Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| import pickle | |
| import pandas as pd | |
| from catboost import CatBoostClassifier | |
| # Load the trained model and unique values from the pickle file | |
| with open('model_and_key_components.pkl', 'rb') as file: | |
| saved_components = pickle.load(file) | |
| model = saved_components['model'] | |
| unique_values = saved_components['unique_values'] | |
| # Define the Streamlit app | |
| def main(): | |
| st.title("Employee Attrition Prediction App") | |
| st.sidebar.title("Model Settings") | |
| # Sidebar inputs | |
| with st.sidebar.expander("View Unique Values"): | |
| st.write("Unique values for each feature:") | |
| for column, values in unique_values.items(): | |
| st.write(f"- {column}: {values}") | |
| # Main content | |
| st.write("Welcome to the Employee Attrition Prediction App!") | |
| st.write("This app helps HR practitioners predict employee attrition using a trained CatBoost model.") | |
| st.write("Please provide the following information to make a prediction:") | |
| # Define layout with three columns | |
| col1, col2, col3 = st.columns(3) | |
| # Column 1 | |
| with col1: | |
| age = st.number_input("Age", min_value=18, max_value=70) | |
| monthly_income = st.number_input("Monthly Income") | |
| num_companies_worked = st.number_input("Number of Companies Worked") | |
| percent_salary_hike = st.number_input("Percent Salary Hike", min_value=0, max_value=25) | |
| training_times_last_year = st.number_input("Training Times Last Year", min_value=0, max_value=6) | |
| # Column 2 | |
| with col2: | |
| department = st.selectbox("Department", ['Sales', 'Research & Development', 'Human Resources']) | |
| environment_satisfaction = st.selectbox("Environment Satisfaction", [1, 2, 3, 4]) | |
| job_role = st.selectbox("Job Role", ['Sales Executive', 'Research Scientist', 'Laboratory Technician', | |
| 'Manufacturing Director', 'Healthcare Representative', 'Manager', | |
| 'Sales Representative', 'Research Director', 'Human Resources']) | |
| job_satisfaction = st.selectbox("Job Satisfaction", [1, 2, 3, 4]) | |
| work_life_balance = st.selectbox("Work Life Balance", [1, 2, 3, 4]) | |
| # Column 3 | |
| with col3: | |
| over_time = st.checkbox("Over Time") | |
| relationship_satisfaction = st.selectbox("Relationship Satisfaction", [1, 2, 3, 4]) | |
| years_since_last_promotion = st.number_input("Years Since Last Promotion") | |
| years_with_curr_manager = st.number_input("Years With Current Manager") | |
| # Convert Monthly Income to string | |
| monthly_income = str(monthly_income) | |
| # Create a DataFrame to hold the user input data | |
| input_data = pd.DataFrame({ | |
| 'Age': [age], | |
| 'Department': [department], | |
| 'EnvironmentSatisfaction': [environment_satisfaction], | |
| 'JobRole': [job_role], | |
| 'JobSatisfaction': [job_satisfaction], | |
| 'MonthlyIncome': [monthly_income], # Convert to string | |
| 'NumCompaniesWorked': [num_companies_worked], | |
| 'OverTime': [over_time], | |
| 'PercentSalaryHike': [percent_salary_hike], | |
| 'RelationshipSatisfaction': [relationship_satisfaction], | |
| 'TrainingTimesLastYear': [training_times_last_year], | |
| 'WorkLifeBalance': [work_life_balance], | |
| 'YearsSinceLastPromotion': [years_since_last_promotion], | |
| 'YearsWithCurrManager': [years_with_curr_manager] | |
| }) | |
| # Make predictions | |
| prediction = model.predict(input_data) | |
| probability = model.predict_proba(input_data)[:, 1] | |
| # Display prediction | |
| if prediction[0] == 0: | |
| st.success("Employee is predicted to stay (Attrition = No)") | |
| else: | |
| st.error("Employee is predicted to leave (Attrition = Yes)") | |
| # Offer recommendations for retaining the employee | |
| st.subheader("Suggestions for retaining the employee:") | |
| st.markdown("- Invest in orientation programs and career development for entry-level staff, which could contribute to higher retention.") | |
| st.markdown("- Implement mentorship programs and career development initiatives aimed at engaging and retaining younger employees.") | |
| st.markdown("- Offer robust training and development programs and regular promotions to foster career growth. This investment in skills and career advancement can contribute to higher job satisfaction and retention.") | |
| st.markdown("- Recognize the diverse needs of employees based on marital status and consider tailoring benefits or support programs accordingly.") | |
| st.markdown("- Consider offering benefits that cater to the unique needs of married, single, and divorced employees.") | |
| st.markdown("- Introduce or enhance policies that support work-life balance for employees with families.") | |
| st.markdown("- Recognize the unique challenges and opportunities within each department and tailor retention strategies accordingly.") | |
| # Display probability | |
| st.write(f"Probability of Attrition: {probability[0]:.2f}") | |
| if __name__ == "__main__": | |
| main() | |
| import streamlit as st | |
| import pickle | |
| import pandas as pd | |
| from catboost import CatBoostClassifier | |
| # Load the trained model and unique values from the pickle file | |
| with open('model_and_key_components.pkl', 'rb') as file: | |
| saved_components = pickle.load(file) | |
| model = saved_components['model'] | |
| unique_values = saved_components['unique_values'] | |
| # Define the Streamlit app | |
| def main(): | |
| st.title("Employee Attrition Prediction App") | |
| st.sidebar.title("Model Settings") | |
| # Sidebar inputs | |
| with st.sidebar.expander("View Unique Values"): | |
| st.write("Unique values for each feature:") | |
| for column, values in unique_values.items(): | |
| st.write(f"- {column}: {values}") | |
| # Main content | |
| st.write("Welcome to the Employee Attrition Prediction App!") | |
| st.write("This app helps HR practitioners predict employee attrition using a trained CatBoost model.") | |
| st.write("Please provide the following information to make a prediction:") | |
| # Define layout with three columns | |
| col1, col2, col3 = st.columns(3) | |
| # Column 1 | |
| with col1: | |
| age = st.number_input("Age", min_value=18, max_value=70) | |
| monthly_income = st.number_input("Monthly Income", min_value=1000, max_value=20000) | |
| num_companies_worked = st.number_input("Number of Companies Worked", min_value=0, max_value=10) | |
| percent_salary_hike = st.number_input("Percent Salary Hike", min_value=10, max_value=25) | |
| training_times_last_year = st.number_input("Training Times Last Year", min_value=0, max_value=6) | |
| # Column 2 | |
| with col2: | |
| department = st.selectbox("Department", ['Sales', 'Research & Development', 'Human Resources']) | |
| environment_satisfaction = st.selectbox("Environment Satisfaction", [1, 2, 3, 4]) | |
| job_role = st.selectbox("Job Role", ['Sales Executive', 'Research Scientist', 'Laboratory Technician', | |
| 'Manufacturing Director', 'Healthcare Representative', 'Manager', | |
| 'Sales Representative', 'Research Director', 'Human Resources']) | |
| job_satisfaction = st.selectbox("Job Satisfaction", [1, 2, 3, 4]) | |
| work_life_balance = st.selectbox("Work Life Balance", [1, 2, 3, 4]) | |
| # Column 3 | |
| with col3: | |
| over_time = st.checkbox("Over Time") | |
| relationship_satisfaction = st.selectbox("Relationship Satisfaction", [1, 2, 3, 4]) | |
| years_since_last_promotion = st.number_input("Years Since Last Promotion", min_value=0, max_value=15) | |
| years_with_curr_manager = st.number_input("Years With Current Manager", min_value=0, max_value=15) | |
| # Create a DataFrame to hold the user input data | |
| input_data = pd.DataFrame({ | |
| 'Age': [age], | |
| 'Department': [department], | |
| 'EnvironmentSatisfaction': [environment_satisfaction], | |
| 'JobRole': [job_role], | |
| 'JobSatisfaction': [job_satisfaction], | |
| 'MonthlyIncome': [monthly_income], | |
| 'NumCompaniesWorked': [num_companies_worked], | |
| 'OverTime': [over_time], | |
| 'PercentSalaryHike': [percent_salary_hike], | |
| 'RelationshipSatisfaction': [relationship_satisfaction], | |
| 'TrainingTimesLastYear': [training_times_last_year], | |
| 'WorkLifeBalance': [work_life_balance], | |
| 'YearsSinceLastPromotion': [years_since_last_promotion], | |
| 'YearsWithCurrManager': [years_with_curr_manager] | |
| }) | |
| # Make predictions | |
| prediction = model.predict(input_data) | |
| probability = model.predict_proba(input_data)[:, 1] | |
| # Display prediction | |
| if prediction[0] == 0: | |
| st.success("Employee is predicted to stay (Attrition = No)") | |
| else: | |
| st.error("Employee is predicted to leave (Attrition = Yes)") | |
| # Offer recommendations for retaining the employee | |
| st.subheader("Suggestions for retaining the employee:") | |
| st.markdown("- Invest in orientation programs and career development for entry-level staff, which could contribute to higher retention.") | |
| st.markdown("- Implement mentorship programs and career development initiatives aimed at engaging and retaining younger employees.") | |
| st.markdown("- Offer robust training and development programs and regular promotions to foster career growth. This investment in skills and career advancement can contribute to higher job satisfaction and retention.") | |
| st.markdown("- Recognize the diverse needs of employees based on marital status and consider tailoring benefits or support programs accordingly.") | |
| st.markdown("- Consider offering benefits that cater to the unique needs of married, single, and divorced employees.") | |
| st.markdown("- Introduce or enhance policies that support work-life balance for employees with families.") | |
| st.markdown("- Recognize the unique challenges and opportunities within each department and tailor retention strategies accordingly.") | |
| # Display probability | |
| st.write(f"Probability of Attrition: {probability[0]*100:.2f}%") | |
| if __name__ == "__main__": | |
| main() |