prediction.py

# Contents of `app2.py`
import streamlit as st
import pandas as pd 
import joblib
import json

def app():
    st.title('Make Predictions')
    
    # load the model
    with open('model.pkl', 'rb') as file_1:
        model = joblib.load(file_1)
        
    with open('column.txt', 'r') as file_2:
        selected_columns = json.load(file_2)
        
    with open('scaler.pkl', 'rb') as file_3:
        scaler = joblib.load(file_3)
    
    st.title("Data Input Options")

    option = st.selectbox(
        "How would you like to input the data?",
        ("Upload a CSV file", "Manually input data")
    )

    if option == "Upload a CSV file":
        uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
        if uploaded_file is not None:
            df = pd.read_csv(uploaded_file)
            st.write("Data Preview:")
            st.write(df)
            
            # Select only the columns for modeling
            data_inference_num = df[selected_columns]

            # Scaling the data
            data_inference_scaled = scaler.transform(data_inference_num)

            # Create new dataframe
            data_inference_final = pd.DataFrame(data_inference_scaled, columns=selected_columns)

            # Predict the defaulter
            predicted_defaulter = model.predict(data_inference_final)

            # Show result
            st.write("Predicted Defaulter Status:")
            st.write(predicted_defaulter)
            
    elif option == "Manually input data":
        st.write("Enter your data:")
        # Define empty lists for each attribute
        limit_balance = []
        sex = []
        education_level = []
        marital_status = []
        age = []
        pay_0 = []
        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 = []
        
        limit_balance.append(st.number_input("Limit Balance", min_value=0))
        sex.append(st.selectbox("Sex", [1, 2]))
        education_level.append(st.selectbox("Education Level", [0, 1, 2, 3]))
        marital_status.append(st.selectbox("Marital Status", [0, 1, 2 , 3]))
        age.append(st.number_input("Age", min_value=0))
        pay_0.append(st.number_input("Pay 0", min_value=-2, max_value=12))
        pay_2.append(st.number_input("Pay 2", min_value=-2, max_value=12))
        pay_3.append(st.number_input("Pay 3", min_value=-2, max_value=12))
        pay_4.append(st.number_input("Pay 4", min_value=-2, max_value=12))
        pay_5.append(st.number_input("Pay 5", min_value=-2, max_value=12))
        pay_6.append(st.number_input("Pay 6", min_value=-2, max_value=12))
        bill_amt_1.append(st.number_input("Bill Amount 1", min_value=0))
        bill_amt_2.append(st.number_input("Bill Amount 2", min_value=0))
        bill_amt_3.append(st.number_input("Bill Amount 3", min_value=0))
        bill_amt_4.append(st.number_input("Bill Amount 4", min_value=0))
        bill_amt_5.append(st.number_input("Bill Amount 5", min_value=0))
        bill_amt_6.append(st.number_input("Bill Amount 6", min_value=0))
        pay_amt_1.append(st.number_input("Pay Amount 1", min_value=0))
        pay_amt_2.append(st.number_input("Pay Amount 2", min_value=0))
        pay_amt_3.append(st.number_input("Pay Amount 3", min_value=0))
        pay_amt_4.append(st.number_input("Pay Amount 4", min_value=0))
        pay_amt_5.append(st.number_input("Pay Amount 5", min_value=0))
        pay_amt_6.append(st.number_input("Pay Amount 6", min_value=0))

        if st.button("Submit"):
            data = {
                '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
            }
            df = pd.DataFrame(data)
            st.write("Data Preview:")
            st.write(df)
            
            # Select only the columns for modeling
            data_inference_num = df[selected_columns]

            # Scaling the data
            data_inference_scaled = scaler.transform(data_inference_num)

            # Create new dataframe
            data_inference_final = pd.DataFrame(data_inference_scaled, columns=selected_columns)

            # Predict the defaulter
            predicted_defaulter = model.predict(data_inference_final)

            # Show result
            st.write("Predicted Defaulter Status:")
            st.write(predicted_defaulter)