Upload Files

app.py

@@ -0,0 +1,27 @@
+# Import Library
+import streamlit as st
+
+# Import the created Streamlit Page
+# import eda
+import prediction
+
+# Navigation button
+navigasi = st.sidebar.selectbox(label='Select Page:', options=['Home Page', 'Prediction']) # 'Exploratory Data Analysis', 
+
+# Looping for navigation
+if navigasi == 'Home Page':
+    st.markdown("<h1 style='text-align: center;'>Customer Churn Prediction</h1>", unsafe_allow_html=True) 
+    st.image("https://miro.medium.com/v2/resize:fit:1358/0*dzmm3qresODlScte")
+    st.caption("<p style='text-align: center;'>Source : Medium.com</p>", unsafe_allow_html=True)
+    st.write('')
+    st.write('**Author    : Salsa Sabitha Hurriyah**')
+    st.write('**Classification Model for Predicting Customer Churn**') 
+    st.caption('Please select another menu in the Select Box on the left of your screen to start!')
+
+# # Displays the EDA page
+# elif navigasi == 'Exploratory Data Analysis':
+#     eda.run()
+
+# Displays the Predict page
+elif navigasi == 'Prediction':
+    prediction.run()

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985651bcb21c2658e75a8cf804a01f3d2c4073e5cb5f71e5846ac23eb3218a2d
+size 4212727

prediction.py

@@ -0,0 +1,65 @@
+# import library
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+
+# Load Model
+with open('model.pkl', 'rb') as file:
+    model = pickle.load(file)
+
+# Function to run streamlit model predictor
+def run():
+
+   # Set Title
+    st.title("Customer Churn Prediction")
+    st.markdown('---')
+
+    # Create a Form for Data Inference
+    st.markdown('## Input Data')
+    with st.form('my_form'):
+        RowNumber = st.number_input('Row Number', min_value=10000, max_value=200000)
+        CustomerId = st.number_input('Customer ID', min_value=100000, max_value=20000000)
+        Surname = st.text_input('Surname or Last Name', '')
+        CreditScore = st.number_input('Credit Score', min_value=350, max_value=850)
+        Geography = st.selectbox('Select Geography', ['Spain', 'Germany', 'France'])
+        Gender = st.selectbox('Select gender', ['Male', 'Female'])
+        Age = st.number_input('Age', min_value=18, max_value=95)
+        Tenure  = st.number_input('Tenure', min_value=0, max_value=11)
+        Balance = st.number_input('Balance', min_value=0, max_value=300000)
+        NumOfProducts = st.selectbox('Number of Products', (1,2,3,4))
+        HasCrCard = st.selectbox('Has Credit Card or not? 0 = No, Yes = 1', (0,1))
+        IsActiveMember = st.selectbox('Is Active Member or not? 0 = No, Yes = 1', (0,1))
+        EstimatedSalary = st.number_input('Estimated Salary', min_value=12, max_value=300000)
+
+        # Create a button to make predictions
+        submitted = st.form_submit_button("Predict")
+
+    # Dataframe
+    data = {'RowNumber': RowNumber,
+            'CustomerId': CustomerId,
+            'Surname': Surname,
+            'CreditScore': CreditScore,
+            'Geography': Geography,
+            'Gender': Gender, 
+            'Age': Age,
+            'Tenure': Tenure, 
+            'Balance': Balance,
+            'NumOfProducts': NumOfProducts,
+            'HasCrCard': HasCrCard,
+            'IsActiveMember': IsActiveMember,
+            'EstimatedSalary': EstimatedSalary
+            }
+
+    df = pd.DataFrame([data])
+    st.dataframe(df)
+
+    if submitted:        
+        y_pred_inf = model.predict(df)
+        if y_pred_inf[0] == 0:
+            st.subheader('~ This Customer is Predicted Not to Churn ~')
+        else:
+            st.write('~ This Customer is Predicted to Churn ~')
+
+if __name__== '__main__':
+    run()

requirements.txt

@@ -0,0 +1,5 @@
+seaborn
+pandas
+matplotlib
+plotly
+scikit-learn==1.2.2