notebook.community

Edit and run



In [1]:

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



In [3]:

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









    Out[3]:





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



In [4]:

    
dates = pd.date_range('20130101',periods=6)



In [5]:

    
dates









    Out[5]:





DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')



In [6]:

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



In [11]:

    
df2 = pd.DataFrame({'A': 1.,
                    'B': pd.Timestamp('20130102'),
                    'C': pd.Series(1,index = list((range(4)))),
                    'D': np.array([3]*4),
                    'E': pd.Categorical(["surya","teja","bala","dileep"]),
                    'F': 'Foo'})
df2



In [21]:

    
df2.tail(2)



In [26]:

    
df2.dtypes









    Out[26]:





A           float64
B    datetime64[ns]
C             int64
D             int64
E          category
F            object
dtype: object



In [27]:

    
df2.









    



  File "<ipython-input-27-e8d0e54abc86>", line 1
    df2.<TAB>
        ^
SyntaxError: invalid syntax



In [29]:

    
df.index









    Out[29]:





DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')



In [31]:

    
df2.columns









    Out[31]:





Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')



In [32]:

    
df2.values









    Out[32]:





array([[1.0, Timestamp('2013-01-02 00:00:00'), 1, 3, 'surya', 'Foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1, 3, 'teja', 'Foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1, 3, 'bala', 'Foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1, 3, 'dileep', 'Foo']], dtype=object)



In [34]:

    
df.describe()
df2.describe()



In [36]:

    
#Transposing the data
print(df)
print(df.T)









    



                   A         B         C         D
2013-01-01 -1.164873  0.008331  0.801343 -0.217401
2013-01-02 -1.567579 -1.793393  0.753424 -0.289366
2013-01-03 -0.733508  0.829952  2.265642  2.105826
2013-01-04  0.980079 -0.107410  1.225999 -0.554620
2013-01-05 -0.992219  1.327886  0.648874  0.227911
2013-01-06  0.529250 -0.085388  2.327908 -1.007254
   2013-01-01  2013-01-02  2013-01-03  2013-01-04  2013-01-05  2013-01-06
A   -1.164873   -1.567579   -0.733508    0.980079   -0.992219    0.529250
B    0.008331   -1.793393    0.829952   -0.107410    1.327886   -0.085388
C    0.801343    0.753424    2.265642    1.225999    0.648874    2.327908
D   -0.217401   -0.289366    2.105826   -0.554620    0.227911   -1.007254



In [42]:

    
print(df)
df.sort_index(axis=1,ascending=True)









    



                   A         B         C         D
2013-01-01 -1.164873  0.008331  0.801343 -0.217401
2013-01-02 -1.567579 -1.793393  0.753424 -0.289366
2013-01-03 -0.733508  0.829952  2.265642  2.105826
2013-01-04  0.980079 -0.107410  1.225999 -0.554620
2013-01-05 -0.992219  1.327886  0.648874  0.227911
2013-01-06  0.529250 -0.085388  2.327908 -1.007254






    Out[42]:






  
    
      
      A
      B
      C
      D
    
  
  
    
      2013-01-01
      -1.164873
      0.008331
      0.801343
      -0.217401
    
    
      2013-01-02
      -1.567579
      -1.793393
      0.753424
      -0.289366
    
    
      2013-01-03
      -0.733508
      0.829952
      2.265642
      2.105826
    
    
      2013-01-04
      0.980079
      -0.107410
      1.225999
      -0.554620
    
    
      2013-01-05
      -0.992219
      1.327886
      0.648874
      0.227911
    
    
      2013-01-06
      0.529250
      -0.085388
      2.327908
      -1.007254



In [43]:

    
df.sort_values(by='B')



In [44]:

    
df.A









    Out[44]:





2013-01-01   -1.164873
2013-01-02   -1.567579
2013-01-03   -0.733508
2013-01-04    0.980079
2013-01-05   -0.992219
2013-01-06    0.529250
Freq: D, Name: A, dtype: float64



In [50]:

    
df[0:3]

	A	B	C	D
2013-01-01	-1.164873	0.008331	0.801343	-0.217401
2013-01-02	-1.567579	-1.793393	0.753424	-0.289366
2013-01-03	-0.733508	0.829952	2.265642	2.105826
2013-01-04	0.980079	-0.107410	1.225999	-0.554620
2013-01-05	-0.992219	1.327886	0.648874	0.227911
2013-01-06	0.529250	-0.085388	2.327908	-1.007254

	A	B	C	D	E	F
0	1.0	2013-01-02	1	3	surya	Foo
1	1.0	2013-01-02	1	3	teja	Foo
2	1.0	2013-01-02	1	3	bala	Foo
3	1.0	2013-01-02	1	3	dileep	Foo

	A	C	D
count	4.0	4.0	4.0
mean	1.0	1.0	3.0
std	0.0	0.0	0.0
min	1.0	1.0	3.0
25%	1.0	1.0	3.0
50%	1.0	1.0	3.0
75%	1.0	1.0	3.0
max	1.0	1.0	3.0