Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 import numpy as np
 import pandas as pd
 import joblib
-import os
 import warnings
 from huggingface_hub import hf_hub_download
 
@@ -27,12 +26,11 @@ def predict_employee_status(
     average_monthly_hours, time_spend_company,
     work_accident, promotion_last_5years, salary, department, threshold=0.5
 ):
-    # List of all departments as encoded during training
     departments = [
-        'IT', 'RandD', 'accounting', 'hr', 'management',
-        'marketing', 'product_mng', 'sales', 'support', 'technical'
+        'sales', 'accounting', 'hr', 'technical', 'support',
+        'management', 'IT', 'product_mng', 'marketing', 'RandD'
     ]
-
+    
     # One-hot encode department
     department_features = {f"department_{dept}": 0 for dept in departments}
     if department in departments:
@@ -42,7 +40,7 @@ def predict_employee_status(
     satisfaction_evaluation = satisfaction_level * last_evaluation
     work_balance = average_monthly_hours / number_project
 
-    # Construct input DataFrame
+    # Input data
     input_data = {
         "satisfaction_level": [satisfaction_level],
         "last_evaluation": [last_evaluation],
@@ -59,6 +57,22 @@ def predict_employee_status(
 
     input_df = pd.DataFrame(input_data)
 
+    # Match training column order exactly
+    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'
+    ]
+
+    for col in expected_columns:
+        if col not in input_df.columns:
+            input_df[col] = 0
+    input_df = input_df[expected_columns]
+
+    # Predict
     try:
         prob = model.predict_proba(input_df)[0][1]
         result = "✅ Employee is likely to quit." if prob >= threshold else "✅ Employee is likely to stay."
@@ -80,8 +94,8 @@ 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(
-                ['IT', 'RandD', 'accounting', 'hr', 'management',
-                 'marketing', 'product_mng', 'sales', 'support', 'technical'],
+                ['sales', 'accounting', 'hr', 'technical', 'support',
+                 'management', 'IT', 'product_mng', 'marketing', 'RandD'],
                 label="Department"
             ),
             gr.Slider(0.1, 0.9, value=0.5, step=0.05, label="Prediction Threshold")