Update app.py

app.py

@@ -21,7 +21,6 @@ def safe_convert(value, default, min_val, max_val):
 # Create the main function for the model
 def main_func(Department, ChainScale, SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing):
     
-    
     ChainScale_mapping = {
         'Luxury': 1,
         'Upper Midscale': 2,
@@ -37,8 +36,12 @@ def main_func(Department, ChainScale, SupportiveGM, Merit, LearningDevelopment,
         "Front Office Operations": 4,
         "Guest Activities": 5,
     }
-
     
+    # Convert inputs
+    Department = department_mapping.get(Department, 1)  # Default to "Guest Services"
+    ChainScale = ChainScale_mapping.get(ChainScale, 3)  # Default to "Upper Upscale"
+
+    # Ensure numeric input validity
     LearningDevelopment = safe_convert(LearningDevelopment, 3.0, 1, 5)
     SupportiveGM = safe_convert(SupportiveGM, 3.0, 1, 5)
     Merit = safe_convert(Merit, 3.0, 1, 5)
@@ -46,8 +49,10 @@ def main_func(Department, ChainScale, SupportiveGM, Merit, LearningDevelopment,
     Engagement = safe_convert(Engagement, 3.0, 1, 5)
     WellBeing = safe_convert(WellBeing, 3.0, 1, 5)
 
-    
+    # Create DataFrame for prediction
     new_row = pd.DataFrame({
+        'Department': [Department],
+        'ChainScale': [ChainScale],
         'SupportiveGM': [SupportiveGM],
         'Merit': [Merit],
         'LearningDevelopment': [LearningDevelopment],
@@ -85,15 +90,11 @@ def main_func(Department, ChainScale, SupportiveGM, Merit, LearningDevelopment,
 title = "**Mod 3 Team 5: Employee Turnover Predictor & Interpreter**"
 description1 = """
 This app evaluates six key factors affecting employee satisfaction—Supportive GM, Merit, Learning & Development, Work Environment, Engagement, and Well-Being—to predict whether an employee is likely to stay with Hilton or leave.
-
 The app provides two key outputs:
-
 **Predicted Probability**  
 A likelihood score indicating whether an employee will stay or leave.
-
 **SHAP Force Plot**  
 A dynamic visualization that illustrates how each factor influences the prediction, helping to pinpoint the most impactful drivers of employee retention.
-
 Designed for HR teams at both departmental and hotel chain levels, this tool delivers data-driven insights to improve employee experience and retention strategies across Hilton properties.
 """
 
@@ -161,15 +162,15 @@ with gr.Blocks(title=title) as demo:
     
     gr.Examples(
         [
-            ["Guest Service Employee", "Upper Upscale", 4.1, 3.7, 3.9, 4.2, 4.4, 4.3],  
-            ["Food and Beverage Employee, "Upper Upscale", 3.9, 3.7, 4.1, 4.3, 4.5, 4.4],  
-            ["Housekeeping Employee", "Upper Upscale", 4.3, 4.0, 4.3, 4.4, 4.5, 4.4],  
-            ["Guest Service Employee 2", "Upper Upscale", 5.0, 4.0, 4.3, 4.4, 5.0, 5.0]  
+            ["Guest Services", "Upper Upscale", 4.1, 3.7, 3.9, 4.2, 4.4, 4.3],  
+            ["Food and Beverage", "Upper Upscale", 3.9, 3.7, 4.1, 4.3, 4.5, 4.4],  
+            ["Housekeeping", "Upper Upscale", 4.3, 4.0, 4.3, 4.4, 4.5, 4.4],  
+            ["Guest Services", "Upper Upscale", 5.0, 4.0, 4.3, 4.4, 5.0, 5.0]  
         ],
         [Department, ChainScale, SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing],
         [label, local_plot],
         main_func,
         cache_examples=True
     )
-
-demo.launch()
+    
+demo.launch()