In [3]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt


    

In [5]:

    

s = pd.Series([1,3,5,np.nan,6,8])
print(s)


    

    




0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64

In [19]:

    

# DataFrame
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))
df


    

    
Out[19]:






  

    

      

      
A
      
B
      
C
      
D
    
  
  

    

      
2013-01-01
      
-0.283966
      
0.047616
      
-1.183938
      
0.313243
    
    

      
2013-01-02
      
1.417953
      
-0.048616
      
1.178293
      
-0.107940
    
    

      
2013-01-03
      
-0.793594
      
0.055211
      
0.187253
      
-0.242368
    
    

      
2013-01-04
      
1.147936
      
-0.454217
      
0.591398
      
1.520469
    
    

      
2013-01-05
      
-0.590837
      
-2.491837
      
0.859189
      
0.147979
    
    

      
2013-01-06
      
-0.262742
      
3.061295
      
1.211843
      
-0.625622
    
  

In [17]:

    

df2 = pd.DataFrame({'A': 1., 'B': pd.Timestamp('20130102'), 'C': pd.Series(1, index=list(range(4)), dtype='float32'), 
                   'D': np.array([3] * 4, dtype='int32'), 'E': pd.Categorical(['test', 'train', 'test', 'train']), 
                   'F': 'foo'})
df2.head()
df2.T


    

    
Out[17]:






  

    

      

      
0
      
1
      
2
      
3
    
  
  

    

      
A
      
1
      
1
      
1
      
1
    
    

      
B
      
2013-01-02 00:00:00
      
2013-01-02 00:00:00
      
2013-01-02 00:00:00
      
2013-01-02 00:00:00
    
    

      
C
      
1
      
1
      
1
      
1
    
    

      
D
      
3
      
3
      
3
      
3
    
    

      
E
      
test
      
train
      
test
      
train
    
    

      
F
      
foo
      
foo
      
foo
      
foo
    
  

In [27]:

    

df['A']
df[0:3]
df.iloc[1, 2]
df.iat[1,2]


    

    
Out[27]:





1.1782931634104032

In [29]:

    

df.A > 0


    

    
Out[29]:





2013-01-01    False
2013-01-02     True
2013-01-03    False
2013-01-04     True
2013-01-05    False
2013-01-06    False
Freq: D, Name: A, dtype: bool

In [31]:

    

df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
df1.loc[dates[0]:dates[1], 'E'] = 1
df1


    

    
Out[31]:






  

    

      

      
A
      
B
      
C
      
D
      
E
    
  
  

    

      
2013-01-01
      
-0.283966
      
0.047616
      
-1.183938
      
0.313243
      
1.0
    
    

      
2013-01-02
      
1.417953
      
-0.048616
      
1.178293
      
-0.107940
      
1.0
    
    

      
2013-01-03
      
-0.793594
      
0.055211
      
0.187253
      
-0.242368
      
NaN
    
    

      
2013-01-04
      
1.147936
      
-0.454217
      
0.591398
      
1.520469
      
NaN
    
  

In [35]:

    

df1.dropna(how='any')
df1.fillna(value=5)
pd.isnull(df1)


    

    
Out[35]:






  

    

      

      
A
      
B
      
C
      
D
      
E
    
  
  

    

      
2013-01-01
      
False
      
False
      
False
      
False
      
False
    
    

      
2013-01-02
      
False
      
False
      
False
      
False
      
False
    
    

      
2013-01-03
      
False
      
False
      
False
      
False
      
True
    
    

      
2013-01-04
      
False
      
False
      
False
      
False
      
True