Spaces:
Sleeping
Sleeping
File size: 3,533 Bytes
7c5d1d0 7a63bb7 a719e13 2750f6c a178285 2750f6c a178285 de496ae 7c5d1d0 a178285 2750f6c a178285 7a63bb7 2750f6c 96a2bd1 3e635fa 96a2bd1 3e635fa 96a2bd1 3e635fa a719e13 7a63bb7 96a2bd1 2ab8b05 96a2bd1 a719e13 2d5fce6 de496ae a719e13 de496ae 2d5fce6 a719e13 7a63bb7 96a2bd1 a178285 96a2bd1 a178285 96a2bd1 3e635fa 96a2bd1 a178285 96a2bd1 a178285 96a2bd1 2750f6c a178285 3e635fa |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
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
# Suppress warnings
warnings.filterwarnings("ignore")
# Load ensemble model from Hugging Face Hub
def load_model():
model_path = hf_hub_download(
repo_id="Zeyadd-Mostaffa/final_ensemble_model",
filename="final_ensemble_model.pkl"
)
model = joblib.load(model_path)
print("✅ Ensemble model loaded successfully.")
return model
model = load_model()
# Define 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
):
# List of all departments as encoded during training
departments = [
'IT', 'RandD', 'accounting', 'hr', 'management',
'marketing', 'product_mng', 'sales', 'support', 'technical'
]
# One-hot encode department
department_features = {f"department_{dept}": 0 for dept in departments}
if department in departments:
department_features[f"department_{department}"] = 1
# Interaction features
satisfaction_evaluation = satisfaction_level * last_evaluation
work_balance = average_monthly_hours / number_project
# Construct input 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)
try:
prob = model.predict_proba(input_df)[0][1]
result = "✅ Employee is likely to quit." if prob >= threshold else "✅ Employee is likely to stay."
return f"{result} (Probability: {prob:.2%})"
except Exception as e:
return f"❌ Prediction error: {str(e)}"
# Gradio Interface
def gradio_interface():
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(
['IT', 'RandD', 'accounting', 'hr', 'management',
'marketing', 'product_mng', 'sales', 'support', 'technical'],
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 is likely to stay or quit based on their profile. Supports threshold adjustment.",
theme="dark"
)
interface.launch()
gradio_interface()
|