In [1]:

    

import pandas as pd


    

In [2]:

    

%matplotlib inline


    

In [3]:

    

df = pd.read_csv("07-hw-animals.csv", encoding='UTF8')


    

In [4]:

    

df


    

    
Out[4]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
0
      
cat
      
Anne
      
35
    
    

      
1
      
cat
      
Bob
      
45
    
    

      
2
      
dog
      
Egglesburg
      
65
    
    

      
3
      
dog
      
Devon
      
50
    
    

      
4
      
cat
      
Charlie
      
32
    
    

      
5
      
dog
      
Fontaine
      
35
    
  

In [5]:

    

df.columns


    

    
Out[5]:





Index(['animal', 'name', 'length'], dtype='object')

In [6]:

    

df.head(3)


    

    
Out[6]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
0
      
cat
      
Anne
      
35
    
    

      
1
      
cat
      
Bob
      
45
    
    

      
2
      
dog
      
Egglesburg
      
65
    
  

In [9]:

    

df.sort_values(by='length',ascending=False).head(3)


    

    
Out[9]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
2
      
dog
      
Egglesburg
      
65
    
    

      
3
      
dog
      
Devon
      
50
    
    

      
1
      
cat
      
Bob
      
45
    
  

In [10]:

    

df['animal'].value_counts()


    

    
Out[10]:





dog    3
cat    3
Name: animal, dtype: int64

In [12]:

    

df[df['animal']=='dog']


    

    
Out[12]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
2
      
dog
      
Egglesburg
      
65
    
    

      
3
      
dog
      
Devon
      
50
    
    

      
5
      
dog
      
Fontaine
      
35
    
  

In [18]:

    

df[df['length']>40]


    

    
Out[18]:






  

    

      

      
animal
      
name
      
length
      
lengthincm
      
lengthininches
    
  
  

    

      
1
      
cat
      
Bob
      
45
      
17.716545
      
17.716545
    
    

      
2
      
dog
      
Egglesburg
      
65
      
25.590565
      
25.590565
    
    

      
3
      
dog
      
Devon
      
50
      
19.685050
      
19.685050
    
  

In [22]:

    

df['lengthininches']=df['length']*0.393701


    

In [23]:

    

df.head()


    

    
Out[23]:






  

    

      

      
animal
      
name
      
length
      
lengthininches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.779535
    
    

      
1
      
cat
      
Bob
      
45
      
17.716545
    
    

      
2
      
dog
      
Egglesburg
      
65
      
25.590565
    
    

      
3
      
dog
      
Devon
      
50
      
19.685050
    
    

      
4
      
cat
      
Charlie
      
32
      
12.598432
    
  

In [24]:

    

cats=df[df['animal']=='cat']


    

In [25]:

    

dogs=df[df['animal']=='dog']


    

In [26]:

    

cats


    

    
Out[26]:






  

    

      

      
animal
      
name
      
length
      
lengthininches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.779535
    
    

      
1
      
cat
      
Bob
      
45
      
17.716545
    
    

      
4
      
cat
      
Charlie
      
32
      
12.598432
    
  

In [27]:

    

dogs


    

    
Out[27]:






  

    

      

      
animal
      
name
      
length
      
lengthininches
    
  
  

    

      
2
      
dog
      
Egglesburg
      
65
      
25.590565
    
    

      
3
      
dog
      
Devon
      
50
      
19.685050
    
    

      
5
      
dog
      
Fontaine
      
35
      
13.779535
    
  

In [31]:

    

cats[cats['lengthininches']>12]


    

    
Out[31]:






  

    

      

      
animal
      
name
      
length
      
lengthininches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.779535
    
    

      
1
      
cat
      
Bob
      
45
      
17.716545
    
    

      
4
      
cat
      
Charlie
      
32
      
12.598432
    
  

In [64]:

    

df[(df['animal']=='cat') & (df['lengthininches']>12)]


    

    
Out[64]:






  

    

      

      
animal
      
name
      
length
      
lengthininches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.779535
    
    

      
1
      
cat
      
Bob
      
45
      
17.716545
    
    

      
4
      
cat
      
Charlie
      
32
      
12.598432
    
  

In [46]:

    

cats.describe()


    

    
Out[46]:






  

    

      

      
length
      
lengthininches
    
  
  

    

      
count
      
3.000000
      
3.000000
    
    

      
mean
      
37.333333
      
14.698171
    
    

      
std
      
6.806859
      
2.679867
    
    

      
min
      
32.000000
      
12.598432
    
    

      
25%
      
33.500000
      
13.188984
    
    

      
50%
      
35.000000
      
13.779535
    
    

      
75%
      
40.000000
      
15.748040
    
    

      
max
      
45.000000
      
17.716545
    
  

In [47]:

    

dogs.describe()


    

    
Out[47]:






  

    

      

      
length
      
lengthininches
    
  
  

    

      
count
      
3.0
      
3.000000
    
    

      
mean
      
50.0
      
19.685050
    
    

      
std
      
15.0
      
5.905515
    
    

      
min
      
35.0
      
13.779535
    
    

      
25%
      
42.5
      
16.732292
    
    

      
50%
      
50.0
      
19.685050
    
    

      
75%
      
57.5
      
22.637808
    
    

      
max
      
65.0
      
25.590565
    
  

In [49]:

    

df.groupby(cats,dogs).describe()


    

    




---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-49-87c7a5d03851> in <module>()
----> 1 df.groupby(cats,dogs).describe()

c:\users\harsha devulapalli\appdata\local\programs\python\python35\lib\site-packages\pandas\core\generic.py in groupby(self, by, axis, level, as_index, sort, group_keys, squeeze, **kwargs)
   3773         if level is None and by is None:
   3774             raise TypeError("You have to supply one of 'by' and 'level'")
-> 3775         axis = self._get_axis_number(axis)
   3776         return groupby(self, by=by, axis=axis, level=level, as_index=as_index,
   3777                        sort=sort, group_keys=group_keys, squeeze=squeeze,

c:\users\harsha devulapalli\appdata\local\programs\python\python35\lib\site-packages\pandas\core\generic.py in _get_axis_number(self, axis)
    306 
    307     def _get_axis_number(self, axis):
--> 308         axis = self._AXIS_ALIASES.get(axis, axis)
    309         if com.is_integer(axis):
    310             if axis in self._AXIS_NAMES:

c:\users\harsha devulapalli\appdata\local\programs\python\python35\lib\site-packages\pandas\core\generic.py in __hash__(self)
    804     def __hash__(self):
    805         raise TypeError('{0!r} objects are mutable, thus they cannot be'
--> 806                         ' hashed'.format(self.__class__.__name__))
    807 
    808     def __iter__(self):

TypeError: 'DataFrame' objects are mutable, thus they cannot be hashed

In [50]:

    

dogs


    

    
Out[50]:






  

    

      

      
animal
      
name
      
length
      
lengthininches
    
  
  

    

      
2
      
dog
      
Egglesburg
      
65
      
25.590565
    
    

      
3
      
dog
      
Devon
      
50
      
19.685050
    
    

      
5
      
dog
      
Fontaine
      
35
      
13.779535
    
  

In [51]:

    

dogs['lengthininches'].hist()


    

    
Out[51]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a5fd9b2ef0>






    

In [53]:

    

import matplotlib.pyplot as plt


    

In [54]:

    

plt.style.available


    

    
Out[54]:





['seaborn-talk',
 'seaborn-notebook',
 'seaborn-muted',
 'bmh',
 'seaborn-poster',
 'grayscale',
 'seaborn-ticks',
 'seaborn-white',
 'seaborn-pastel',
 'ggplot',
 'seaborn-dark-palette',
 'seaborn-deep',
 'classic',
 'seaborn-bright',
 'fivethirtyeight',
 'dark_background',
 'seaborn-whitegrid',
 'seaborn-colorblind',
 'seaborn-dark',
 'seaborn-paper',
 'seaborn-darkgrid']

In [55]:

    

plt.style.use('fivethirtyeight')


    

In [69]:

    

dogs.plot(kind='barh',x='name',y='length')


    

    
Out[69]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a5ff362eb8>






    

In [79]:

    

catssorted=cats.sort_values(by='lengthininches')


    

In [80]:

    

catssorted.plot(kind='barh',x='name',y='length')


    

    
Out[80]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a5ff62b668>






    

In [ ]: