Update app.py (#10)

- Update app.py (8432b4cb6b02bc3be3b379814d92657c0886a931)


Co-authored-by: Sarah Albright <[email protected]>

app.py

@@ -1,5 +1,3 @@
-# with cluster profiles 
-
 import gradio as gr
 import pickle
 import pandas as pd
@@ -7,23 +5,37 @@ import shap
 import matplotlib.pyplot as plt
 
 # Load model
-filename = 'xgb_h_new.pkl'
+filename = 'xgb_h_generation.pkl'
 with open(filename, 'rb') as f:
     loaded_model = pickle.load(f)
 
 # Setup SHAP
 explainer = shap.Explainer(loaded_model)
 
-# Employee Profiles (From SPSS 3-Cluster Solution)
+# Generation Mapping (Radio Button Labels → Numeric Values)
+generation_mapping = {
+    "Before 1927": 1,
+    "Silent Generation": 2,
+    "Baby Boomers": 3,
+    "Generation X": 4,
+    "Millennials": 5,
+    "Generation Z": 6
+}
+
+# Employee Profiles (Updated Default Dream Employee Values)
 employee_profiles = {
-    "🏆 Leslie Knope": [4.716, 4.792, 4.864, 4.588, 4.849, 4.601],  # Cluster group 1 averages - high engagement, strong support, high workload
-    "⚠️ Kevin Malone": [3.045, 3.122, 3.129, 2.886, 3.113, 2.197],  # Cluster group 2 averages - disengaged, low recognition, weak support
-    "🌱 Jim Halpert": [3.885, 3.992, 4.119, 3.704, 4.090, 3.377] # Cluster group 3 averages - Moderately engaged, could be more recognized - room to grow
+    "🥇 Default Dream Employee": [5.0, 5.0, 5.0, 4.8, 4.8, 4.9],  
+    "🏆 Leslie Knope": [4.716, 4.792, 4.864, 4.588, 4.849, 4.601],
+    "⚠️ Kevin Malone": [3.045, 3.122, 3.129, 2.886, 3.113, 2.197],
+    "🌱 Jim Halpert": [3.885, 3.992, 4.119, 3.704, 4.090, 3.377]
 }
 
 # Define the prediction function
-def main_func(WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Merit):
+def main_func(Generation_Label, WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Merit):
+    Generation = generation_mapping.get(Generation_Label, 5)  # Convert label to numeric value
+
     new_row = pd.DataFrame({
+        'Generation': [Generation],
         'WellBeing': [WellBeing],
         'SupportiveGM': [SupportiveGM],
         'Engagement': [Engagement],
@@ -40,43 +52,34 @@ def main_func(WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Me
     stay_prob = round((1 - float(prob[0][0])) * 100, 2)
     leave_prob = round(float(prob[0][0]) * 100, 2)
 
-    # Dynamic risk label: Changes color & text based on probability
+    # Dynamic risk label
     risk_label = "🔴 High Risk of Turnover" if leave_prob > 50 else "🟢 Low Risk of Turnover"
     risk_color = "red" if leave_prob > 50 else "green"
 
     risk_html = f"""
-    <div style='padding: 15px; border-radius: 8px;'>
-        <span style='color: {risk_color}; font-size: 26px; font-weight: bold;'>{risk_label}</span>
-        <ul style='list-style-type: none; padding-left: 0; font-size: 20px; font-weight: bold; color: #0057B8;'>
-            <li>🧲 Likelihood of Staying: {stay_prob}%</li>
-            <li>🚪 Likelihood of Leaving: {leave_prob}%</li>
-        </ul>
-    </div>
+    <div style='border: 1px solid black; padding: 15px; border-radius: 8px; display: flex;'>
+        <div style='width: 50%; padding-right: 15px;'>
+            <span style='color: {risk_color}; font-size: 26px; font-weight: bold;'>{risk_label}</span>
+            <ul style='list-style-type: none; padding-left: 0; font-size: 20px; font-weight: bold; color: #0057B8;'>
+                <li>🧲 Likelihood of Staying: {stay_prob}%</li>
+                <li>🚪 Likelihood of Leaving: {leave_prob}%</li>
+            </ul>
+        </div>
+        <div style='width: 50%; border-left: 1px solid black; padding-left: 15px;'>
+            <b style='color: #0057B8; font-size: 22px;'>Key Insights:</b>
     """
 
-    # Key Insights (Updated for 0.1-point increments)
-    insights_html = "<div style='font-size: 18px;'>"
-    for feature, shap_val in dict(zip(new_row.columns, shap_values.values[0])).items():
-        impact = round(shap_val * 10, 2)  # Scaling impact for 0.1 changes
+    # Key Insights (excluding Generation)
+    shap_values_df = pd.DataFrame(shap_values.values, columns=new_row.columns)
+    shap_values_df = shap_values_df.drop(columns=["Generation"])  # Drop Generation
+    for feature in shap_values_df.columns:
+        shap_val = shap_values_df[feature].values[0]
+        impact = round(shap_val * 10, 2)
         icon = "📈" if shap_val > 0 else "📉"
         effect = "raises turnover risk" if shap_val > 0 else "improves retention"
-        insights_html += f"<p style='margin: 5px 0;'> {icon} <b>Each 0.1-point increase in {feature} {effect} by {abs(impact)}%.</b></p>"
-    insights_html += "</div>"
-
-    # Final Layout (Risk + Key Insights)
-    final_layout = f"""
-    <table style='width:100%; border-collapse: collapse; margin-top: 10px; background-color: #FFFFFF;'>
-        <tr>
-            <td style='width: 33%; padding: 15px; background-color: #FFFFFF; border-radius: 8px; vertical-align: top;'>
-                {risk_html}
-            </td>
-            <td style='width: 67%; padding: 15px; background-color: #FFFFFF; border-radius: 8px; vertical-align: top;'>
-                <b style='color: #0057B8; font-size: 22px;'>Key Insights:</b>
-                {insights_html}
-            </td>
-        </tr>
-    </table>
-    """
+        risk_html += f"<p style='margin: 5px 0;'> {icon} <b>Each 0.1-point increase in {feature} {effect} by {abs(impact)}%.</b></p>"
+
+    risk_html += "</div></div>"
 
     # Retention vs. Turnover Chart
     fig, ax = plt.subplots()
@@ -93,16 +96,23 @@ def main_func(WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Me
     plt.savefig(prob_chart_path, transparent=True)
     plt.close()
 
-    # SHAP Chart
+    # SHAP Chart (excluding Generation)
     fig, ax = plt.subplots()
-    shap.plots.bar(shap_values[0], max_display=6, show=False)
+    shap_values_filtered = shap_values[:, 1:]  # Remove Generation from SHAP values
+    shap.plots.bar(shap_values_filtered[0], max_display=6, show=False)  # Adjust max_display if needed
     ax.set_title("Key Drivers of Turnover Risk")
     plt.tight_layout()
     shap_plot_path = "shap_plot.png"
     plt.savefig(shap_plot_path, transparent=True)
     plt.close()
 
-    return final_layout, prob_chart_path, shap_plot_path
+    return risk_html, prob_chart_path, shap_plot_path
+
+# Function to update sliders based on selected profile
+def update_sliders(profile):
+    if profile in employee_profiles:
+        return employee_profiles[profile]
+    return [5.0, 5.0, 5.0, 4.8, 4.8, 4.9]
 
 # UI Setup
 with gr.Blocks() as demo:
@@ -117,41 +127,42 @@ with gr.Blocks() as demo:
     gr.Markdown("""
     <div style='font-size: 20px; color: #0057B8;'>
     ✨ <b>Welcome to Hilton’s Employee Retention Predictor</b><br>
-    This tool helps <b>Sales & Marketing leaders and Front Office Operations teams</b>—The Face of Hilton—  
-    assess <b>team member engagement</b> and predict <b>turnover risk</b> using AI-powered insights.<br>  
+    This tool helps <b>HR and People Analytics professionals</b> assess  
+    <b>Sales, Marketing, and Front Office Operations teams</b>—<span style='color: #0057B8;'>The Face of Hilton</span>—  
+    by analyzing <b>team member engagement</b> and predicting <b>turnover risk</b> using  
+    <span style='color: #0057B8;'>AI-powered insights</span>.<br>  
     🔍 <b>Understand what drives retention and make data-driven decisions to keep top talent.</b>  
     </div>
-    """) 
-    
-    # Dropdown for Employee Profiles
-    profile_dropdown = gr.Dropdown(choices=list(employee_profiles.keys()), label="Select Employee Profile")
+    """)
+
+    # Generation Filter (Radio Button - Independent)
+    generation_filter = gr.Radio(choices=list(generation_mapping.keys()), label="Select Generation", value="Millennials")
 
-    # Sliders for input features
+    # Dropdown for Employee Profiles (Updates Sliders)
+    profile_dropdown = gr.Dropdown(choices=list(employee_profiles.keys()), label="Select Employee Profile", value="🥇 Default Dream Employee")
+
+    # Sliders for input features (Updated Order)
     with gr.Row():
-        WellBeing = gr.Slider(label="WellBeing Score", minimum=1, maximum=5, value=4, step=0.1)
-        SupportiveGM = gr.Slider(label="Supportive GM 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="WellBeing Score", minimum=1, maximum=5, value=5.0, step=0.1)
+        SupportiveGM = gr.Slider(label="Supportive GM Score", minimum=1, maximum=5, value=5.0, step=0.1)
+        Engagement = gr.Slider(label="Engagement Score", minimum=1, maximum=5, value=5.0, step=0.1)
     with gr.Row():
-        Workload = gr.Slider(label="Workload 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)
-        Merit = gr.Slider(label="Merit Score", minimum=1, maximum=5, value=4, step=0.1)
+        Workload = gr.Slider(label="Workload Score", minimum=1, maximum=5, value=4.8, step=0.1)
+        WorkEnvironment = gr.Slider(label="Work Environment Score", minimum=1, maximum=5, value=4.8, step=0.1)
+        Merit = gr.Slider(label="Merit Score", minimum=1, maximum=5, value=4.9, step=0.1)
 
     submit_btn = gr.Button("🔎 Click Here to Analyze Retention")
 
-    # Output elements
     prediction = gr.HTML()
+
+    # Charts Side by Side
     with gr.Row():
         prob_chart = gr.Image(label="Retention vs. Turnover Probability", type="filepath")
         shap_plot = gr.Image(label="Key Drivers of Turnover Risk", type="filepath")
 
-    # Allow profile selection to update sliders
-    def update_sliders(profile):
-        if profile in employee_profiles:
-            return employee_profiles[profile]
-        return [4, 4, 4, 4, 4, 4]
-
     profile_dropdown.change(update_sliders, inputs=[profile_dropdown], outputs=[WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Merit])
 
-    submit_btn.click(main_func, [WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Merit], [prediction, prob_chart, shap_plot])
+    submit_btn.click(main_func, [generation_filter, WellBeing, SupportiveGM, Engagement, Workload, WorkEnvironment, Merit], 
+                     [prediction, prob_chart, shap_plot])
 
-demo.launch()
+demo.launch()