src/prediction.py

import pandas as pd
import numpy as np 
import joblib
import streamlit as st

def predict(new_customer_obj, model_pipeline):
    new_cust_df = pd.DataFrame([new_customer_obj])
    st.dataframe(new_cust_df)
    st.write(new_cust_df.info())
    
    user1_prediction = model_pipeline.predict_proba(new_cust_df)[:, 1]
    label = model_pipeline.predict(new_cust_df)[0]
    return user1_prediction, label

def run():
    # load pipeline
    model_pipeline = joblib.load("./src/logistic_regression_pipeline.pkl")
    
    # fetch dataset 
    # data = pd.read_excel('./src/default_of_credit_card_clients.xls', index_col=0)
    # data.columns = data.iloc[0]
    # data = data.drop(data.index[0])
    
    # form creation
    with st.form(key="prediction_form"):
        limit_balance = st.number_input(label='limit balance', value=0, step=1, min_value=0)
        
        # SEX
        sex_options = {
            "Male": "1",
            "Female": "2"
        }
        sex_label = st.selectbox(
            "Sex", 
            options=list(sex_options.keys()), 
            index=None
        )
        
        # EDUCATION
        education_options = {
            "Graduate School": "1",
            "University": "2",
            "High School": "3", 
            "Others": "4"
        }
        education_label = st.selectbox(
            "Education", 
            options=list(education_options.keys()), 
            index=None
        )
            
        # MARITAL STATUS
        marital_options = {
            "Married": "1",
            "Single": "2",
            "Others": "3"
        }
        maritial_label = st.selectbox(
            "Martial Status", 
            options=list(marital_options.keys()),
            index=None
        )
        
        age = st.number_input("Age", value=1, step=1, min_value=1)
        
        st.write(" === Customer Credit Payment History === ")
    
        pay_options = {
                    "none": "0",
                    "pay duly": "-1",
                    "payment delay for 1 month": "1",
                    "payment delay for 2 month": "2",
                    "payment delay for 3 month": "3",
                    "payment delay for 4 month": "4",
                    "payment delay for 5 month": "5",
                    "payment delay for 6 month": "6",
                    "payment delay for 7 month": "7",
                    "payment delay for 8 month": "8",
                    "payment delay for 9 month and above": "9"
                }
        
        pay_4_label = st.selectbox(
            "June 2005", 
            options=list(pay_options.keys()),
        )
        pay_3_label = st.selectbox(
            "July 2005", 
            options=list(pay_options.keys()),
        )
        pay_2_label = st.selectbox(
            "August 2005", 
            options=list(pay_options.keys()),
        )
        pay_0_label = st.selectbox(
            "September 2005", 
            options=list(pay_options.keys()),
        )
        
        st.write(" === Amount of Bill Statement ===")
        
        bill_amt_4 = st.number_input("June 2005", value=0, step=1, help="can be minus. ex: -123456")
        bill_amt_3 = st.number_input("July 2005", value=0, step=1, help="can be minus. ex: -123456")
        bill_amt_2 = st.number_input("August 2005", value=0, step=1, help="can be minus. ex: -123456")
        bill_amt_1 = st.number_input("September 2005", value=0, step=1, help="can be minus. ex: -123456")
        
        st.write(" === Amount of Previous Statement ===")
        
        pay_amt_4 = st.number_input("June 2005", step=1, min_value=0, help="minimum 0")
        pay_amt_3 = st.number_input("July 2005", step=1, min_value=0, help="minimum 0")
        pay_amt_2 = st.number_input("August 2005", step=1, min_value=0, help="minimum 0")
        pay_amt_1 = st.number_input("September 2005", step=1, min_value=0, help="minimum 0")
        
        submitted = st.form_submit_button('Predict')
        
        if submitted:
            # error handling
            if sex_label == None:
                st.error('Sex cannot be empty')
                st.stop()
                
            if education_label == None:
                st.error('Education cannot be empty')
                st.stop()
                
            if maritial_label == None:
                st.error('Marital Status cannot be empty')
                st.stop()
            
            sex = sex_options[sex_label]
            education = education_options[education_label]
            marital_status = marital_options[maritial_label]
            
            pay_0 = pay_options[pay_0_label]
            pay_2 = pay_options[pay_2_label]
            pay_3 = pay_options[pay_3_label]
            pay_4 = pay_options[pay_4_label]
        
            new_customer = {
                "LIMIT_BAL": limit_balance,
                "SEX": sex,            # 1 = male, 2 = female
                "EDUCATION": education,      # 1 = graduate, 2 = university, 3 = high school
                "MARRIAGE": marital_status,       # 1 = married, 2 = single
                "AGE": age,
                "PAY_0": pay_0,
                "PAY_2": pay_2,
                "PAY_3": pay_3,
                "PAY_4": pay_4,
                "BILL_AMT1": bill_amt_1,
                "BILL_AMT2": bill_amt_2,
                "BILL_AMT3": bill_amt_3,
                "BILL_AMT4": bill_amt_4,
                "PAY_AMT1": pay_amt_1,
                "PAY_AMT2": pay_amt_2,
                "PAY_AMT3": pay_amt_3,
                "PAY_AMT4": pay_amt_4
            }
            
            proba_default,predict_label = predict(new_customer, model_pipeline)
            
            proba_label = "Not Default"
            if predict_label == 1:
                proba_label = "Default"
            
            st.write(f"""
                     proba_default = {proba_default}
                     prediction of default payment next month \n
                     prediction probability ={(proba_default * 100)[0]:.3f}% \n
                     prediction label = {proba_label}
                     """)
            

if __name__ == '__main__':
    run()