predict_credit_card_default.py

import streamlit as st
import pandas as pd
import pickle
import streamlit as st

import pandas as pd
import numpy as np
import pickle
import json

# Load the pre-trained model using pickle
with open('best_svm_model.pkl', 'rb') as file_1:
  model = pickle.load(file_1)

# Create a Streamlit web app
def run():
    st.title("Credit Card Default Prediction Dashboard")

    # Add input fields for user input
    st.header("User Input Features")

    with st.form('predict player'):
            st.title('Playernya aja')

    # Input fields for each feature
            limit_balance = st.slider("LIMIT_BAL (Amount of Credit in NT dollars)", 0, 1000000, 50000)
            sex = st.radio("SEX (Gender)", ["Male", "Female"])
            education = st.radio("EDUCATION (Education Level)", ["Graduate School", "University", "High School", "Others"])
            marriage = st.radio("MARRIAGE (Marital Status)", ["Married", "Single", "Others"])
            age = st.slider("AGE (Age in years)", 20, 80, 30)
            st.write('Payment Status')
            st.write("-1 : Sudah Dibayar Sebelum H-1")
            st.write("-2 : Sudah Dibayar Sebelum H-2")
            st.write("0 : Dibayar Tepat Waktu")
            st.write("2 : Telat Pembayaran 2 Bulan")
            st.write("3 : Telat Pembayaran 3 Bulan")
            st.write("4 : Telat Pembayaran 4 Bulan")
            st.write("5 : Telat Pembayaran 5 Bulan")
            st.write("6 : Telat Pembayaran 6 Bulan")
            pay_status_sept = st.slider("PAY_0 (Repayment status in September, 2005)", -2, 8, 0)
            pay_status_aug = st.slider("PAY_2 (Repayment status in August, 2005)", -2, 8, 0)
            pay_status_jul = st.slider("PAY_3 (Repayment status in July, 2005)", -2, 8, 0)
            pay_status_jun = st.slider("PAY_4 (Repayment status in June, 2005)", -2, 8, 0)
            pay_status_may = st.slider("PAY_5 (Repayment status in May, 2005)", -2, 8, 0)
            pay_status_apr = st.slider("PAY_6 (Repayment status in April, 2005)", -2, 8, 0)
            bill_amt_sept = st.slider("BILL_AMT1 (Bill statement in September, 2005 - NT dollar)", 0, 1000000, 5000)
            bill_amt_aug = st.slider("BILL_AMT2 (Bill statement in August, 2005 - NT dollar)", 0, 1000000, 5000)
            bill_amt_jul = st.slider("BILL_AMT3 (Bill statement in July, 2005 - NT dollar)", 0, 1000000, 5000)
            bill_amt_jun = st.slider("BILL_AMT4 (Bill statement in June, 2005 - NT dollar)", 0, 1000000, 5000)
            bill_amt_may = st.slider("BILL_AMT5 (Bill statement in May, 2005 - NT dollar)", 0, 1000000, 5000)
            bill_amt_apr = st.slider("BILL_AMT6 (Bill statement in April, 2005 - NT dollar)", 0, 1000000, 5000)
            pay_amt_sept = st.slider("PAY_AMT1 (Previous payment in September, 2005 - NT dollar)", 0, 100000, 500)
            pay_amt_aug = st.slider("PAY_AMT2 (Previous payment in August, 2005 - NT dollar)", 0, 100000, 500)
            pay_amt_jul = st.slider("PAY_AMT3 (Previous payment in July, 2005 - NT dollar)", 0, 100000, 500)
            pay_amt_jun = st.slider("PAY_AMT4 (Previous payment in June, 2005 - NT dollar)", 0, 100000, 500)
            pay_amt_may = st.slider("PAY_AMT5 (Previous payment in May, 2005 - NT dollar)", 0, 100000, 500)
            pay_amt_apr = st.slider("PAY_AMT6 (Previous payment in April, 2005 - NT dollar)", 0, 100000, 500)

            submit = st.form_submit_button("Predict Player Rating")

    # Define mappings for education and marriage
    education_mapping = {
        "Graduate School": 1,
        "University": 2,
        "High School": 3,
        "Others": 4
    }

    marriage_mapping = {
        "Married": 1,
        "Single": 2,
        "Others": 3
    }

    # Create a DataFrame with user input data
    user_input_data = pd.DataFrame({
        "limit_balance": [limit_balance],
        "sex": [1 if sex == "Male" else 2],  # Map 'Male' to 1 and 'Female' to 2
        "education_level": [education_mapping[education]],
        "marital_status": [marriage_mapping[marriage]],
        "age": [age],
        "pay_1": [pay_status_sept],
        "pay_2": [pay_status_aug],
        "pay_3": [pay_status_jul],
        "pay_4": [pay_status_jun],
        "pay_5": [pay_status_may],
        "pay_6": [pay_status_apr],
        "bill_amt_1": [bill_amt_sept],
        "bill_amt_2": [bill_amt_aug],
        "bill_amt_3": [bill_amt_jul],
        "bill_amt_4": [bill_amt_jun],
        "bill_amt_5": [bill_amt_may],
        "bill_amt_6": [bill_amt_apr],
        "pay_amt_1": [pay_amt_sept],
        "pay_amt_2": [pay_amt_aug],
        "pay_amt_3": [pay_amt_jul],
        "pay_amt_4": [pay_amt_jun],
        "pay_amt_5": [pay_amt_may],
        "pay_amt_6": [pay_amt_apr]
    })

    # Predict button
    if submit:
        # Make predictions using the loaded model
        predicted_default = model.predict(user_input_data)

        # Display the prediction result
        st.subheader("Prediction Result")
        if predicted_default[0] == 1:
            st.write("The model predicts that the client may default on their credit card payment.")
        else:
            st.write("The model predicts that the client is unlikely to default on their credit card payment.")





            #limit_balance,sex,education_level,marital_status,age,pay_1,pay_2,pay_3,pay_4,pay_5,pay_6,bill_amt_1,bill_amt_2,bill_amt_3,bill_amt_4,bill_amt_5,bill_amt_6,pay_amt_1,pay_amt_2,pay_amt_3,pay_amt_4,pay_amt_5,pay_amt_6,default_payment_next_month,Klasifikasi
    #0,240000.0,2,2,1,41.0,1.0,-1.0,-1.0,-1.0,-1,-1,0.0,40529.0,3211.0,9795.0,11756.0,12522.0,40529.0,3211.0,9795.0,11756.0,12522.0,6199.0,0,Dewasa