testapp.py

# Import libraries
import streamlit as st
import pandas as pd
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import seaborn as sns
import joblib

# Load the model from disk
model = joblib.load(r"./notebook/model.sav")

# Import python scripts
from preprocessing import preprocess

def plot_histogram(data, column, color):
    plt.figure(figsize=(8, 4))
    plt.hist(data[column], bins=20, color=color, edgecolor='black')
    plt.title(f'Distribution of {column}')
    plt.xlabel(column)
    plt.ylabel('Frequency')
    return plt

def plot_pie_chart(data, column):
    plt.figure(figsize=(8, 4))
    data[column].value_counts().plot(kind='pie', autopct='%1.1f%%')
    plt.title(f'Distribution of {column}')
    plt.ylabel('')
    return plt

def plot_correlation_heatmap(data):
    plt.figure(figsize=(10, 6))
    sns.heatmap(data.corr(), annot=True, fmt=".2f")
    plt.title('Correlation Heatmap')
    return plt

def main():
    # Setting Application title and description
    st.title('Telco Customer Churn Prediction App')
    st.markdown("""
     :dart:  This Streamlit app is made to predict customer churn in a fictional telecommunication use case.
    The application is functional for both online prediction and batch data prediction. \n
    """)
    image = Image.open('App.jpg')
    st.sidebar.image(image)

    # Application sidebar
    add_selectbox = st.sidebar.selectbox(
        "How would you like to predict?", ("Online", "Batch"))

    if add_selectbox == "Online":
        st.info("Input data below")
        #Based on our optimal features selection
        st.subheader("Demographic data")
        seniorcitizen = st.selectbox('Senior Citizen:', ('Yes', 'No'))
        dependents = st.selectbox('Dependent:', ('Yes', 'No'))


        st.subheader("Payment data")
        tenure = st.slider('Number of months the customer has stayed with the company', min_value=0, max_value=72, value=0)
        contract = st.selectbox('Contract', ('Month-to-month', 'One year', 'Two year'))
        paperlessbilling = st.selectbox('Paperless Billing', ('Yes', 'No'))
        PaymentMethod = st.selectbox('PaymentMethod',('Electronic check', 'Mailed check', 'Bank transfer (automatic)','Credit card (automatic)'))
        monthlycharges = st.number_input('The amount charged to the customer monthly', min_value=0, max_value=150, value=0)
        totalcharges = st.number_input('The total amount charged to the customer',min_value=0, max_value=10000, value=0)

        st.subheader("Services signed up for")
        mutliplelines = st.selectbox("Does the customer have multiple lines",('Yes','No','No phone service'))
        phoneservice = st.selectbox('Phone Service:', ('Yes', 'No'))
        internetservice = st.selectbox("Does the customer have internet service", ('DSL', 'Fiber optic', 'No'))
        onlinesecurity = st.selectbox("Does the customer have online security",('Yes','No','No internet service'))
        onlinebackup = st.selectbox("Does the customer have online backup",('Yes','No','No internet service'))
        techsupport = st.selectbox("Does the customer have technology support", ('Yes','No','No internet service'))
        streamingtv = st.selectbox("Does the customer stream TV", ('Yes','No','No internet service'))
        streamingmovies = st.selectbox("Does the customer stream movies", ('Yes','No','No internet service'))

        data = {
                'SeniorCitizen': seniorcitizen,
                'Dependents': dependents,
                'tenure':tenure,
                'PhoneService': phoneservice,
                'MultipleLines': mutliplelines,
                'InternetService': internetservice,
                'OnlineSecurity': onlinesecurity,
                'OnlineBackup': onlinebackup,
                'TechSupport': techsupport,
                'StreamingTV': streamingtv,
                'StreamingMovies': streamingmovies,
                'Contract': contract,
                'PaperlessBilling': paperlessbilling,
                'PaymentMethod':PaymentMethod, 
                'MonthlyCharges': monthlycharges, 
                'TotalCharges': totalcharges
                }
        features_df = pd.DataFrame.from_dict([data])
        st.markdown("<h3></h3>", unsafe_allow_html=True)
        st.write('Overview of input is shown below')
        st.markdown("<h3></h3>", unsafe_allow_html=True)
        st.dataframe(features_df)


        #Preprocess inputs
        preprocess_df = preprocess(features_df, 'Online')

        prediction = model.predict(preprocess_df)

        if st.button('Predict'):
            if prediction == 1:
                st.warning('Yes, the customer will terminate the service.')
            else:
                st.success('No, the customer is happy with Telco Services.')

    else:
        # Batch prediction
        uploaded_file = st.file_uploader("Choose a file")
        if uploaded_file is not None:
            data = pd.read_csv(uploaded_file)
            st.write(data.head())

            # Optional: Plotting the pie chart for Contract
            if st.checkbox('Show Distribution of Contract Types'):
                st.pyplot(plot_pie_chart(data, 'Contract'))

            # Optional: Plotting correlation heatmap
            if st.checkbox('Show Correlation Heatmap'):
                st.pyplot(plot_correlation_heatmap(data))

            #Preprocess inputs
            preprocess_df = preprocess(data, "Batch")
            if st.button('Predict'):
                #Get batch prediction
                prediction = model.predict(preprocess_df)
                prediction_df = pd.DataFrame(prediction, columns=["Predictions"])
                prediction_df = prediction_df.replace({1:'Yes, the customer will terminate the service.', 
                                                    0:'No, the customer is happy with Telco Services.'})

                st.markdown("<h3></h3>", unsafe_allow_html=True)
                st.subheader('Prediction')
                st.write(prediction_df)
            
if __name__ == '__main__':
        main()