Skip to content

Latest commit

 

History

History
321 lines (238 loc) · 4.56 KB

DataFrame2-pandas.asciidoc

File metadata and controls

321 lines (238 loc) · 4.56 KB
Raw

*In[1]:*

import numpy as np
import pandas as pd

*In[4]:*

from numpy.random import randn
df=pd.DataFrame(randn(5,4),['A','B','C','D','E'],['W','X','Y','Z'])

*In[5]:*

df

*Out[5]:*

[cols=",,,,",options="header",]
|===
| |W |X |Y |Z
|A |-0.469724 |0.443672 |-1.009412 |0.118840
|B |0.152000 |-1.015101 |0.292788 |-0.179682
|C |-0.650724 |0.098453 |-2.513389 |-0.636284
|D |2.248024 |0.481968 |-0.944033 |-0.107866
|E |-0.590276 |0.964199 |-0.248336 |0.777561
|===

*In[6]:*

df.reset_index()

*Out[6]:*

[cols=",,,,,",options="header",]
|===
| |index |W |X |Y |Z
|0 |A |-0.469724 |0.443672 |-1.009412 |0.118840
|1 |B |0.152000 |-1.015101 |0.292788 |-0.179682
|2 |C |-0.650724 |0.098453 |-2.513389 |-0.636284
|3 |D |2.248024 |0.481968 |-0.944033 |-0.107866
|4 |E |-0.590276 |0.964199 |-0.248336 |0.777561
|===

*In[7]:*

df

*Out[7]:*

[cols=",,,,",options="header",]
|===
| |W |X |Y |Z
|A |-0.469724 |0.443672 |-1.009412 |0.118840
|B |0.152000 |-1.015101 |0.292788 |-0.179682
|C |-0.650724 |0.098453 |-2.513389 |-0.636284
|D |2.248024 |0.481968 |-0.944033 |-0.107866
|E |-0.590276 |0.964199 |-0.248336 |0.777561
|===

*In[8]:*

newind = 'CA NY WR OR CO'.split()

*In[9]:*

newind

*Out[9]:* ----['CA', 'NY', 'WR', 'OR', 'CO']----

*In[10]:*

df['States']=newind

*In[11]:*

df.set_index('States')

*Out[11]:*

[cols=",,,,",options="header",]
|===
| |W |X |Y |Z
|States | | | |
|CA |-0.469724 |0.443672 |-1.009412 |0.118840
|NY |0.152000 |-1.015101 |0.292788 |-0.179682
|WR |-0.650724 |0.098453 |-2.513389 |-0.636284
|OR |2.248024 |0.481968 |-0.944033 |-0.107866
|CO |-0.590276 |0.964199 |-0.248336 |0.777561
|===

*In[12]:*

#Index levels

*In[23]:*

outside = ['G1','G1','G1','G2','G2','G2']
inside =[1,2,3,1,2,3]
hier_index=list(zip(outside,inside))
hier_index=pd.MultiIndex.from_tuples(hier_index)

*In[24]:*

outside

*Out[24]:* ----['G1', 'G1', 'G1', 'G2', 'G2', 'G2']----

*In[25]:*

inside

*Out[25]:* ----[1, 2, 3, 1, 2, 3]----

*In[26]:*

list(zip(outside,inside))

*Out[26]:* ----[('G1', 1), ('G1', 2), ('G1', 3), ('G2', 1), ('G2', 2), ('G2', 3)]----

*In[27]:*

hier_index

*Out[27]:* ----MultiIndex([('G1', 1), ('G1', 2), ('G1', 3), ('G2', 1), ('G2', 2), ('G2', 3)], )----

*In[21]:*

df=pd.DataFrame(randn(6,2),hier_index,['A','B'])

*In[22]:*

df

*Out[22]:*

[cols=",,,",options="header",]
|===
| | |A |B
|G1 |1 |-0.281696 |-0.048233
| |2 |0.709150 |-0.702492
| |3 |-1.534195 |-0.088502
|G2 |1 |0.871283 |-1.122875
| |2 |-0.838875 |-0.007073
| |3 |-0.924876 |-0.509193
|===

*In[30]:*

df.index.names['Groups','Number']

*Out[30]:*

    ---------------------------------------------------------------------------

    TypeError                                 Traceback (most recent call last)

    <ipython-input-30-6804b513d92d> in <module>
    ----> 1 df.index.names['Groups','Number']


    ~/miniconda3/lib/python3.8/site-packages/pandas/core/indexes/frozen.py in __getitem__(self, n)
         67         if isinstance(n, slice):
         68             return type(self)(super().__getitem__(n))
    ---> 69         return super().__getitem__(n)
         70
         71     def __radd__(self, other):


    TypeError: list indices must be integers or slices, not tuple

*In[31]:*

df

*Out[31]:*

[cols=",,,",options="header",]
|===
| | |A |B
|G1 |1 |-0.281696 |-0.048233
| |2 |0.709150 |-0.702492
| |3 |-1.534195 |-0.088502
|G2 |1 |0.871283 |-1.122875
| |2 |-0.838875 |-0.007073
| |3 |-0.924876 |-0.509193
|===

*In[32]:*

df.loc['G1']

*Out[32]:*

[cols=",,",options="header",]
|===
| |A |B
|1 |-0.281696 |-0.048233
|2 |0.709150 |-0.702492
|3 |-1.534195 |-0.088502
|===

*In[40]:*

df.loc['G1'].loc[1]['B']

*Out[40]:* -----0.04823307471528516----

*In[36]:*

df.loc['G2'].loc[3]['B']

*Out[36]:* -----0.5091927179301485----

*In[ ]:*