Update app.py

app.py

@@ -22,18 +22,7 @@ def analyze_email(email_text):
     confidence = max(prediction, 1 - prediction)
     label = "Spam" if prediction > 0.5 else "Not Spam"
     
-    # Get feature importance
-    feature_names = tfidf.get_feature_names_out()
-    feature_importance = model.get_score(importance_type='gain')
-    top_features = sorted(feature_importance.items(), key=lambda x: x[1], reverse=True)[:5]
     
-    analysis = f"Classification: {label} (Confidence: {confidence:.2%})\n\n"
-    analysis += "Top 5 influential words:\n"
-    for feature, importance in top_features:
-        if feature in email_text.lower():
-            analysis += f"- {feature}: {importance:.2f}\n"
-    
-    return analysis
 
 # Create Gradio interface
 with gr.Blocks(css="footer {visibility: hidden}") as iface:
@@ -72,10 +61,9 @@ with gr.Blocks(css="footer {visibility: hidden}") as iface:
     The model achieved a 98% accuracy on the training data and 94% accuracy on the test data.
     It analyzes the content and structure of the email to determine if it's spam or not.
     
-    ### Tips for use
+    ### Tip for use
     - Enter the full text of the email for best results
-    - The 'Detailed Analysis' shows the top words influencing the classification
-    - Confidence score indicates how sure the model is about its prediction
+    
     """
     )