Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import numpy as np | |
| import joblib | |
| model = joblib.load("src/model.pkl") | |
| st.set_page_config( | |
| page_icon= "💵", | |
| page_title= "Check loan Status", | |
| layout= "wide", | |
| menu_items={ | |
| 'About': "faizwajidkhatri@gmail.com Data Science student" | |
| } | |
| ) | |
| st.title("Loan Status Checker") | |
| st.write("Please enter the details of the applicant:") | |
| person_age=st.slider("Age of the applicant", min_value=18, max_value=100, step=1) | |
| person_gender=st.selectbox("Gender of the applicant", options=[0, 1]) | |
| person_eduation=st.selectbox("Highest education level", options=[0, 1, 2, 3, 4, 5]) | |
| person_income=st.number_input("Annual income of the applicant", min_value=1000, max_value=1000000, step=1000) | |
| person_emp_exp=st.number_input("Years of employment experience", min_value=0, max_value=50, step=1) | |
| person_home_ownership=st.selectbox("Type of home ownership", options=[0, 1, 2, 3]) | |
| loan_amnt=st.number_input("Loan amount requested", min_value=1000, max_value=500000, step=1000) | |
| loan_intent=st.selectbox("Purpose of the loan", options=[0, 1, 2, 3, 4, 5]) | |
| loan_int_rate=st.number_input("Interest rate on the loan (%)", min_value=0.0, max_value=100.0, step=0.1) | |
| loan_percent_income=st.number_input("Loan amount as a percentage of income", min_value=0.0, max_value=100.0, step=0.1) | |
| cb_person_cred_hist_length=st.slider("Credit history length (in years)", min_value=0, max_value=50, step=1) | |
| credit_score=st.slider("Credit score", min_value=300, max_value=850, step=1) | |
| previous_loan_defaults_on_file=st.selectbox("Previous loan defaults on file", options=[0, 1]) | |
| if st.button("Predict Loan Approval"): | |
| input = np.array([[ | |
| person_age, | |
| person_gender, | |
| person_eduation, | |
| person_income, | |
| person_emp_exp, | |
| person_home_ownership, | |
| loan_amnt, | |
| loan_intent, | |
| loan_int_rate, | |
| loan_percent_income, | |
| cb_person_cred_hist_length, | |
| credit_score, | |
| previous_loan_defaults_on_file | |
| ]]) | |
| prediction = model.predict(input)[0] | |
| result = 'approved' if prediction == 1 else 'rejected' | |
| st.success(f"Predicted status: {result}") |