In [1]:

    

import pandas as pd


    

In [2]:

    

import numpy as np


    

In [4]:

    

from pandas import DataFrame, Series


    

In [6]:

    

df = DataFrame([[1.4, np.nan], [7.1, -4.5], [np.nan, np.nan], [0.75, -1.3]],
index=['a', 'b', 'c', 'd'], columns=['one', 'two'])


    

In [7]:

    

df


    

    
Out[7]:






  

    

      

      
one
      
two
    
  
  

    

      
a
      
1.40
      
NaN
    
    

      
b
      
7.10
      
-4.5
    
    

      
c
      
NaN
      
NaN
    
    

      
d
      
0.75
      
-1.3
    
  

In [8]:

    

df.sum()


    

    
Out[8]:





one    9.25
two   -5.80
dtype: float64

In [9]:

    

df.sum(axis=1)


    

    
Out[9]:





a    1.40
b    2.60
c     NaN
d   -0.55
dtype: float64

In [10]:

    

df.mean(axis=1, skipna=False)


    

    
Out[10]:





a      NaN
b    1.300
c      NaN
d   -0.275
dtype: float64

In [11]:

    

df.idxmax()


    

    
Out[11]:





one    b
two    d
dtype: object

In [12]:

    

df.cumsum()


    

    
Out[12]:






  

    

      

      
one
      
two
    
  
  

    

      
a
      
1.40
      
NaN
    
    

      
b
      
8.50
      
-4.5
    
    

      
c
      
NaN
      
NaN
    
    

      
d
      
9.25
      
-5.8
    
  

In [13]:

    

df.describe()


    

    




/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/numpy/lib/function_base.py:3834: RuntimeWarning: Invalid value encountered in percentile
  RuntimeWarning)






    
Out[13]:






  

    

      

      
one
      
two
    
  
  

    

      
count
      
3.000000
      
2.000000
    
    

      
mean
      
3.083333
      
-2.900000
    
    

      
std
      
3.493685
      
2.262742
    
    

      
min
      
0.750000
      
-4.500000
    
    

      
25%
      
NaN
      
NaN
    
    

      
50%
      
NaN
      
NaN
    
    

      
75%
      
NaN
      
NaN
    
    

      
max
      
7.100000
      
-1.300000
    
  

In [17]:

    

obj = Series(['c', 'a', 'd', 'a', 'a', 'b', 'b', 'c', 'c'])


    

In [18]:

    

uniques = obj.unique()


    

In [19]:

    

uniques


    

    
Out[19]:





array(['c', 'a', 'd', 'b'], dtype=object)

In [20]:

    

obj.value_counts()


    

    
Out[20]:





a    3
c    3
b    2
d    1
dtype: int64

In [21]:

    

pd.value_counts(obj.values, sort=False)


    

    
Out[21]:





c    3
d    1
b    2
a    3
dtype: int64

In [22]:

    

mask = obj.isin(['b', 'c'])


    

In [23]:

    

mask


    

    
Out[23]:





0     True
1    False
2    False
3    False
4    False
5     True
6     True
7     True
8     True
dtype: bool

In [24]:

    

obj[mask]


    

    
Out[24]:





0    c
5    b
6    b
7    c
8    c
dtype: object

In [25]:

    

data = DataFrame({'Qu1': [1, 3, 4, 3, 4], 
                  'Qu2': [2, 3, 1, 2, 3],
                 'Qu3': [1, 5, 2, 4, 4]})


    

In [26]:

    

data


    

    
Out[26]:






  

    

      

      
Qu1
      
Qu2
      
Qu3
    
  
  

    

      
0
      
1
      
2
      
1
    
    

      
1
      
3
      
3
      
5
    
    

      
2
      
4
      
1
      
2
    
    

      
3
      
3
      
2
      
4
    
    

      
4
      
4
      
3
      
4
    
  

In [27]:

    

result = data.apply(pd.value_counts).fillna(0)


    

In [28]:

    

result


    

    
Out[28]:






  

    

      

      
Qu1
      
Qu2
      
Qu3
    
  
  

    

      
1
      
1.0
      
1.0
      
1.0
    
    

      
2
      
0.0
      
2.0
      
1.0
    
    

      
3
      
2.0
      
2.0
      
0.0
    
    

      
4
      
2.0
      
0.0
      
2.0
    
    

      
5
      
0.0
      
0.0
      
1.0
    
  

In [ ]: