data_cleaning.py

# -*- coding: utf-8 -*-
"""
Created on Wed Oct  4 19:27:12 2023

@author: anuja
"""


import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import seaborn as sns # For creating plots
import matplotlib.ticker as mtick # For specifying the axes tick format 
import matplotlib.pyplot as plt

sns.set(style = 'white')

telecom_cust = pd.read_csv('WA_Fn-UseC_-Telco-Customer-Churn.csv')

telecom_cust.head()

telecom_cust.columns.values
# Converting Total Charges to a numerical data type.
telecom_cust.TotalCharges = pd.to_numeric(telecom_cust.TotalCharges, errors='coerce')
telecom_cust.isnull().sum()
#Removing missing values 
telecom_cust.dropna(inplace = True)
#Remove customer IDs from the data set
df2 = telecom_cust.iloc[:,1:]
#Convertin the predictor variable in a binary numeric variable
df2['Churn'].replace(to_replace='Yes', value=1, inplace=True)
df2['Churn'].replace(to_replace='No',  value=0, inplace=True)

#Let's convert all the categorical variables into dummy variables
df_dummies = pd.get_dummies(df2)
df_dummies.head()
#Get Correlation of "Churn" with other variables:
plt.figure(figsize=(15,8))
df_dummies.corr()['Churn'].sort_values(ascending = False).plot(kind='bar')