replica milestone 1

app.py

@@ -0,0 +1,11 @@
+import streamlit as st
+import eda
+import prediction
+
+navigation = st.sidebar.selectbox('page : ', ('EDA', 'Churn Prediction'))
+
+if navigation == 'EDA':
+    eda.run()
+
+else:
+    prediction.run()

churn_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253015b1eebae93237b0bc62a9ef768eafcc48a3b79598b264c830c65a799643
+size 130772

eda.py

@@ -0,0 +1,109 @@
+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
+
+
+st.set_page_config(
+    page_title = 'Churn Condition',
+    layout = 'wide',
+    initial_sidebar_state='expanded'
+)
+
+def run():
+
+    # title
+    st.title( 'Churn Prediction')
+
+    # sub header
+    st.subheader('Churn or Not Churn')
+
+    # insert image
+    image = Image.open('2.jpg')
+    st.image(image, caption='image from project pro, education purpose only')
+
+    # Deskripsi
+    st.write('Exploratory Data from Churn dataset')
+
+    # show data frame
+    st.write('The first 10 Data')
+    df = pd.read_csv('https://raw.githubusercontent.com/mukhlishr/rasyidi/main/churn.csv')
+    st.dataframe(df.head(10))
+
+    # Barplot target columns 
+    st.write('###### Churn condition ')
+    st.write('###### Churn = 1 ; Not Churn = 0 ')
+    fig=plt.figure(figsize=(15,5))
+    sns.countplot(x='churn_risk_score', data = df)
+    st.pyplot(fig)
+
+   # Barplot avg transaction value 
+   # st.write('###### Avg Transaction Value by Customer churn')
+   # a=df[df['churn_risk_score']==1]['avg_transaction_value']
+   # fig=plt.figure(figsize=(15,5))
+   # sns.barplot(x=a.index, y=a)
+   # st.pyplot(fig)
+
+    # Barplot frequency login
+    st.write('###### Avg Frequency login (1 = 1-10, 2 = 11-20, ... 7 >= 51)')
+    bins = [-1, 10,20,30,40,50,100]
+    labels =[1,2,3,4,5,6,7]
+    df['binned_frequency_login'] = pd.cut(df['avg_frequency_login_days'], bins,labels=labels).astype(float)
+    fig=plt.figure(figsize=(15,5))
+    sns.countplot(x='binned_frequency_login', data = df)
+    st.pyplot(fig)
+
+    # Pieplot membership
+    st.write('###### Membership')
+    data = df['membership_category'].value_counts()
+    keys = df['membership_category'].value_counts().index
+    palette_color = sns.color_palette('bright')
+    fig=plt.figure(figsize=(15,5))
+    plt.pie(data, labels=keys, colors=palette_color, autopct='%.0f%%')
+    plt.title('Pieplot')
+    st.pyplot(fig)    
+
+    # Pieplot joined through referral 
+    st.write('###### joined through referral')
+    data = df['joined_through_referral'].value_counts()
+    keys = df['joined_through_referral'].value_counts().index
+    palette_color = sns.color_palette('bright')
+    fig=plt.figure(figsize=(15,5))
+    plt.pie(data, labels=keys, colors=palette_color, autopct='%.0f%%')
+    plt.title('Pieplot')
+    st.pyplot(fig)    
+
+    # Pieplot preferred_offer_types 
+    st.write('###### preferred offer types')
+    data = df['preferred_offer_types'].value_counts()
+    keys = df['preferred_offer_types'].value_counts().index
+    palette_color = sns.color_palette('bright')
+    fig=plt.figure(figsize=(15,5))
+    plt.pie(data, labels=keys, colors=palette_color, autopct='%.0f%%')
+    plt.title('Pieplot')
+    st.pyplot(fig)    
+
+    # Pieplot past_complaint 
+    st.write('###### past complaint')
+    data = df['past_complaint'].value_counts()
+    keys = df['past_complaint'].value_counts().index
+    palette_color = sns.color_palette('bright')
+    fig=plt.figure(figsize=(15,5))
+    plt.pie(data, labels=keys, colors=palette_color, autopct='%.0f%%')
+    plt.title('Pieplot')
+    st.pyplot(fig)        
+
+    # Pieplot feedback 
+    st.write('###### feedback ')
+    data = df['feedback'].value_counts()
+    keys = df['feedback'].value_counts().index
+    palette_color = sns.color_palette('bright')
+    fig=plt.figure(figsize=(15,5))
+    plt.pie(data, labels=keys, colors=palette_color, autopct='%.0f%%')
+    plt.title('Pieplot')
+    st.pyplot(fig)       
+
+if __name__ == '__main__':
+    run()

final_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff04c06f1136714341749382df40e154ee717071d1c89e92bbc2f4f81e8b481
+size 2950

prediction.py

@@ -0,0 +1,95 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import tensorflow 
+from tensorflow.keras.models import load_model
+import datetime
+import pickle
+
+
+
+
+# Load All Files
+
+with open('final_pipeline.pkl', 'rb') as file_1:
+  model_pipeline = pickle.load(file_1)
+
+  model_ann = load_model('churn_model.h5')
+
+
+
+# bikin fungsi  
+def run():
+
+  with st.form(key='churn_data'):
+
+      user_id = st.text_input('User ID', value='')
+      age  = st.number_input('Age', min_value=10, max_value=70, value=25, help='Customer Age')
+      gender  = st.selectbox('Gender', ('F','M'), index=1, help='M = Male  F= Female')
+      region_category = st.selectbox('Region category', ('Town','Village','City'), index=1)
+      membership_category = st.selectbox('Membership', ('No Membership','Basic Membership','Silver Membership', 'Gold Membership','Platinum Membership','Premium Membership'), index=1)
+      joining_date = st.date_input('Joining date',datetime.date(2019, 7, 6))
+      joined_through_referral = st.selectbox('Join using referral', ('Yes','No'), index=1)
+      preferred_offer_types = st.selectbox('preferred offer', ('Gift Vouchers/Coupons','Without Offers','Credit/Debit Card Offers'), index=1)
+      medium_of_operation = st.selectbox('device ', ('Desktop','Smartphone','Both'), index=1)
+      internet_option= st.selectbox('Internet', ('Mobile_data','Fiber_Optic','Wi-Fi'), index=1)
+      days_since_last_login = st.number_input('How many days since last login', min_value=0, max_value=30, value=5)
+      avg_time_spent = st.number_input('Avg time login', min_value=0, max_value=3000, value=5)
+      avg_transaction_value = st.number_input('Avg transaction value', min_value=0, max_value=100000, value=1000)
+      avg_frequency_login_days= st.number_input('Avg freq login', min_value=0, max_value=100, value=5)
+      points_in_wallet= st.number_input('Avg time login', min_value=0, max_value=3000, value=5)
+      used_special_discount = st.selectbox('Spesial discount', ('Yes','No'), index=1)
+      offer_application_preference = st.selectbox('app preference', ('Yes','No'), index=1)
+      past_complaint = st.selectbox('past complaint', ('Yes','No'), index=1)
+      complaint_status  = st.selectbox('Complain status', ('No Information Available','Not Applicable','Solved','Solved in Follow-up','Unsolved'), index=1)
+      feedback  = st.selectbox('Complain status', ('User Friendly Website','Too many ads','Reasonable Price','Quality Customer Care','Products always in Stock','Poor Website','Poor Product Quality','Poor Customer Service'), index=1) 
+      st.markdown('---')
+           
+      submitted = st.form_submit_button('Predict')
+
+  data_inf = {
+    'user_id':user_id,
+    'age': age,
+    'gender':gender,
+    'region_category': region_category,
+    'membership_category': membership_category,
+    'joining_date': joining_date,
+    'joined_through_referral':joined_through_referral,
+    'preferred_offer_types': preferred_offer_types,
+    'medium_of_operation': medium_of_operation,
+    'internet_option': internet_option,
+    'days_since_last_login': days_since_last_login,
+    'avg_time_spent': avg_time_spent,
+    'avg_transaction_value': avg_transaction_value,
+    'avg_frequency_login_days': avg_frequency_login_days,
+    'points_in_wallet': points_in_wallet,
+    'used_special_discount': used_special_discount,
+    'offer_application_preference': offer_application_preference,
+    'past_complaint': past_complaint,
+    'complaint_status': complaint_status,
+    'feedback': feedback
+  }
+
+  data_inf = pd.DataFrame([data_inf])
+  # Create Binning frequency login
+  bins = [-1, 10, 20, 30, 40, 50, 100]
+  labels =[1,2,3,4,6,7]
+  data_inf['binned_frequency_login'] = pd.cut(data_inf['avg_frequency_login_days'], bins,labels=labels).astype(float)
+  st.dataframe(data_inf)
+
+  if submitted:
+      
+      # transform data inference
+      data_inf_transform = model_pipeline.transform(data_inf)
+
+      # Predict using model ann
+      y_pred_inf = model_ann.predict(data_inf_transform)
+      y_pred_inf = np.where(y_pred_inf >= 0.5, 1, 0)
+      if y_pred_inf.any() == 1:
+            st.write('## The Customer probably will CHURN')
+      else:
+            st.write('## The Customer probably will NOT Churn')
+
+      
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,10 @@
+# daftar library yang dibutuhkan semua
+streamlit
+tensorflow
+pandas
+seaborn
+matplotlib
+numpy
+scikit-learn==1.2.1
+plotly
+datetime