import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px

st.set_page_config(
    page_title = 'Credit Card Default - EDA',
    layout='wide',
    initial_sidebar_state='expanded'
)

def run():
    # Membuat title
    st.title('Model Prediksi Credit Card Default')

    # Membuat Subheader
    st.subheader('EDA untuk Analisis Dataset Credit Card Default')

    # Menambah Gambar
    st.image('https://media.istockphoto.com/id/957837328/photo/business-debt-collection-or-recovery-unpaid-invoice.jpg?s=612x612&w=0&k=20&c=7sH7P4t7Fl2PjFfAUOIolZictaF8CsXXsxkbwZBz98g=',
             caption= 'Credit Card Default')
    
    # Menambah Deskripsi
    st.write('-'*50)
    st.write('Graded Challenge 5')
    st.write('Nama  : Achmad Abdillah Ghifari')
    st.write('Batch : BSD-006')
    st.write('-'*50)

    # menjelaskan kegunaan page ini
    st.write('Pada page ini, kita akan melihat exploratory data analyst (EDA) dari dataset credit card default yang dapat dilihat di [BigQuery](https://console.cloud.google.com/bigquery?p=bigquery-public-data&d=ml_datasets&t=credit_card_default&page=table&project=graded-challenge-5&ws=!1m5!1m4!4m3!1sbigquery-public-data!2sml_datasets!3scredit_card_default). dalam exploratory data analysis ini kita akan mencoba menjawab pertanyaan-pertanyaan berikut')
    st.write('1. bagaimana distribusi limit balance customer pada data?')
    st.write('2. bagaimana persebaran limit balance dan age?')
    st.write('3. marital status apa yang memiliki average limit_balance tertinggi?')
    st.write('4. apakah lebih banyak customer yang membayar atau melakukan default?')
    st.write('5. customer umur berapa yang paling sering melakukan default?')
    st.write('6. apa education level terbanyak dari customer kartu kredit?')
    st.write('7. berapa limit balance yang paling sering dimiliki kedua gender?')

    # membuat garis lurus
    st.markdown('---')

    # show dataframe
    st.write('### Credit Card Default Dataset')
    data = pd.read_csv('P1G5_Set_1_A.A_Ghifari(Changed).csv')
    st.dataframe(data)


    # Membuat Histogram (EDA 1)
    st.write('### Histogram of limit balance')
    fig = plt.figure(figsize=[15,5])
    sns.histplot(data['limit_balance'], kde=True, bins = 30)
    st.pyplot(fig)

    # Membuat ScatterPlot (EDA 2)
    st.write('### Scatterplot of limit balance and age')
    fig = plt.figure(figsize=[15,5])
    sns.scatterplot(x = 'limit_balance', y = 'age', hue= 'default', data = data)
    st.pyplot(fig)

    # Membuat barplot (EDA 3)
    st.write('### barchart of marital status and limit balance')
    fig = plt.figure(figsize=[15,5])
    sns.barplot(data=data, x='marital_status', y='limit_balance',)
    st.pyplot(fig)

    # Membuat pie chart (EDA 4)
    st.write('### pie chart of if a customer has defaulted')
    fig = plt.figure(figsize=(15,5))
    data['default'].value_counts().plot(kind='pie', autopct='%.2f%%')
    st.pyplot(fig)

    # Membuat line chart (EDA 5)
    st.write('### age of defaulting customer')
    Def_Age= data.groupby(['age', 'default']).size().unstack(fill_value=0)
    fig, ax = plt.subplots(figsize=[15, 5])
    Def_Age.plot(kind='line', ax=ax)
    st.pyplot(fig)

    # Membuat bar chart (EDA 6)
    st.write('### The amount of education level')
    fig = plt.figure(figsize=[15,5])
    data['education_level'].value_counts().plot(kind='bar')
    st.pyplot(fig)

    # Membuat line chart (EDA7)
    st.write('### limit balance of gender')
    Sex_Bal= data.groupby(['limit_balance', 'sex']).size().unstack(fill_value=0)
    fig, ax = plt.subplots(figsize=[15, 5])
    Sex_Bal.plot(kind='line', ax=ax)
    st.pyplot(fig)

if __name__ == '__main__':
    run()