Working with Text Data

import pandas as pd
import numpy as np

s = pd.Series(['Tom', 'William Rick', 'John', 'Alber@t', np.nan, '1234','SteveSmith'])

print s
print "                                       "
print s.str.lower()
print "                                       "
print s.str.upper()
print "                                       "
print s.str.len()
print "                                       "
print "Adding String "
print s.str.cat(sep='_')



print "                                       "
print "                                       "
print "Contains match "

s = pd.Series(['Tom ', ' William Rick', 'John', 'Alber@t'])
print s.str.contains(' ')

print "Replace "
print "                                       "
print "                                       "


print s.str.replace('@','$')


s = pd.Series(['Tom ', ' William Rick', 'John', 'Alber@t'])

print "                                       "
print "                                       "
print ("The number of 'm's in each string:")
print s.str.count('R')
print s.str.contains('r')
print "                                       "
print "                                       "
print ("Starts with:")
print s.str.startswith('J')
print ("Starts with:")
print s.str.endswith('t')


s = pd.Series(['Tom ', ' William Rick', 'John', 'Alber@t'])

print s.str.find('e')

# "-1" indicates that there no such pattern available in the element.


s = pd.Series(['Tom ', ' William Rick', 'John', 'Alber@t'])

print s.str.findall('e')


#Null list([ ]) indicates that there is no such pattern available in the element.

s = pd.Series(['Tom', 'William Rick', 'John', 'Alber@t'])
print s.str.swapcase()


print s.str.islower()
# to validate full string in lower 

print s.str.isupper()
# to validate full string in upper

print s.str.isnumeric()
# to validate full string in Numeric