Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import xgboost as xgb
 import numpy as np
+import pandas as pd
 import joblib
 import os
 import warnings
@@ -32,23 +33,34 @@ def predict_employee_status(satisfaction_level, last_evaluation, number_project,
         'RandD', 'accounting', 'hr', 'management', 'marketing',
         'product_mng', 'sales', 'support', 'technical'
     ]
-    department_encoded = [1 if dept == department else 0 for dept in departments]
+    department_features = {f"department_{dept}": 0 for dept in departments}
+    if department in departments:
+        department_features[f"department_{department}"] = 1
 
-    # Prepare the input with all 18 features
-    input_data = np.array([
-        satisfaction_level, last_evaluation, number_project, 
-        average_monthly_hours, time_spent_company, work_accident, 
-        promotion_last_5years, salary
-    ] + department_encoded).reshape(1, -1)
+    # Prepare the input with all 18 features as a DataFrame with column names
+    input_data = {
+        "satisfaction_level": [satisfaction_level],
+        "last_evaluation": [last_evaluation],
+        "number_project": [number_project],
+        "average_montly_hours": [average_monthly_hours],
+        "time_spend_company": [time_spent_company],
+        "Work_accident": [work_accident],
+        "promotion_last_5years": [promotion_last_5years],
+        "salary": [salary],
+        **department_features,
+        "satisfaction_evaluation": [satisfaction_level * last_evaluation]
+    }
+
+    input_df = pd.DataFrame(input_data)
 
     # Predict using the model
     if model is None:
         return "❌ No model found. Please upload the model file."
 
     try:
-        dmatrix = xgb.DMatrix(input_data)
+        dmatrix = xgb.DMatrix(input_df)
         prediction = model.predict(dmatrix)
-        return "Employee is likely to quit." if prediction[0] > 0.5 else "Employee is likely to stay."
+        return "✅ Employee is likely to quit." if prediction[0] > 0.5 else "✅ Employee is likely to stay."
     except Exception as e:
         return f"❌ Error: {str(e)}"