6.32 - Pandas operations

In [1]:

    

import numpy as np
import pandas as pd


    

In [2]:

    

df = pd.DataFrame({'col1':[1,2,3,4],'col2':[444,555,666,444],'col3':['abc','def','ghi','xyz']})
df.head()


    

    
Out[2]:






  

    

      

      
col1
      
col2
      
col3
    
  
  

    

      
0
      
1
      
444
      
abc
    
    

      
1
      
2
      
555
      
def
    
    

      
2
      
3
      
666
      
ghi
    
    

      
3
      
4
      
444
      
xyz
    
  

In [4]:

    

df['col2'].unique()


    

    
Out[4]:





array([444, 555, 666])

In [6]:

    

len(df['col2'].unique()) # Checking the number of unique values


    

    
Out[6]:





3

In [8]:

    

df['col2'].nunique() # .nunique() is the same as len()


    

    
Out[8]:





3

In [9]:

    

df['col2'].value_counts()


    

    
Out[9]:





444    2
555    1
666    1
Name: col2, dtype: int64

In [11]:

    

df[df['col1']>2]


    

    
Out[11]:






  

    

      

      
col1
      
col2
      
col3
    
  
  

    

      
2
      
3
      
666
      
ghi
    
    

      
3
      
4
      
444
      
xyz
    
  

In [12]:

    

df[(df['col1']>2) & (df['col2']==444)]


    

    
Out[12]:






  

    

      

      
col1
      
col2
      
col3
    
  
  

    

      
3
      
4
      
444
      
xyz
    
  

In [13]:

    

def times2(x):
    return x*2


    

In [14]:

    

df['col1'].apply(times2) # wow much cool


    

    
Out[14]:





0    2
1    4
2    6
3    8
Name: col1, dtype: int64

In [15]:

    

df['col3'].apply(len)


    

    
Out[15]:





0    3
1    3
2    3
3    3
Name: col3, dtype: int64

In [17]:

    

df['col2'].apply(lambda x: x*2) # coolwow


    

    
Out[17]:





0     888
1    1110
2    1332
3     888
Name: col2, dtype: int64

In [20]:

    

df.columns


    

    
Out[20]:





Index([u'col1', u'col2', u'col3'], dtype='object')

In [22]:

    

df.index


    

    
Out[22]:





RangeIndex(start=0, stop=4, step=1)

In [24]:

    

df.sort_values('col2')


    

    
Out[24]:






  

    

      

      
col1
      
col2
      
col3
    
  
  

    

      
0
      
1
      
444
      
abc
    
    

      
3
      
4
      
444
      
xyz
    
    

      
1
      
2
      
555
      
def
    
    

      
2
      
3
      
666
      
ghi
    
  

In [25]:

    

df.isnull()


    

    
Out[25]:






  

    

      

      
col1
      
col2
      
col3
    
  
  

    

      
0
      
False
      
False
      
False
    
    

      
1
      
False
      
False
      
False
    
    

      
2
      
False
      
False
      
False
    
    

      
3
      
False
      
False
      
False
    
  

In [28]:

    

data = {'A':['foo','foo','foo','bar','bar','bar'],
     'B':['one','one','two','two','one','one'],
       'C':['x','y','x','y','x','y'],
       'D':[1,3,2,5,4,1]}

df = pd.DataFrame(data)
df


    

    
Out[28]:






  

    

      

      
A
      
B
      
C
      
D
    
  
  

    

      
0
      
foo
      
one
      
x
      
1
    
    

      
1
      
foo
      
one
      
y
      
3
    
    

      
2
      
foo
      
two
      
x
      
2
    
    

      
3
      
bar
      
two
      
y
      
5
    
    

      
4
      
bar
      
one
      
x
      
4
    
    

      
5
      
bar
      
one
      
y
      
1
    
  

In [29]:

    

df.pivot_table(values='D',index=['A','B'],columns='C')


    

    
Out[29]:






  

    

      

      
C
      
x
      
y
    
    

      
A
      
B
      

      

    
  
  

    

      
bar
      
one
      
4.0
      
1.0
    
    

      
two
      
NaN
      
5.0
    
    

      
foo
      
one
      
1.0
      
3.0
    
    

      
two
      
2.0
      
NaN
    
  

In [ ]: