10 Minute Panda Training

In [45]:

    

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


    

In [63]:

    

s = pd.Series([1,3,5,np.nan,6,8])
dates = pd.date_range('20130101',periods=6)
df = pd.DataFrame(np.random.randn(6,5),index=dates,columns=list('ABCDE'))


    

In [62]:

    

np.random.randn(6,4)


    

    
Out[62]:





array([[-0.72141978,  1.75647938, -0.84297956, -1.87490759],
       [ 0.61284124,  0.88152499,  0.23692212, -0.46196475],
       [ 0.49427992,  0.83530742, -1.06899914, -0.40358203],
       [ 1.26489497, -1.06422262, -1.55284967,  1.16017867],
       [-0.2598227 ,  0.86774058, -0.64080989,  0.75744095],
       [-0.72803805,  0.72472441,  0.81294184,  0.24446359]])

In [30]:

    

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' : 'foo' })


    

In [31]:

    

df2


    

    
Out[31]:






  

    

      

      
A
      
B
      
C
      
D
      
E
    
  
  

    

      
0
      
 1
      
2013-01-02 00:00:00
      
 1
      
 3
      
 foo
    
    

      
1
      
 1
      
2013-01-02 00:00:00
      
 1
      
 3
      
 foo
    
    

      
2
      
 1
      
2013-01-02 00:00:00
      
 1
      
 3
      
 foo
    
    

      
3
      
 1
      
2013-01-02 00:00:00
      
 1
      
 3
      
 foo
    
  

4 rows × 5 columns

In [32]:

    

#I guess this shows where the data types are.
df2.dtypes


    

    
Out[32]:





A           float64
B    datetime64[ns]
C           float32
D             int32
E            object
dtype: object

In [64]:

    

df.head()


    

    
Out[64]:






  

    

      

      
A
      
B
      
C
      
D
      
E
    
  
  

    

      
2013-01-01
      
 1.100527
      
-0.381699
      
-0.451535
      
 0.713584
      
-1.293972
    
    

      
2013-01-02
      
-0.391748
      
-1.480627
      
 0.590120
      
-0.640268
      
-0.440093
    
    

      
2013-01-03
      
 0.661144
      
 0.361374
      
-0.882714
      
 1.120732
      
 0.276473
    
    

      
2013-01-04
      
-1.130035
      
-0.168796
      
 0.072885
      
 0.875275
      
 0.575093
    
    

      
2013-01-05
      
 2.405335
      
-0.583955
      
-0.690658
      
-2.137181
      
-1.716164
    
  

5 rows × 5 columns

In [37]:

    

df.index


    

    
Out[37]:





<class 'pandas.tseries.index.DatetimeIndex'>
[2013-01-01 00:00:00, ..., 2013-01-06 00:00:00]
Length: 6, Freq: D, Timezone: None

In [41]:

    

df.values[0][0]


    

    
Out[41]:





0.26366085386647958

In [42]:

    

df.T


    

    
Out[42]:






  

    

      

      
2013-01-01 00:00:00
      
2013-01-02 00:00:00
      
2013-01-03 00:00:00
      
2013-01-04 00:00:00
      
2013-01-05 00:00:00
      
2013-01-06 00:00:00
    
  
  

    

      
A
      
 0.263661
      
-1.148435
      
 1.753792
      
 0.771710
      
-0.456610
      
-0.375286
    
    

      
B
      
 1.263971
      
-0.750341
      
-0.436259
      
 1.207909
      
 0.944913
      
-2.548341
    
    

      
C
      
-0.039726
      
-0.228849
      
 0.566032
      
 1.505498
      
 0.573583
      
 0.647772
    
    

      
D
      
 0.352130
      
 0.991504
      
 0.392104
      
-1.446948
      
-1.511025
      
 2.033515
    
  

4 rows × 6 columns

In [44]:

    

df.sort(columns='B', ascending=False)


    

    
Out[44]:






  

    

      

      
A
      
B
      
C
      
D
    
  
  

    

      
2013-01-01
      
 0.263661
      
 1.263971
      
-0.039726
      
 0.352130
    
    

      
2013-01-04
      
 0.771710
      
 1.207909
      
 1.505498
      
-1.446948
    
    

      
2013-01-05
      
-0.456610
      
 0.944913
      
 0.573583
      
-1.511025
    
    

      
2013-01-03
      
 1.753792
      
-0.436259
      
 0.566032
      
 0.392104
    
    

      
2013-01-02
      
-1.148435
      
-0.750341
      
-0.228849
      
 0.991504
    
    

      
2013-01-06
      
-0.375286
      
-2.548341
      
 0.647772
      
 2.033515
    
  

6 rows × 4 columns

In [48]:

    

df['A']


    

    
Out[48]:





2013-01-01    0.263661
2013-01-02   -1.148435
2013-01-03    1.753792
2013-01-04    0.771710
2013-01-05   -0.456610
2013-01-06   -0.375286
Freq: D, Name: A, dtype: float64

In [51]:

    

df.loc[:,['A','B']]


    

    
Out[51]:






  

    

      

      
A
      
B
    
  
  

    

      
2013-01-01
      
 0.263661
      
 1.263971
    
    

      
2013-01-02
      
-1.148435
      
-0.750341
    
    

      
2013-01-03
      
 1.753792
      
-0.436259
    
    

      
2013-01-04
      
 0.771710
      
 1.207909
    
    

      
2013-01-05
      
-0.456610
      
 0.944913
    
    

      
2013-01-06
      
-0.375286
      
-2.548341
    
  

6 rows × 2 columns

In [52]:

    

df.at[dates[0],'A']


    

    
Out[52]:





0.26366085386647958

In [53]:

    

df.iloc[3:5,0:2]


    

    
Out[53]:






  

    

      

      
A
      
B
    
  
  

    

      
2013-01-04
      
 0.77171
      
 1.207909
    
    

      
2013-01-05
      
-0.45661
      
 0.944913
    
  

2 rows × 2 columns

In [54]:

    




    

    
Out[54]:






  

    

      

      
A
      
B
      
C
      
D
    
  
  

    

      
2013-01-01
      
 0.263661
      
 1.263971
      
-0.039726
      
 0.352130
    
    

      
2013-01-02
      
-1.148435
      
-0.750341
      
-0.228849
      
 0.991504
    
    

      
2013-01-03
      
 1.753792
      
-0.436259
      
 0.566032
      
 0.392104
    
    

      
2013-01-04
      
 0.771710
      
 1.207909
      
 1.505498
      
-1.446948
    
    

      
2013-01-05
      
-0.456610
      
 0.944913
      
 0.573583
      
-1.511025
    
    

      
2013-01-06
      
-0.375286
      
-2.548341
      
 0.647772
      
 2.033515
    
  

6 rows × 4 columns

In [57]:

    

df.iloc[1:3,:]


    

    
Out[57]:






  

    

      

      
A
      
B
      
C
      
D
    
  
  

    

      
2013-01-02
      
-1.148435
      
-0.750341
      
-0.228849
      
 0.991504
    
    

      
2013-01-03
      
 1.753792
      
-0.436259
      
 0.566032
      
 0.392104
    
  

2 rows × 4 columns

In [58]:

    

#most efficient
df.iat[1,1]


    

    
Out[58]:





-0.75034058387714442

In [ ]: