|
import streamlit as st |
|
import pandas as pd |
|
import seaborn as sns |
|
import matplotlib.pyplot as plt |
|
import plotly.express as px |
|
from PIL import Image |
|
|
|
|
|
|
|
def run() : |
|
|
|
st.markdown("<h1 style='text-align: center;'>Exploratory Data Analysis</h1>", unsafe_allow_html=True) |
|
st.write('Berikut adalah EDA dari setiap feature') |
|
|
|
|
|
df_eda = pd.read_csv('eda_churn.csv') |
|
|
|
|
|
st.subheader('**EDA Feature Churn**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- *Customer* yang *churn* lebih banyak dari pada *customer* yang tidak *churn*') |
|
|
|
|
|
fig, ax =plt.subplots(1,2,figsize=(15,6)) |
|
|
|
sns.countplot(x='churn_risk_score', data=df_eda, palette="winter", ax=ax[0]) |
|
ax[0].set_xlabel("churn_risk_score", fontsize= 12) |
|
ax[0].set_ylabel("# of Customer", fontsize= 12) |
|
fig.suptitle('Customer Churn Distribution', fontsize=18, fontweight='bold') |
|
ax[0].set_ylim(0,23000) |
|
plt.xlabel("churn_risk_score", fontsize= 12) |
|
plt.ylabel("# of Customer", fontsize= 12) |
|
ax[0].set_xticks([0,1], ['Not Churn', 'Churn']) |
|
for p in ax[0].patches: |
|
ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+405), ha='center', va='center',fontsize = 11) |
|
|
|
df_eda['churn_risk_score'].value_counts().plot(kind='pie', labels = ['Not Churn', 'Churn'],autopct='%1.1f%%', textprops = {"fontsize":12}) |
|
ax[1].set_ylabel("% of Customer", fontsize= 12) |
|
st.pyplot(fig) |
|
|
|
|
|
st.subheader('**EDA Feature Age**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- *Customer* paling banyak adalah *customer* yang memiliki *range* umur 40-50 tahun') |
|
st.markdown('- *Customer* yang paling banyak *churn* adalah *customer* dengan *range* umur 50-60 tahun') |
|
st.markdown('- Akan tetapi jika dilihat dari persentase *churn* pada setiap kelas *range* umur, maka tidak ada perbedaan signifikan') |
|
|
|
|
|
fig, ax =plt.subplots(1,2,figsize=(15,6)) |
|
sns.countplot(x='AgeBin', data=df_eda, palette='winter', ax=ax[0]) |
|
ax[0].set_xlabel("Range Customer Age", fontsize= 12) |
|
ax[0].set_ylabel("# of Customer", fontsize= 12) |
|
fig.suptitle('Range Customer Age Distribution', fontsize=18, fontweight='bold') |
|
ax[0].set_ylim(0,7600) |
|
for p in ax[0].patches: |
|
ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+105), ha='center', va='center',fontsize = 10) |
|
|
|
df_eda['AgeBin'].value_counts().plot(kind='pie', autopct='%1.1f%%', textprops = {"fontsize":12}) |
|
ax[1].set_ylabel("% of Customer", fontsize= 10) |
|
st.pyplot(fig) |
|
|
|
|
|
fig, ax =plt.subplots(1,2,figsize=(15,6)) |
|
sns.countplot(data = df_eda, x = 'AgeBin', hue="churn_risk_score", palette = 'winter', order = ['(10, 20]', '(20, 30]', '(30, 40]', '(40, 50]', '(50, 60]', '(60, 70]'], ax=ax[0]) |
|
ax[0].set_title('Range Age Distribution', fontsize=14, fontweight='bold',) |
|
ax[0].set_xlabel("Range Age", fontsize= 12) |
|
ax[0].set_ylabel("# of Customer", fontsize= 12) |
|
ax[0].tick_params(axis="x", labelsize= 9.5) |
|
ax[0].legend(fontsize=10,title='Churn Classification', loc='upper right', labels=['Not Churn', 'Churn']) |
|
for p in ax[0].patches: |
|
ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+75), ha='center', va='center',fontsize = 10) |
|
ax[0].set_ylim(0,4700) |
|
|
|
|
|
sns.barplot(x = 'AgeBin', y = 'churn_risk_score', data = df_eda, palette = 'winter', order = ['(10, 20]', '(20, 30]', '(30, 40]', '(40, 50]', '(50, 60]', '(60, 70]'],ax=ax[1]) |
|
ax[1].set_xlabel("Range Age", fontsize= 12) |
|
ax[1].set_ylabel("% Churn", fontsize= 12) |
|
ax[1].set_title('% Churn based on Age', fontsize=14, fontweight='bold') |
|
ax[1].set_ylim(0,0.7) |
|
for p in ax[1].patches: |
|
ax[1].annotate("%.2f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+0.03), ha='center', va='center',fontsize = 11) |
|
st.pyplot(fig) |
|
|
|
|
|
st.subheader('**EDA Feature Time Spent**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- Jika dilihat pada visualisasi diatas maka `avg_time_spent` antara *customer* yang *churn* dan *customer* yang tidak *churn* tidak berbeda secara signifikan') |
|
|
|
|
|
fig =plt.figure(figsize=(15,6)) |
|
plt.rcParams['figure.figsize'] = (10, 5) |
|
sns.boxenplot(y=df_eda['avg_time_spent'], x= df_eda['churn_risk_score'], palette = 'Blues') |
|
plt.title('Average Time Spent vs Churn', fontsize = 20) |
|
st.pyplot(fig) |
|
|
|
|
|
|
|
st.subheader('**EDA Feature Transaction Value**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- *Customer* yang tidak *churn* memiliki *average transaction value* yang lebih tinggi (terpusat di 18.000-40.000) dari pada *customer* yang *churn* (terpusat di 16.000-36.000)') |
|
|
|
|
|
fig =plt.figure(figsize=(15,6)) |
|
plt.rcParams['figure.figsize'] = (10, 5) |
|
sns.boxenplot(y=df_eda['avg_transaction_value'], x= df_eda['churn_risk_score'], palette = 'Blues') |
|
plt.title('Average Transaction Value vs Churn', fontsize = 20) |
|
st.pyplot(fig) |
|
|
|
|
|
st.subheader('**EDA Feature Avg Frequency Login Days**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- *Customer* yang tidak *churn* memiliki *average frequency login days* yang lebih rendah (terpusat di 8-20x) dari pada *customer* yang *churn* (terpusat di 10-25x)') |
|
|
|
|
|
fig =plt.figure(figsize=(15,6)) |
|
plt.rcParams['figure.figsize'] = (10, 5) |
|
sns.boxenplot(y=df_eda['avg_frequency_login_days'], x= df_eda['churn_risk_score'], palette = 'Blues') |
|
plt.title('Average Frequency Login Days vs Churn', fontsize = 20) |
|
st.pyplot(fig) |
|
|
|
|
|
st.subheader('**EDA Feature Point Wallet**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- *Customer* yang tidak *churn* memiliki *points in wallet* yang lebih tinggi (terpusat di 700-800) dari pada *customer* yang *churn* (terpusat di 600-700)') |
|
|
|
|
|
fig =plt.figure(figsize=(15,6)) |
|
plt.rcParams['figure.figsize'] = (10, 5) |
|
sns.boxenplot(y=df_eda['points_in_wallet'], x= df_eda['churn_risk_score'], palette = 'Blues') |
|
plt.title('Points in Wallet vs Churn', fontsize = 20) |
|
st.pyplot(fig) |
|
|
|
|
|
st.subheader('**EDA Feature Gender**') |
|
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :') |
|
st.markdown('- *Customer* paling banyak adalah *customer* wanita (50.1%). Akan tetapi tidak berbeda signifikan, hanya berbeda 0.1% dari *customer* pria') |
|
st.markdown('- *Customer* yang paling banyak *churn* adalah *customer* wanita. Kemungkinan banyak pada kelas wanita karena *customer* paling banyak juga pada kelas ini') |
|
st.markdown('- Akan tetapi jika dilihat dari persentase *churn* pada setiap kelas *gender*, maka tidak ada perbedaan signifikan') |
|
|
|
|
|
fig, ax =plt.subplots(1,2,figsize=(15,6)) |
|
sns.countplot(x='gender', data=df_eda, palette='winter', ax=ax[0]) |
|
ax[0].set_xlabel("Gender", fontsize= 12) |
|
ax[0].set_ylabel("# of Customer", fontsize= 12) |
|
fig.suptitle('Gender Distribution', fontsize=18, fontweight='bold') |
|
ax[0].set_ylim(0,21000) |
|
for p in ax[0].patches: |
|
ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+305), ha='center', va='center',fontsize = 10) |
|
df_eda['gender'].value_counts().plot(kind='pie', autopct='%1.1f%%', textprops = {"fontsize":12}) |
|
ax[1].set_ylabel("% of Customer", fontsize= 10) |
|
st.pyplot(fig) |
|
|
|
|
|
fig, ax =plt.subplots(1,2,figsize=(15,6)) |
|
sns.countplot(data = df_eda, x = 'gender', hue="churn_risk_score", palette = 'winter', ax=ax[0]) |
|
ax[0].set_title('Gender Distribution', fontsize=14, fontweight='bold',) |
|
ax[0].set_xlabel("Gender", fontsize= 12) |
|
ax[0].set_ylabel("# of Customer", fontsize= 12) |
|
ax[0].tick_params(axis="x", labelsize= 9.5) |
|
ax[0].legend(fontsize=10,title='Churn Classification', loc='upper right', labels=['Not Churn', 'Churn']) |
|
for p in ax[0].patches: |
|
ax[0].annotate("%.0f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+175), ha='center', va='center',fontsize = 10) |
|
ax[0].set_ylim(0,13000) |
|
|
|
|
|
sns.barplot(x = 'gender', y = 'churn_risk_score', data = df_eda, palette = 'winter',ax=ax[1]) |
|
ax[1].set_xlabel("Gender", fontsize= 12) |
|
ax[1].set_ylabel("% Churn", fontsize= 12) |
|
ax[1].set_title('% Churn based on Gender', fontsize=14, fontweight='bold') |
|
ax[1].set_ylim(0,0.7) |
|
for p in ax[1].patches: |
|
ax[1].annotate("%.2f"%(p.get_height()), (p.get_x() + p.get_width() / 2, |
|
p.get_height()+0.02), ha='center', va='center',fontsize = 11) |
|
st.pyplot(fig) |
|
|
|
if __name__ == '__main__': |
|
run() |