import streamlit as st
import numpy as np
import pandas as pd
import joblib
model = joblib.load('Churn_pipe.sav')
gender= ("Men","Women")
SeniorCitizen= (0,1)
Partner= (1, 0)
Dependents= (0,1)
PhoneService=(1, 0)
MultipleLines= (1, 0)
InternetService= ('Fiber optic', 'DSL', 'No')
OnlineSecurity= (0,1)
OnlineBackup= (0,1)
DeviceProtection= (1, 0)
TechSupport= (0,1)
StreamingTV= (0,1)
StreamingMovies= (0,1)
y_n=("Yes","No")
Contract= ('Month-to-month', 'One year' ,'Two year')
PaperlessBilling=(1, 0)
PaymentMethod= ('Electronic check' ,'Bank transfer (automatic)' ,'Credit card (automatic)',
 'Mailed check')
st.title('Chuen prediction!')
st.write("""### we can predict churn!!""")
gender = st.selectbox("gender" ,gender)
SeniorCitizen= st.selectbox("SeniorCitizen",(0,1))
Partner= st.selectbox("Partner", y_n)
Dependents= st.selectbox("Dependents", y_n)
PhoneService=st.selectbox("PhoneService", y_n)
MultipleLines= st.selectbox("MultipleLines", y_n)
InternetService= st.selectbox("InternetService", InternetService)
OnlineSecurity= st.selectbox("OnlineSecurity", y_n)
OnlineBackup= st.selectbox("OnlineBackup", y_n)
DeviceProtection= st.selectbox("DeviceProtection", y_n)
TechSupport= st.selectbox("TechSupport", y_n)
StreamingTV= st.selectbox("StreamingTV", y_n)
StreamingMovies= st.selectbox("StreamingMovies", y_n)
PaperlessBilling=st.selectbox("PaperlessBilling", y_n)
Contract=st.selectbox("Contract", Contract)
PaymentMethod=st.selectbox("PaymentMethod",PaymentMethod)
tenure=st.slider("tenure", 0, 100)
MonthlyCharges=st.slider("MonthlyCharges", 0, 200)
TotalCharges=st.slider("TotalCharges", 0, 10000)
ok = st.button("Calculate Churn")
columns = ['gender', 'SeniorCitizen', 'Partner', 'Dependents', 'tenure',
       'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity',
       'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV',
       'StreamingMovies', 'Contract', 'PaperlessBilling', 'PaymentMethod',
       'MonthlyCharges', 'TotalCharges']
if ok:
    X_new = np.array([gender, SeniorCitizen, Partner, Dependents, tenure,
       PhoneService, MultipleLines, InternetService, OnlineSecurity,
       OnlineBackup, DeviceProtection, TechSupport, StreamingTV,
       StreamingMovies, Contract, PaperlessBilling, PaymentMethod,
       MonthlyCharges, TotalCharges])
    X_new_df = pd.DataFrame([X_new], columns = columns)
    yes_no= ['Partner','Dependents','PhoneService','MultipleLines','OnlineSecurity','OnlineBackup',
                      'DeviceProtection','TechSupport','StreamingTV','StreamingMovies','PaperlessBilling']
    for col in yes_no:
        X_new_df[col].replace({'Yes':1,'No':0},inplace=True)
    X_new_df['gender'].replace({'Female':1,'Male':0},inplace=True)
    churn = model.predict(X_new_df)
    if churn == 1:
        st.subheader('yes')
    else:
        st.subheader('no')