eda.py

import streamlit as st
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
from PIL import Image

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

def run():
    # Membuat Title
    st.title('Home Credit Analysis')

    # Membuat Sub Header
    st.subheader('EDA for Home Credit Analysis')

    # Menambahkan Gambar
    image = Image.open('credit.jpeg')
    st.image(image, caption='Home Credit')

    # Menambahkan Deskripsi
    st.write('This page created by **Imam Zarkasie**')
    st.write('### Hello!')
    st.write('#### The competition of credit card service is heating up!')
    st.write('##### In this page we can explore customer segmentation, more than that this website provides an ability to predict a customer payment risk.')


    # Membuat Garis Lurus
    st.markdown('---')

    # Magic Syntax
    '''
    On this page, the author will do a simple exploration.
    The dataset used is the churn dataset.
    '''

    # Show DataFrame
    df = pd.read_csv('df_subset.csv')
    st.dataframe(df)

    #Melihat histogram fitur target
    # Membuat visualisasi Distribusi Payment
    fig, ax =plt.subplots(1,2,figsize=(15,6))

    sns.countplot(x='TARGET', data=df, palette="winter", ax=ax[0])
    ax[0].set_xlabel("Payment", fontsize= 12)
    ax[0].set_ylabel("# of Payment", fontsize= 12)
    fig.suptitle('Payment Distribution', fontsize=18, fontweight='bold')
    ax[0].set_ylim(0,300000)
    ax[0].tick_params(axis='x', rotation=90)
    plt.xlabel("Payment", fontsize= 12)
    plt.ylabel("# of Payment", fontsize= 12)

    for p in ax[0].patches:
        ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2,
                        p.get_height()+205), ha='center', va='center',fontsize = 11)

    df['TARGET'].value_counts().plot(kind='pie',autopct='%1.1f%%', textprops = {"fontsize":12})
    ax[1].set_ylabel("% of Payment", fontsize= 12)
    st.pyplot(fig)

    # Membuat visualisasi Distribusi Contract
    fig, ax =plt.subplots(1,2,figsize=(15,6))

    sns.countplot(x='NAME_CONTRACT_TYPE', data=df, palette="winter", ax=ax[0])
    ax[0].set_xlabel("Contract", fontsize= 12)
    ax[0].set_ylabel("# of Contract", fontsize= 12)
    fig.suptitle('Contract Distribution', fontsize=18, fontweight='bold')
    ax[0].set_ylim(0,300000)
    ax[0].tick_params(axis='x', rotation=90)
    plt.xlabel("Contract", fontsize= 12)
    plt.ylabel("# of Contract", fontsize= 12)

    for p in ax[0].patches:
        ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2,
                        p.get_height()+205), ha='center', va='center',fontsize = 11)

    df['NAME_CONTRACT_TYPE'].value_counts().plot(kind='pie',autopct='%1.1f%%', textprops = {"fontsize":12})
    ax[1].set_ylabel("% of Contract", fontsize= 12)
    plt.show()

    # Menampilkan plot di Streamlit
    st.pyplot(fig)

    # Membuat visualisasi Distribusi Gender
    fig, ax =plt.subplots(1,2,figsize=(15,6))

    sns.countplot(x='CODE_GENDER', data=df, palette="winter", ax=ax[0])
    ax[0].set_xlabel("Gender", fontsize= 12)
    ax[0].set_ylabel("# of Gender", fontsize= 12)
    fig.suptitle('Gender Distribution', fontsize=18, fontweight='bold')
    ax[0].set_ylim(0,300000)
    ax[0].tick_params(axis='x', rotation=90)
    plt.xlabel("Gender", fontsize= 12)
    plt.ylabel("# of Gender", fontsize= 12)

    for p in ax[0].patches:
        ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2,
                        p.get_height()+205), ha='center', va='center',fontsize = 11)

    df['CODE_GENDER'].value_counts().plot(kind='pie',autopct='%1.1f%%', textprops = {"fontsize":12})
    ax[1].set_ylabel("% of Gender", fontsize= 12)
    plt.show()

    # Menampilkan plot di Streamlit
    st.pyplot(fig)


    # Membuat plot scatter
    fig, ax = plt.subplots(figsize=(6, 3))
    sns.scatterplot(x='AMT_ANNUITY', y='AMT_CREDIT', hue='TARGET', data=df, ax=ax)

    # Menambahkan label sumbu dan judul plot
    plt.xlabel('AMT_ANNUITY')
    plt.ylabel('AMT_CREDIT')
    plt.title('Scatter Plot: AMT_ANNUITY vs AMT_CREDIT')

    # Menambahkan legenda
    plt.legend(title='Target')

    # Menampilkan plot di Streamlit
    st.pyplot(fig)

if __name__=='__main__':
    run()