Update app.py

app.py

@@ -26,21 +26,27 @@ def predict_employee_status(
     average_monthly_hours, time_spend_company,
     work_accident, promotion_last_5years, salary, department, threshold=0.5
 ):
-    departments = [
-        'IT', 'RandD', 'accounting', 'hr', 'management',
-        'marketing', 'product_mng', 'sales', 'support', 'technical'
+    # Expected columns from training
+    expected_columns = [
+        'satisfaction_level', 'last_evaluation', 'number_project', 'average_monthly_hours',
+        'time_spend_company', 'Work_accident', 'promotion_last_5years', 'salary',
+        'satisfaction_evaluation', 'work_balance',
+        'department_IT', 'department_RandD', 'department_accounting', 'department_hr',
+        'department_management', 'department_marketing', 'department_product_mng',
+        'department_sales', 'department_support', 'department_technical'
     ]
 
-    # One-hot encode department
-    department_features = {f"department_{dept}": 0 for dept in departments}
-    if department in departments:
-        department_features[f"department_{department}"] = 1
+    # Construct department one-hot features
+    department_features = {col: 0 for col in expected_columns if col.startswith("department_")}
+    dept_key = f"department_{department}"
+    if dept_key in department_features:
+        department_features[dept_key] = 1
 
-    # Interaction features
+    # Create interaction features
     satisfaction_evaluation = satisfaction_level * last_evaluation
     work_balance = average_monthly_hours / number_project
 
-    # Input data
+    # Create input dataframe
     input_data = {
         "satisfaction_level": [satisfaction_level],
         "last_evaluation": [last_evaluation],
@@ -57,15 +63,7 @@ def predict_employee_status(
 
     input_df = pd.DataFrame(input_data)
 
-    # Ensure exact column order
-    expected_columns = [
-        'satisfaction_level', 'last_evaluation', 'number_project', 'average_monthly_hours',
-        'time_spend_company', 'Work_accident', 'promotion_last_5years', 'salary',
-        'satisfaction_evaluation', 'work_balance',
-        'department_IT', 'department_RandD', 'department_accounting', 'department_hr',
-        'department_management', 'department_marketing', 'department_product_mng',
-        'department_sales', 'department_support', 'department_technical'
-    ]
+    # Ensure all expected columns are present and ordered
     for col in expected_columns:
         if col not in input_df.columns:
             input_df[col] = 0
@@ -92,8 +90,8 @@ def gradio_interface():
             gr.Radio([0, 1], label="Promotion in Last 5 Years (0 = No, 1 = Yes)"),
             gr.Radio([0, 1, 2], label="Salary (0 = Low, 1 = Medium, 2 = High)"),
             gr.Dropdown(
-                ['sales', 'accounting', 'hr', 'technical', 'support',
-                 'management', 'IT', 'product_mng', 'marketing', 'RandD'],
+                ['IT', 'RandD', 'accounting', 'hr', 'management',
+                 'marketing', 'product_mng', 'sales', 'support', 'technical'],
                 label="Department"
             ),
             gr.Slider(0.1, 0.9, value=0.5, step=0.05, label="Prediction Threshold")
@@ -107,3 +105,4 @@ def gradio_interface():
 
 gradio_interface()
 
+