ Tasks:
     gpt_reply = response.choices[0].message.content.strip()
     st.markdown(gpt_reply)
 
+    # Complete
+    progress.progress(100)
+    progress.text("Done!")
+
 if __name__ == "__main__":
     main()