app.py

import pandas as pd
import numpy as np
import gradio as gr
import joblib

# Load the saved model
ensemble = joblib.load('ensemble_model.joblib')

# Load your data
df = pd.read_csv('City_Employee_Payroll__Current__20240915.csv', low_memory=False)

def predict_total_pay(gender, job_title, ethnicity):
    # Your existing prediction function
    # ...

def gradio_predict(gender, ethnicity, job_title):
    predicted_pay = predict_total_pay(gender, job_title, ethnicity)
    return f"${predicted_pay:.2f}"

# Prepare dropdown options
genders = df['GENDER'].dropna().unique().tolist()
ethnicities = df['ETHNICITY'].dropna().unique().tolist()
job_titles = sorted(df['JOB_TITLE'].dropna().unique().tolist())

# Create Gradio interface
iface = gr.Interface(
    fn=gradio_predict,
    inputs=[
        gr.Dropdown(choices=genders, label="Gender"),
        gr.Dropdown(choices=ethnicities, label="Ethnicity"),
        gr.Dropdown(choices=job_titles, label="Job Title")
    ],
    outputs=gr.Textbox(label="Predicted Total Pay"),
    title="LA City Employee Pay Predictor",
    description="Predict the total pay for LA City employees based on gender, ethnicity, and job title."
)

iface.launch()