prediction.py

import streamlit as st
import pandas as pd
import numpy as np
import pickle
import json
from PIL import Image

#load
with open('list_kat.txt', 'r') as file_1:
  list_kat = json.load(file_1)

with open('list_num.txt', 'r') as file_2:
  list_num = json.load(file_2)

with open('scaler.pkl', 'rb') as file_3:
  scaler = pickle.load(file_3)

with open('ohe.pkl', 'rb') as file_4:
  ohe = pickle.load(file_4)

with open('model_SVM.pkl', 'rb') as file_5:
  model_svm = pickle.load(file_5)

def run():
    #membuat judul
    st.title('Credit Card prediction')
    #membuat sub header
    st.subheader('Tugas GC5')
    with st.form('Form_credit_prediciton'):
        limit_balance = st.number_input('Limit Balance', value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        sex = st.number_input('sex',value=1 ,help='1=male, 2=female',min_value=1,max_value=2, format='%d')
        education_level= st.number_input('education level',value=1,help='1=graduate school, 2=university, 3=high school, 4=others, 5=unknown',min_value=1,max_value=5,format='%d')
        marital_status= st.number_input('Marital status',value=2,help='1=married, 2=single, 3=others',min_value=1,max_value=3,format='%d')
        age= st.number_input('Age',value=15,help='Umur anda',min_value=1,max_value=99)
        pay_0= st.number_input('pay_0',value=1,help='-1=pay duly, 1=payment delay for one month, 2=payment delay for two months,...',min_value=-1,max_value=8)
        pay_2= st.number_input('pay_2',value=1,help='-1=pay duly, 1=payment delay for one month, 2=payment delay for two months,...',min_value=-1,max_value=8)
        pay_3= st.number_input('pay_3',value=1,help='-1=pay duly, 1=payment delay for one month, 2=payment delay for two months,...',min_value=-1,max_value=8)
        pay_4= st.number_input('pay_4',value=1,help='-1=pay duly, 1=payment delay for one month, 2=payment delay for two months,...',min_value=-1,max_value=8)
        pay_5= st.number_input('pay_5',value=1,help='-1=pay duly, 1=payment delay for one month, 2=payment delay for two months,...',min_value=-1,max_value=8)
        pay_6= st.number_input('pay_6',value=1,help='-1=pay duly, 1=payment delay for one month, 2=payment delay for two months,...',min_value=-1,max_value=8)
        bill_amt_1= st.number_input('bill_amt_1',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        bill_amt_2= st.number_input('bill_amt_2',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        bill_amt_3= st.number_input('bill_amt_3',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        bill_amt_4= st.number_input('bill_amt_4',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        bill_amt_5= st.number_input('bill_amt_5',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        bill_amt_6= st.number_input('bill_amt_6',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        pay_amt_1= st.number_input('pay_amt_1',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        pay_amt_2= st.number_input('pay_amt_2',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        pay_amt_3= st.number_input('pay_amt_3',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        pay_amt_4= st.number_input('pay_amt_4',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        pay_amt_5= st.number_input('pay_amt_5',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)
        pay_amt_6= st.number_input('pay_amt_6',value = 10000000, help='numerik int ribuan lebih', min_value = 1000)

        #bikin submit button form
        submitted = st.form_submit_button('Predict')
  
    data_inf = {
        'limit_balance' : limit_balance,
        "sex" : sex,
        "education_level" : education_level,
        "marital_status" : marital_status,
        'age' : age,
        'pay_0' : pay_0,
        'pay_2' : pay_2,
        'pay_3' : pay_3,
        'pay_4' : pay_4,
        'pay_5' : pay_5,
        'pay_6' : pay_6,
        'bill_amt_1' : bill_amt_1,
        'bill_amt_2' : bill_amt_2,
        'bill_amt_3' : bill_amt_3,
        'bill_amt_4' : bill_amt_4,
        'bill_amt_5' : bill_amt_5,
        'bill_amt_6' : bill_amt_6,
        'pay_amt_1' : pay_amt_1,
        'pay_amt_2' : pay_amt_2,
        'pay_amt_3' : pay_amt_3,
        'pay_amt_4' : pay_amt_4,
        'pay_amt_5' : pay_amt_5,
        'pay_amt_6' : pay_amt_6
        }
    data_inf = pd.DataFrame([data_inf])
    st.dataframe(data_inf)


    if submitted:
        #Split categorical and numerical
        data_inf_num = data_inf[list_num]
        data_inf_kat = data_inf[list_kat]

        #Feature Scaling and Encoding
        data_inf_scaled = scaler.transform(data_inf_num)
        data_inf_encoding = ohe.transform(data_inf_kat)
        nama_fitur=ohe.get_feature_names_out()
        data_inf_encoding=data_inf_encoding.toarray()

        data_inf_final =  np.concatenate([data_inf_scaled,data_inf_encoding], axis = 1)
        
        #predict using SVM

        y_pred_inf = model_svm.predict(data_inf_final)

        st.write('## Default payment: ', str(int(y_pred_inf)))



if __name__ == '__main__':
   run()