app.py

import pandas as pd
from transformers import pipeline
import streamlit as st
import datetime
from huggingface_hub import hf_hub_download
import joblib

REPO_ID = "AlbieCofie/predict-customer-churn"
FILENAME = "sklearn_model.joblib"

num_imputer = joblib.load(
    hf_hub_download(repo_id=REPO_ID, filename="numerical_imputer.joblib")
)

cat_imputer = joblib.load(
    hf_hub_download(repo_id=REPO_ID, filename="categorical_imputer.joblib")
)

encoder = joblib.load(
    hf_hub_download(repo_id=REPO_ID, filename="encoder.joblib")
)

scaler = joblib.load(
    hf_hub_download(repo_id=REPO_ID, filename="scaler.joblib")
)

model = joblib.load(
    hf_hub_download(repo_id=REPO_ID, filename="Final_model.joblib")
)

# Create a function that applies the ML pipeline and makes predictions
def predict(gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
                       InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
                       Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges):



    # Create a dataframe with the input data
    input_df = pd.DataFrame({
        'gender': [gender],
        'SeniorCitizen': [SeniorCitizen],
        'Partner': [Partner],
        'Dependents': [Dependents],
        'tenure': [tenure],
        'PhoneService': [PhoneService],
        'MultipleLines': [MultipleLines],
        'InternetService': [InternetService],
        'OnlineSecurity': [OnlineSecurity],
        'OnlineBackup': [OnlineBackup],
        'DeviceProtection': [DeviceProtection],
        'TechSupport': [TechSupport],
        'StreamingTV': [StreamingTV],
        'StreamingMovies': [StreamingMovies],
        'Contract': [Contract],
        'PaperlessBilling': [PaperlessBilling],
        'PaymentMethod': [PaymentMethod],
        'MonthlyCharges': [MonthlyCharges],
        'TotalCharges': [TotalCharges]
        })

# Selecting categorical and numerical columns separately
    cat_columns = [col for col in input_df.columns if input_df[col].dtype == 'object']
    num_columns = [col for col in input_df.columns if input_df[col].dtype != 'object']

    # Apply the imputers on the input data
    input_df_imputed_cat = cat_imputer.transform(input_df[cat_columns])
    input_df_imputed_num = num_imputer.transform(input_df[num_columns])

    # Encode the categorical columns
    input_encoded_df = pd.DataFrame(encoder.transform(input_df_imputed_cat).toarray(),
                                   columns=encoder.get_feature_names_out(cat_columns))

    # Scale the numerical columns
    input_df_scaled = scaler.transform(input_df_imputed_num)
    input_scaled_df = pd.DataFrame(input_df_scaled , columns = num_columns)


    #joining the cat encoded and num scaled
    final_df = pd.concat([input_encoded_df, input_scaled_df], axis=1)

    final_df = final_df.reindex(columns=['SeniorCitizen','tenure','MonthlyCharges','TotalCharges',
     'gender_Female','gender_Male','Partner_No','Partner_Yes','Dependents_No','Dependents_Yes','PhoneService_No',
     'PhoneService_Yes','MultipleLines_No','MultipleLines_Yes','InternetService_DSL','InternetService_Fiber optic',
     'InternetService_No','OnlineSecurity_No','OnlineSecurity_Yes','OnlineBackup_No','OnlineBackup_Yes','DeviceProtection_No',
     'DeviceProtection_Yes','TechSupport_No','TechSupport_Yes','StreamingTV_No','StreamingTV_Yes','StreamingMovies_No',
     'StreamingMovies_Yes','Contract_Month-to-month','Contract_One year','Contract_Two year','PaperlessBilling_No',
     'PaperlessBilling_Yes','PaymentMethod_Bank transfer (automatic)','PaymentMethod_Credit card (automatic)','PaymentMethod_Electronic check',
     'PaymentMethod_Mailed check'])

    # Make predictions using the model
    predictions = model.predict(final_df)

     # Make predictions using the model
     #predictions = model.predict(final_df)

     # Convert the numpy array to an integer
     #prediction_label = int(predictions.item())

    prediction_label = "Beware!!! This customer is likely to Churn" if predictions.item() == "Yes" else "This customer is Not likely churn"


    return prediction_label

     #return predictions    


if 'clicked' not in st.session_state:
    st.session_state.clicked = False

def click_button():
    st.session_state.clicked = True


st.title("CUSTOMER CHURN PREDICTION APP")

with st.form(key="customer-information"):
    st.markdown("This app predicts whether a customer will leave your company or not. Enter the details of the customer below to see the result")
    gender = st.radio('Select your gender', ('male', 'female'))
    SeniorCitizen = st.radio("Are you a Seniorcitizen; No=0 and Yes=1", ('0', '1'))
    Partner = st.radio('Do you have Partner', ('Yes', 'No'))
    Dependents = st.selectbox('Do you have any Dependents?', ('No', 'Yes'))
    tenure = st.number_input('Lenght of tenure (no. of months with Telco)', min_value=0, max_value=90, value=1, step=1)
    PhoneService = st.radio('Do you have PhoneService? ', ('No', 'Yes'))
    MultipleLines = st.radio('Do you have MultipleLines', ('No', 'Yes'))
    InternetService = st.radio('Do you have InternetService', ('DSL', 'Fiber optic', 'No'))
    OnlineSecurity = st.radio('Do you have OnlineSecurity?', ('No', 'Yes'))
    OnlineBackup = st.radio('Do you have OnlineBackup?', ('No', 'Yes'))
    DeviceProtection = st.radio('Do you have DeviceProtection?', ('No', 'Yes'))
    TechSupport = st.radio('Do you have TechSupport?', ('No', 'Yes'))
    StreamingTV = st.radio('Do you have StreamingTV?', ('No', 'Yes'))
    StreamingMovies = st.radio('Do you have StreamingMovies?', ('No', 'Yes'))
    Contract = st.selectbox('which Contract do you use?', ('Month-to-month', 'One year', 'Two year'))
    PaperlessBilling = st.radio('Do you prefer PaperlessBilling?', ('Yes', 'No'))
    PaymentMethod = st.selectbox('Which PaymentMethod do you prefer?', ('Electronic check', 'Mailed check', 'Bank transfer (automatic)',
                                        'Credit card (automatic)'))
    MonthlyCharges = st.number_input("Enter monthly charges (the range should between 0-120)")
    TotalCharges = st.number_input("Enter total charges (the range should between 0-10.000)")           
    st.form_submit_button('Predict', on_click=click_button)

    if st.session_state.clicked:
    # The message and nested widget will remain on the page
        list = [gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
            InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
            Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges]
        df = pd.DataFrame(list, columns=("{f}", list), index=False)
        st.dataframe(df)
        
        #predict(gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
                       #InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
                       #Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges)