app.py

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

warnings.filterwarnings("ignore")

# Load Ensemble Model
def load_model():
    model_path = "final_ensemble_model.pkl"  # Must match your saved model name
    if os.path.exists(model_path):
        model = joblib.load(model_path)
        print("✅ Ensemble model loaded successfully.")
        return model
    else:
        print("❌ Model file not found.")
        return None

model = load_model()

# Prediction function
def predict_employee_status(satisfaction_level, last_evaluation, number_project,
                            average_monthly_hours, time_spend_company,
                            work_accident, promotion_last_5years, salary, department, threshold=0.5):

    departments = [
        'RandD', 'accounting', 'hr', 'management', 'marketing',
        'product_mng', 'sales', 'support', 'technical'
    ]
    department_features = {f"department_{dept}": 0 for dept in departments}
    if department in departments:
        department_features[f"department_{department}"] = 1

    # Feature engineering
    satisfaction_evaluation = satisfaction_level * last_evaluation
    work_balance = average_monthly_hours / number_project

    # Construct DataFrame
    input_data = {
        "satisfaction_level": [satisfaction_level],
        "last_evaluation": [last_evaluation],
        "number_project": [number_project],
        "average_monthly_hours": [average_monthly_hours],
        "time_spend_company": [time_spend_company],
        "Work_accident": [work_accident],
        "promotion_last_5years": [promotion_last_5years],
        "salary": [salary],
        "satisfaction_evaluation": [satisfaction_evaluation],
        "work_balance": [work_balance],
        **department_features
    }

    input_df = pd.DataFrame(input_data)

    # Prediction
    if model is None:
        return "❌ No model loaded."

    try:
        prob = model.predict_proba(input_df)[0][1]
        label = "✅ Employee is likely to quit." if prob >= threshold else "✅ Employee is likely to stay."
        return f"{label} (Probability: {prob:.2%})"
    except Exception as e:
        return f"❌ Error during prediction: {str(e)}"

# Launch Gradio Interface
gr.Interface(
    fn=predict_employee_status,
    inputs=[
        gr.Number(label="Satisfaction Level (0.0 - 1.0)"),
        gr.Number(label="Last Evaluation (0.0 - 1.0)"),
        gr.Number(label="Number of Projects (1 - 10)"),
        gr.Number(label="Average Monthly Hours (80 - 320)"),
        gr.Number(label="Time Spend at Company (Years)"),
        gr.Radio([0, 1], label="Work Accident (0 = No, 1 = Yes)"),
        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(departments, label="Department"),
        gr.Slider(0.1, 0.9, value=0.5, step=0.05, label="Prediction Threshold")
    ],
    outputs="text",
    title="Employee Retention Prediction System (Voting Ensemble)",
    description="Predict whether an employee will stay or quit. Adjust threshold for sensitivity.",
    theme="dark"
).launch()