Update app.py

app.py

@@ -30,6 +30,14 @@ def load_sentiment_pipeline():
 def load_keybert_model():
     return KeyBERT(model="all-MiniLM-L6-v2")
 
+LABEL_MAP = {
+    "LABEL_0": "Very Negative",
+    "LABEL_1": "Negative",
+    "LABEL_2": "Neutral",
+    "LABEL_3": "Positive",
+    "LABEL_4": "Very Positive"
+}
+
 
 def main():
     st.title("📊 Review Analyzer")
@@ -52,8 +60,9 @@ def main():
 
     # Run sentiment analysis
     progress.text("Analyzing sentiment...")
-    scores = sentiment_pipeline(review)[0]
-    sentiment_results = {item['label']: float(item['score']) for item in scores}
+    raw_scores = sentiment_pipeline(review)[0]
+    # Map labels
+    sentiment_results = {LABEL_MAP[item['label']]: float(item['score']) for item in raw_scores}
     progress.progress(40)
 
     # Extract keywords
@@ -79,7 +88,7 @@ def main():
     # Bar chart
     progress.text("Rendering chart...")
     df_scores = pd.DataFrame.from_dict(sentiment_results, orient='index', columns=['score'])
-    df_scores.index.name = 'label'
+    df_scores.index.name = 'Sentiment'
     st.bar_chart(df_scores)
     progress.progress(80)
 
@@ -95,8 +104,8 @@ Review: \"{review}\"
 Sentiment Scores: {sentiment_results}
 Top Keywords: {[kw for kw, _ in keywords]}
 Tasks:
-1. Write a concise paragraph (2 sentences) interpreting customer sentiment by combining the scores and keywords.
-2. Provide 3 actionable suggestions with brief explanations (up to 3 sentences each).
+1. Write a concise paragraph (3 sentences) interpreting customer sentiment by combining the scores and keywords.
+2. Provide 3 actionable suggestions with brief explanations (up to 4 sentences each).
 """
 
     response = openai_client.chat.completions.create(
@@ -116,4 +125,4 @@ Tasks:
     progress.text("Done!")
 
 if __name__ == "__main__":
-    main()
+    main()