Update app.py

app.py

@@ -13,78 +13,189 @@ loaded_model = pickle.load(open("h22_xgb_Final(2).pkl", 'rb'))
 # Setup SHAP Explainer for XGBoost
 explainer = shap.Explainer(loaded_model)
 
-# Define the prediction function
-def main_func(SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing):
-    new_row = pd.DataFrame.from_dict({
-        'SupportiveGM': SupportiveGM, 
-        'Merit': Merit,
-        'LearningDevelopment': LearningDevelopment, 
-        'WorkEnvironment': WorkEnvironment, 
-        'Engagement': Engagement, 
-        'WellBeing': WellBeing
-    }, orient='index').transpose()
-    
-   
-    # Predict probability for staying (XGBoost Booster returns class probabilities)
-    prob = loaded_model.predict_proba(new_row)
+def safe_convert(value, default, min_val, max_val):
+    try:
+        num = float(value)
+        return max(min_val, min(num, max_val))  # Ensure within range
+    except (TypeError, ValueError):
+        return default  # Use default if conversion fails
+
+# Create the main function for server
+def main_func(Department, ChainScale, SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing):    
+        
+    # ChainScale mapping
+    ChainScale = {               
+        'Luxury': 1,
+        'Upper Midscale': 2,
+        'Upper Upscale': 3,
+        'Upscale': 4,
+        'Independent': 5,
+    }
+    default_ChainScale = 4  
+    ChainScale_value = ChainScale_mapping.get(ChainScale, ChainScale)
+
+    # Department mapping
+    department_mapping = {            
+        "Guest Services": 1,
+        "Food and Beverage": 2,
+        "Housekeeping": 3,
+        "Front Office Operations": 4,
+        "Guest Activities": 5,
+    }
+    default_department = 5  
+    department_value = department_mapping.get(Department, default_department)
+
+   LearningDevelopment = safe_convert(LearningDevelopment, 3.0, 1, 5)
+    SupportiveGM = safe_convert(SupportiveGM, 3.0, 1, 5)
+    Merit = safe_convert(Merit, 3.0, 1, 5)
+    WorkEnvironment = safe_convert(WorkEnvironment, 3.0, 1, 5)
+    WellBeing = safe_convert(WellBeing, 3.0, 1, 5)
+
+    new_row = pd.DataFrame({
+        'Department': [int(department_value)],  
+        'ChainScale': [int(ChainScale_value)],          
+        'SupportiveGM': [SupportiveGM],
+        'Merit': [Merit],
+        'LearningDevelopment': [LearningDevelopment],
+        'WorkEnvironment': [WorkEnvironment],
+        'Engaged': [Engaged],
+        'WellBeing': [WellBeing]
+    }).astype(float)
+
+    prob = loaded_model.predict_proba(new_row) 
 
-    # Compute SHAP values
     shap_values = explainer(new_row)
 
-    # Generate SHAP Plot
-    plot = shap.plots.bar(shap_values[0], max_display=6, order=shap.Explanation.abs, show_data='auto', show=False)
+    fig, ax = plt.subplots(figsize=(8, 4))
+    values = shap_values.values[0]  # Extract SHAP values
+    features = new_row.columns  # Feature names
+
+    # Assign colors manually (Hilton Blue for positive, Red for negative)
+    colors = ['#FF0000' if v < 0 else '#1E4380' for v in values]
+
+    sorted_indices = np.argsort(np.abs(values))[-6:]  # Select top 6 features
+    sorted_values = values[sorted_indices]
+    sorted_features = [features[i] for i in sorted_indices]
+    sorted_colors = [colors[i] for i in sorted_indices]
+    ax.barh(sorted_features, sorted_values, color=sorted_colors)
+    ax.set_xlabel("SHAP Value Impact")
+    ax.set_title("Feature Importance (SHAP)")
 
     plt.tight_layout()
     local_plot = plt.gcf()
-    plt.rcParams['figure.figsize'] = (6, 4)
     plt.close()
-    
-    return {"Leave": float(prob[0][0]), "Stay": 1-float(prob[0][0])}, local_plot
+
+    return {"Leave": float(prob[0][0]), "Stay": 1 - float(prob[0][0])}, local_plot
 
 # Create the UI
-title = "**Mod 3 Team 5: Employee Turnover Predictor**"
+title = "**Mod 3 Team 5: Employee Turnover Predictor & Interpreter**"
 description1 = """
-This app takes six inputs about employees' satisfaction with different aspects of their work (such as work-life balance, ...) 
-and predicts whether the employee intends to stay with the employer or leave. The outputs include:
-1. The predicted probability of staying or leaving.
-2. A SHAP plot that visualizes how different factors impact the prediction.
+This app predicts whether an employee intends to stay or leave based on satisfaction factors and department. There are two outputs from the app: 1- the predicted probability of stay or leave, 2- Shapley's 
+force-plot which visualizes the extent to which each factor impacts the stay/leave prediction.
 """
 
 description2 = """
-To use the app, adjust the values of the six employee satisfaction factors and click **Analyze**. ✨ 
+To use the app, click on one of the examples, or adjust the values of the employee satisfaction 
+factors in the employee generation and tenure population of interest, and click on Analyze. ✨ 
 """ 
 
 with gr.Blocks(title=title) as demo:
+    gr.Image("Hilton-Logo-Resized.png")
     gr.Markdown(f"## {title}")
     gr.Markdown(description1)
     gr.Markdown("""---""")
     gr.Markdown(description2)
     gr.Markdown("""---""")
-
-    with gr.Row():        
+    
+    with gr.Row():      
         with gr.Column():
-            SupportiveGM = gr.Slider(label="Supportive GM Score", minimum=1, maximum=5, value=4, step=0.1)
-            Merit = gr.Slider(label="Merit Score", minimum=1, maximum=5, value=4, step=0.1)
-            LearningDevelopment = gr.Slider(label="Learning & Development Score", minimum=1, maximum=5, value=4, step=0.1)
-            WorkEnvironment = gr.Slider(label="Work Environment Score", minimum=1, maximum=5, value=4, step=0.1)
-            Engagement = gr.Slider(label="Engagement Score", minimum=1, maximum=5, value=4, step=0.1)
-            WellBeing = gr.Slider(label="Well-Being Score", minimum=1, maximum=5, value=4, step=0.1)
+            Department = gr.Radio(
+                ["Guest Services", "Food and Beverage", "Housekeeping", 
+                 "Front Office Operations", "Guest Activties"], 
+                label="Department", 
+                value="Guest Services"
+            )
+            ChainScale = gr.Dropdown(
+                ["Luxury", "Upper Mid-Scale", "Upper Upscale", "Upscale", "Indepdendent"], 
+                label="ChainScale", 
+                value="Upper Upscale"
+            )
+            LearningDevelopment = gr.Slider(
+                label="SupportiveGM Score", minimum=1, maximum=5, value=4, step=0.1,
+                interactive=True
+            )
+            SupportiveGM = gr.Slider(
+                label="Merit Score", minimum=1, maximum=5, value=4, step=0.1,
+                interactive=True
+            )
+            Merit = gr.Slider(
+                label="Learning and Development Score", minimum=1, maximum=5, value=4, step=0.1,
+                interactive=True
+            )
+            WorkEnvironment = gr.Slider(
+                label="Work Environment Score", minimum=1, maximum=5, value=4, step=0.1,
+                interactive=True
+            )
+             Engagement = gr.Slider(
+                label="Engagement Score", minimum=1, maximum=5, value=4, step=0.1,
+                interactive=True
+            )
+            WellBeing = gr.Slider(
+                label="Well-Being Score", minimum=1, maximum=5, value=4, step=0.1,
+                interactive=True
+            )
             submit_btn = gr.Button("Analyze")
         
         with gr.Column(visible=True, scale=1, min_width=600) as output_col:
-            label = gr.Label(label="Predicted Turnover Probability")
-            local_plot = gr.Plot(label="SHAP Plot:")
+            label = gr.Label(label="Predicted Label")
+            local_plot = gr.Plot(label='SHAP Analysis')
 
-            submit_btn.click(
-                main_func,
-                [SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing],
-                [label, local_plot], api_name="Employee_Turnover"
-            )
+    submit_btn.click(
+        main_func,
+        [Department, ChainScale, SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing],
+        [label, local_plot],
+        api_name="Employee_Turnover"
+    )
     
-    gr.Markdown("### Click on an example below to see how it works:")
-    gr.Examples([[4, 4, 4, 4, 5, 5], [5, 4, 5, 4, 4, 4]], 
-                [SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing], 
-                [label, local_plot], main_func, cache_examples=True)
+    gr.Markdown("### Click on any of the examples below to see how it works:")
 
-demo.launch()
+    gr.Examples(
+        [
+            ["Guest Services", "UpperUpscale", 2.5, 3.0, 2.8, 3.5],  
+            ["Food and Beverage", "UpperUpscale", 3.5, 4.0, 4.2, 4.5],  
+            ["Housekeeping", "UpperUpscale", 5.0, 4.8, 5.0, 4.7]  
+        ],
+        [Department, ChainScale, SupportiveGM, Merit, LearningDevelopment, WorkEnvironment, Engagement, WellBeing],
+        [label, local_plot],
+        main_func,
+        cache_examples=True
+    )
+    
+    demo.css = """
+        body {
+            font-family: "Garamond", "Georgia", serif !important;
+        }
+        .gr-button {
+            background-color: #1E4380 !important;
+            color: white !important;
+            border-radius: 8px !important;
+            padding: 10px !important;
+        }
+        .gr-label {
+            color: #1E4380 !important;
+            font-weight: bold;
+            font-size: 18px !important;
+        }
+        /* Fix Slider Colors */
+        input[type="range"] {
+            accent-color: #1E4380 !important;
+        }
+        .gr-slider .track {
+            background: #1E4380 !important;
+        }
+        .gr-slider .thumb {
+            background: #1E4380 !important;
+        }
+    """
 
+demo.launch()