Update app.py

app.py

@@ -1,17 +1,38 @@
 import pandas as pd
 import numpy as np
+from sklearn.ensemble import VotingRegressor
 import gradio as gr
 import joblib
 
-# Load the saved model
-ensemble = joblib.load('ensemble_model.joblib')
-
-# Load your data
+# Load your data and trained model
 df = pd.read_csv('City_Employee_Payroll__Current__20240915.csv', low_memory=False)
+ensemble = joblib.load('ensemble_model.joblib')
 
 def predict_total_pay(gender, job_title, ethnicity):
-    # Your existing prediction function
-    # ...
+    # Create a sample input DataFrame
+    sample = pd.DataFrame({
+        'GENDER': [gender],
+        'JOB_TITLE': [job_title],
+        'ETHNICITY': [ethnicity],
+    })
+    
+    # Fill in other required features (you may need to adjust this based on your model's requirements)
+    sample['EMPLOYMENT_TYPE'] = df['EMPLOYMENT_TYPE'].mode().iloc[0]
+    sample['JOB_STATUS'] = df['JOB_STATUS'].mode().iloc[0]
+    sample['MOU'] = df['MOU'].mode().iloc[0]
+    sample['DEPARTMENT_NO'] = df['DEPARTMENT_NO'].mode().iloc[0]
+    sample['PAY_YEAR'] = df['PAY_YEAR'].max()
+    sample['REGULAR_PAY'] = df['REGULAR_PAY'].mean()
+    sample['OVERTIME_PAY'] = df['OVERTIME_PAY'].mean()
+    sample['ALL_OTHER_PAY'] = df['ALL_OTHER_PAY'].mean()
+    
+    # Calculate derived features
+    sample['PAY_RATIO'] = sample['REGULAR_PAY'] / (sample['OVERTIME_PAY'] + sample['ALL_OTHER_PAY'] + 1)
+    sample['TOTAL_NON_REGULAR_PAY'] = sample['OVERTIME_PAY'] + sample['ALL_OTHER_PAY']
+    
+    # Make prediction
+    prediction = ensemble.predict(sample)[0]
+    return prediction
 
 def gradio_predict(gender, ethnicity, job_title):
     predicted_pay = predict_total_pay(gender, job_title, ethnicity)