Spaces:
Runtime error
Runtime error
Upload 7 files
Browse files- app.py +20 -0
- churn_best_model.h5 +3 -0
- eda.py +100 -0
- image_pred.jpg +0 -0
- prediction.py +86 -0
- preprocessor_churn.pkl +3 -0
- requirements.txt +8 -0
app.py
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import eda
|
3 |
+
import prediction
|
4 |
+
from PIL import Image
|
5 |
+
|
6 |
+
# Set Config dan icon
|
7 |
+
st.set_page_config(
|
8 |
+
page_title='Churn Prediction',
|
9 |
+
layout='wide',
|
10 |
+
)
|
11 |
+
|
12 |
+
#klik eda, bawa ke page eda
|
13 |
+
navigation = st.sidebar.selectbox('Select Page (EDA/Churn Prediction):', ('EDA', 'Churn Prediction'))
|
14 |
+
|
15 |
+
|
16 |
+
#Run modul dengan if else
|
17 |
+
if navigation == 'EDA':
|
18 |
+
eda.run()
|
19 |
+
else :
|
20 |
+
prediction.run()
|
churn_best_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1b8f9f4329696af5ceb64050282eca7f556586ef77213e85cfb571c80e8de09
|
3 |
+
size 262152
|
eda.py
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import seaborn as sns
|
4 |
+
import matplotlib.pyplot as plt
|
5 |
+
import plotly.express as px
|
6 |
+
from PIL import Image
|
7 |
+
|
8 |
+
def run() :
|
9 |
+
# Membuat Sub Header
|
10 |
+
st.title('**EDA Churn Customer**')
|
11 |
+
st.write('~ P2M1-Desti Ratna Komala-RMT-020')
|
12 |
+
#menambahkan Gambar
|
13 |
+
image = Image.open('image_pred.jpg')
|
14 |
+
st.image(image, caption='churn.jpg')
|
15 |
+
|
16 |
+
# Import df
|
17 |
+
df_eda = pd.read_csv('https://raw.githubusercontent.com/destiratnakomala/Hacktiv8_Folder/main/churn.csv')
|
18 |
+
|
19 |
+
#membuat garis lurus
|
20 |
+
st.markdown('-----')
|
21 |
+
|
22 |
+
#magic syntax
|
23 |
+
'''
|
24 |
+
Pada page ini, akan dilakukan ekplorasi dataset sederhana.
|
25 |
+
Berikut adalah dataset Customer Churn yang digunakan
|
26 |
+
'''
|
27 |
+
#membuat title
|
28 |
+
st.subheader('Customer Churn EDA')
|
29 |
+
|
30 |
+
# Import df
|
31 |
+
df = pd.read_csv('https://raw.githubusercontent.com/destiratnakomala/Hacktiv8_Folder/main/churn.csv')
|
32 |
+
st.dataframe(df)
|
33 |
+
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
+
st.write('Dari visualisasi dibawah dapat disimpulkan bahwa :')
|
40 |
+
st.markdown('- *Customer* yang *churn* lebih banyak dari pada *customer* yang tidak *churn*')
|
41 |
+
#membuat garis lurus
|
42 |
+
st.markdown('-----')
|
43 |
+
pilihanuser=st.selectbox('Pilih Feature:', ('gender', 'region_category', 'membership_category', 'joined_through_referral', 'preferred_offer_types', 'medium_of_operation', 'internet_option', 'used_special_discount', 'offer_application_preference', 'past_complaint', 'complaint_status', 'feedback'))
|
44 |
+
|
45 |
+
|
46 |
+
#--------------------------------------------
|
47 |
+
|
48 |
+
fig, ax =plt.subplots(1,3,figsize=(25,8))
|
49 |
+
fig.suptitle(f'{pilihanuser} terhadap Customer Churn', fontsize=17, fontweight='bold')
|
50 |
+
#visualisasikan data
|
51 |
+
|
52 |
+
plt.subplot(1,3,1)
|
53 |
+
plt.title(f'{pilihanuser} terhadap Customer Churn', fontsize=14)
|
54 |
+
ax = sns.countplot(data = df, x = df[pilihanuser], hue="churn_risk_score", palette = 'pastel')
|
55 |
+
plt.ylabel("#churn", fontsize= 14)
|
56 |
+
plt.xticks(rotation=90)
|
57 |
+
plt.legend(loc=0)
|
58 |
+
|
59 |
+
|
60 |
+
plt.subplot(1,3,2)
|
61 |
+
plt.title(f'{pilihanuser} terhadap %Customer Churn', fontsize=12)
|
62 |
+
ax = sns.barplot(x = df[pilihanuser], y = "churn_risk_score", data = df, palette = sns.color_palette('pastel')[1:2], errorbar= None)
|
63 |
+
plt.ylabel("%Churn", fontsize= 14)
|
64 |
+
plt.xticks(rotation=90)
|
65 |
+
|
66 |
+
for p in ax.patches:
|
67 |
+
ax.annotate("%.2f" %(p.get_height()), (p.get_x()+0.3, p.get_height()+0.005),fontsize=12)
|
68 |
+
|
69 |
+
plt.subplot(1,3,3)
|
70 |
+
round(df[pilihanuser].value_counts()/df.shape[0]*500,2).plot.pie(autopct= '%1.1f%%',colors=sns.color_palette('pastel')[0:10],shadow=True, legend=None)
|
71 |
+
plt.ylabel("")
|
72 |
+
plt.xticks(rotation=45)
|
73 |
+
plt.title(pilihanuser, fontsize=14)
|
74 |
+
st.pyplot(fig)
|
75 |
+
|
76 |
+
|
77 |
+
st.markdown('-----')
|
78 |
+
fig=plt.figure(figsize=(15, 5))
|
79 |
+
pilihanuser2=st.selectbox('Pilih Feature Numerik:',('age','days_since_last_login', 'avg_time_spent','avg_transaction_value', 'avg_frequency_login_days', 'points_in_wallet'))
|
80 |
+
plt.subplot(1,2,1)
|
81 |
+
sns.distplot(df[pilihanuser2])
|
82 |
+
plt.ticklabel_format(style='plain', axis='x')
|
83 |
+
plt.ylabel('')
|
84 |
+
|
85 |
+
plt.subplot(1,2,2)
|
86 |
+
sns.kdeplot(df.loc[(df['churn_risk_score'] == 0), pilihanuser2], label = 'not_churn', fill = True)
|
87 |
+
sns.kdeplot(df.loc[(df['churn_risk_score'] == 1), pilihanuser2], label = 'churn', fill = True)
|
88 |
+
plt.ylabel('')
|
89 |
+
plt.legend()
|
90 |
+
st.pyplot(fig)
|
91 |
+
|
92 |
+
|
93 |
+
|
94 |
+
|
95 |
+
#membuat garis lurus
|
96 |
+
st.markdown('-----')
|
97 |
+
|
98 |
+
|
99 |
+
if __name__ == '__main__':
|
100 |
+
run()
|
image_pred.jpg
ADDED
prediction.py
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import numpy as np
|
4 |
+
import pickle
|
5 |
+
from tensorflow.keras.models import load_model
|
6 |
+
|
7 |
+
|
8 |
+
def run() :
|
9 |
+
# Load Model
|
10 |
+
with open('preprocessor_churn.pkl', 'rb') as file_1:
|
11 |
+
preprocessor = pickle.load(file_1)
|
12 |
+
model_churn = load_model('churn_best_model.h5', compile=False)
|
13 |
+
|
14 |
+
# Membuat Title
|
15 |
+
st.markdown("<h1 style='text-align: center;'>Churn Customer Prediction</h1>", unsafe_allow_html=True)
|
16 |
+
|
17 |
+
# Menambahkan Deskripsi form
|
18 |
+
st.write('Page ini berisi pemodelan untuk memprediksi churn customer. Silakan masukkan data Anda pada form dibawah ini.')
|
19 |
+
|
20 |
+
#Membuat Form
|
21 |
+
with st.form(key= 'form_customer'):
|
22 |
+
|
23 |
+
st.markdown('### **Data Customer**')
|
24 |
+
user_id = st.text_input('User ID',value= '')
|
25 |
+
gender = st.selectbox('Gender',('M','F'),index=1)
|
26 |
+
age = st.slider('Age',10,90,30)
|
27 |
+
region_category = st.radio('Region', options=['City','Village','Town'], horizontal=True)
|
28 |
+
internet_option = st.selectbox('Internet Option',('Wi-Fi','Fiber_Optic', 'Mobile_Data'),index=1)
|
29 |
+
medium_of_operation = st.radio('Medium', options=['Desktop','Smartphone','Both'], horizontal=True)
|
30 |
+
st.markdown('---')
|
31 |
+
st.markdown('### **Login Data**')
|
32 |
+
days_since_last_login = st.slider('Days Since Last Login',0,30,3)
|
33 |
+
avg_frequency_login_days = st.slider('Avg Frequency Login Days',0,90,14)
|
34 |
+
st.markdown('---')
|
35 |
+
st.markdown('### **Membership Data**')
|
36 |
+
joined_through_referral = st.selectbox('Referral',('Yes','No'),index=1)
|
37 |
+
membership_category = st.selectbox('Membership Category',('No Membership','Basic Membership','Silver Membership', 'Premium Membership', 'Gold Membership', 'Platinum Membership'),index=1)
|
38 |
+
st.markdown('---')
|
39 |
+
st.markdown('### **Transaction Data**')
|
40 |
+
points_in_wallet = st.number_input('Points in Wallet', min_value=0, max_value=2070, value=600 ,step=1)
|
41 |
+
avg_transaction_value = st.number_input('Avg Transaction Value', min_value=800, max_value=90000, value=30000 ,step=1)
|
42 |
+
preferred_offer_types = st.radio('Offer Types', options=['Without Offers','Credit/Debit Card Offers','Gift Vouchers/Coupons'], horizontal=True)
|
43 |
+
used_special_discount = st.selectbox('Used Special Discount',('Yes','No'),index=1)
|
44 |
+
past_complaint = st.selectbox('Past Complaint',('Yes','No'),index=1)
|
45 |
+
feedback = st.selectbox('Feedback',('Poor Website','Poor Customer Service', 'Too many ads', 'Poor Product Quality', 'No reason specified', 'Products always in Stock', 'Reasonable Price', 'Quality Customer Care', 'User Friendly Website'),index=1)
|
46 |
+
submitted = st.form_submit_button('Predict')
|
47 |
+
|
48 |
+
# Create New Data
|
49 |
+
data_inf = {
|
50 |
+
'user_id' : user_id,
|
51 |
+
'age' : age,
|
52 |
+
'gender' : gender,
|
53 |
+
'region_category' : region_category,
|
54 |
+
'internet_option' : internet_option,
|
55 |
+
'medium_of_operation' : medium_of_operation,
|
56 |
+
'days_since_last_login' : days_since_last_login,
|
57 |
+
'avg_frequency_login_days' : avg_frequency_login_days,
|
58 |
+
'joined_through_referral' : joined_through_referral,
|
59 |
+
'membership_category' : membership_category,
|
60 |
+
'points_in_wallet' : points_in_wallet,
|
61 |
+
'avg_transaction_value' : avg_transaction_value,
|
62 |
+
'used_special_discount' : used_special_discount,
|
63 |
+
'past_complaint' : past_complaint,
|
64 |
+
'preferred_offer_types' : preferred_offer_types,
|
65 |
+
'feedback' : feedback
|
66 |
+
}
|
67 |
+
|
68 |
+
data_inf = pd.DataFrame([data_inf])
|
69 |
+
data_inf
|
70 |
+
|
71 |
+
if submitted :
|
72 |
+
# Feature Scaling and Feature Encoding
|
73 |
+
data_final = preprocessor.transform(data_inf)
|
74 |
+
|
75 |
+
# Predict using Linear Regression
|
76 |
+
y_inf_pred = np.where(model_churn.predict(data_final) >= 0.5, 1, 0)
|
77 |
+
|
78 |
+
if y_inf_pred == 1:
|
79 |
+
prediction = 'Churn'
|
80 |
+
else:
|
81 |
+
prediction = 'Not Churn'
|
82 |
+
|
83 |
+
st.write('##### This customer is predicted:', prediction)
|
84 |
+
|
85 |
+
if __name__ == '__main__':
|
86 |
+
run()
|
preprocessor_churn.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53f9ce0813c933ea397ed161e771c8cf61281e54e1d41745100fb6636ed89aeb
|
3 |
+
size 3148
|
requirements.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
streamlit
|
2 |
+
pandas
|
3 |
+
seaborn
|
4 |
+
matplotlib
|
5 |
+
tensorflow == 2.11.0
|
6 |
+
scikit-learn == 1.0.2
|
7 |
+
numpy
|
8 |
+
plotly
|