notebook.community



In [1]:

    
import pandas as pd
import numpy as np

pd.__version__, np.__version__









    Out[1]:





('0.24.2', '1.16.3')



In [2]:

    
df = pd.DataFrame({
    'name': ['alice smith','bob jones','charlie joneson','daisy white'],
    'age': [25,20,30,35]
})



In [3]:

    
df









    Out[3]:







  
    
      
      name
      age
    
  
  
    
      0
      alice smith
      25
    
    
      1
      bob jones
      20
    
    
      2
      charlie joneson
      30
    
    
      3
      daisy white
      35

select rows by partial string



In [4]:

    
df[df['name'].str.contains('jones',regex=False)]









    Out[4]:







  
    
      
      name
      age
    
  
  
    
      1
      bob jones
      20
    
    
      2
      charlie joneson
      30

select rows by regular expression



In [5]:

    
df[df['name'].str.contains('^b|da')]









    Out[5]:







  
    
      
      name
      age
    
  
  
    
      1
      bob jones
      20
    
    
      3
      daisy white
      35

concatenate string columns



In [6]:

    
df = pd.DataFrame({
    'first_name': ['alice','bob','charlie','daisy'],
    'last_name':['smith','jones','joneson','white'],
    'age': [25,20,30,35]
})
df









    Out[6]:







  
    
      
      first_name
      last_name
      age
    
  
  
    
      0
      alice
      smith
      25
    
    
      1
      bob
      jones
      20
    
    
      2
      charlie
      joneson
      30
    
    
      3
      daisy
      white
      35



In [7]:

    
df['full_name'] = df['first_name'] + df['last_name']
df









    Out[7]:







  
    
      
      first_name
      last_name
      age
      full_name
    
  
  
    
      0
      alice
      smith
      25
      alicesmith
    
    
      1
      bob
      jones
      20
      bobjones
    
    
      2
      charlie
      joneson
      30
      charliejoneson
    
    
      3
      daisy
      white
      35
      daisywhite



In [8]:

    
df['full_name'] = df['first_name'] + ' ' + df['last_name']
df









    Out[8]:







  
    
      
      first_name
      last_name
      age
      full_name
    
  
  
    
      0
      alice
      smith
      25
      alice smith
    
    
      1
      bob
      jones
      20
      bob jones
    
    
      2
      charlie
      joneson
      30
      charlie joneson
    
    
      3
      daisy
      white
      35
      daisy white

split string column



In [9]:

    
df = pd.DataFrame({
    'name': ['alice smith','bob jones','charlie joneson','daisy white'],
    'age': [25,20,30,35]
})
df









    Out[9]:







  
    
      
      name
      age
    
  
  
    
      0
      alice smith
      25
    
    
      1
      bob jones
      20
    
    
      2
      charlie joneson
      30
    
    
      3
      daisy white
      35



In [10]:

    
def split_name(name):
    first_name, last_name = name.split(' ')
    
    return pd.Series({
        'first_name': first_name,
        'last_name': last_name
    })

df_new = df['name'].apply(split_name)

df_final = pd.concat([df,df_new],axis=1)
df_final









    Out[10]:







  
    
      
      name
      age
      first_name
      last_name
    
  
  
    
      0
      alice smith
      25
      alice
      smith
    
    
      1
      bob jones
      20
      bob
      jones
    
    
      2
      charlie joneson
      30
      charlie
      joneson
    
    
      3
      daisy white
      35
      daisy
      white

simple series



In [11]:

    
s = pd.Series(['foo','bar','baz'])



In [12]:

    
s.str.capitalize()









    Out[12]:





0    Foo
1    Bar
2    Baz
dtype: object

	first_name	last_name	age	full_name
0	alice	smith	25	alicesmith
1	bob	jones	20	bobjones
2	charlie	joneson	30	charliejoneson
3	daisy	white	35	daisywhite

	first_name	last_name	age	full_name
0	alice	smith	25	alice smith
1	bob	jones	20	bob jones
2	charlie	joneson	30	charlie joneson
3	daisy	white	35	daisy white