Update app.py

app.py

@@ -95,7 +95,8 @@ def evaluate_model_with_report(val_loader):
 def generate_performance_metrics():
     y_pred = model.predict(X_test)
     accuracy = accuracy_score(y_test,y_pred)
-    report = classification_report(y_test, y_pred, output_dict=True))
+    report = classification_report(y_test, y_pred, output_dict=True)
+    
     return {
         "accuracy": f"{accuracy:.2%}",
         "precision": f"{report['1']['precision']:.2%}",
@@ -108,7 +109,7 @@ def generate_performance_metrics():
 def create_interface():
     performance_metrics = generate_performance_metrics()
     with gr.Blocks() as interface:
-        gr.Markdown("Spam Email Classification")
+        gr.Markdown("Spam and Phishing Email Detection")
 
         # Email Text Input
         email_input = gr.Textbox(
@@ -120,7 +121,7 @@ def create_interface():
         confidence_output = gr.Textbox(label="Confidence Score", interactive=False)
         accuracy_output = gr.Textbox(label="Accuracy", interactive=False)
 
-        analyze_button = gr.Button("Analyze Email 🕵️‍♂️")
+        analyze_button = gr.Button("Analyze Email")
 
         def email_analysis_pipeline(email_text):
             results = classify_email(email_text)
@@ -136,7 +137,7 @@ def create_interface():
             fn=classify_email,
             inputs=email_input,
             outputs=[result_output, confidence_output, accuracy_output]
-        )
+)
 
         gr.Markdown("## 📊 Model Performance Analytics")
         with gr.Row():
@@ -144,8 +145,8 @@ def create_interface():
             gr.Textbox(value=performance_metrics["precision"], label="Precision", interactive=False)
             gr.Textbox(value=performance_metrics["recall"], label="Recall", interactive=False)
             gr.Textbox(value=performance_metrics["f1_score"], label="F1 Score", interactive=False)
-
-    return interface
+        
+            return interface
 
 # Launch the interface
 interface = create_interface()