#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().run_line_magic('matplotlib', 'inline')
get_ipython().run_line_magic('config', "InlineBackend.figure_format = 'retina'")
from matplotlib import pyplot as plt

import pandas as pd


# In[2]:


churn_data = pd.read_csv('https://raw.githubusercontent.com/'
                         'treselle-systems/customer_churn_analysis/'
                         'master/WA_Fn-UseC_-Telco-Customer-Churn.csv')
churn_data.head()


# In[3]:


churn_data = churn_data.set_index('customerID')
churn_data = churn_data.drop(['TotalCharges'], axis=1)

# The dataset is naturally hierarchical: some columns only apply to some users. Ex, if you don't have internet 
# then the column OnlineBackup isn't applicable, as it's value is "No internet service". We 
# are going to map this back to No. We will treat the hierachical nature by stratifying on the 
# different services a user may have. 
churn_data = churn_data.applymap(lambda x: "No" if str(x).startswith("No ") else x)
churn_data['Churn'] = (churn_data['Churn'] == "Yes")
strata_cols = ['InternetService', 'StreamingMovies', 'StreamingTV', 'PhoneService']
print(churn_data.columns)


# In[4]:


from lifelines import CoxPHFitter

cph = CoxPHFitter().fit(churn_data, 'tenure', 'Churn', 
                        formula="gender + SeniorCitizen + Partner + Dependents  + MultipleLines + OnlineSecurity + OnlineBackup + DeviceProtection + TechSupport + Contract + PaperlessBilling + PaymentMethod + MonthlyCharges",
                        strata=strata_cols)


# In[5]:


cph


# In[6]:


cph.print_summary()


# In[7]:


ax = plt.subplots(figsize=(8, 6))
cph.plot(ax=ax[1])


# In[8]:


cph.plot_partial_effects_on_outcome('Contract', values=["Month-to-month", "One year", "Two year"], plot_baseline=False);


# In[ ]:





# In[ ]: