1.Import pandas with the right name:



In [12]:

    
import pandas as pd

2. Set all graphics from matplotlib to display inline



In [13]:

    
import matplotlib.pyplot as plt



In [14]:

    
%matplotlib inline

3. Read the csv in (it should be UTF-8 already so you don't have to worry about encoding), save it with the proper boring name



In [19]:

    
df = pd.read_csv("07-hw-animals.csv")



In [30]:

    
df









    Out[30]:






  
    
      
      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

4. Display the names of the columns in the csv



In [20]:

    
df.columns









    Out[20]:





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



In [21]:

    
df.head()









    Out[21]:






  
    
      
      animal
      name
      length
    
  
  
    
      0
      cat
      Anne
      35
    
    
      1
      cat
      Bob
      45
    
    
      2
      dog
      Egglesburg
      65
    
    
      3
      dog
      Devon
      50
    
    
      4
      cat
      Charlie
      32

5. Display the first 3 animals



In [22]:

    
df['animal'].head(3)









    Out[22]:





0    cat
1    cat
2    dog
Name: animal, dtype: object

6. Sort the animals to see the 3 longest animals.



In [26]:

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









    Out[26]:






  
    
      
      animal
      name
      length
    
  
  
    
      2
      dog
      Egglesburg
      65
    
    
      3
      dog
      Devon
      50
    
    
      1
      cat
      Bob
      45

7. What are the counts of the different values of the "animal" column? a.k.a. how many cats and how many dogs.



In [29]:

    
df['animal'].value_counts()









    Out[29]:





cat    3
dog    3
Name: animal, dtype: int64

8. Only select the dogs



In [33]:

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



In [34]:

    
dogs









    Out[34]:






  
    
      
      animal
      name
      length
    
  
  
    
      2
      dog
      Egglesburg
      65
    
    
      3
      dog
      Devon
      50
    
    
      5
      dog
      Fontaine
      35

9. Display all of the animals that are greater than 40 cm.



In [37]:

    
animal_larger_40 = df['length'] > 40
animal_larger_40









    Out[37]:





0    False
1     True
2     True
3     True
4    False
5    False
Name: length, dtype: bool



In [38]:

    
df[animal_larger_40]









    Out[38]:






  
    
      
      animal
      name
      length
    
  
  
    
      1
      cat
      Bob
      45
    
    
      2
      dog
      Egglesburg
      65
    
    
      3
      dog
      Devon
      50

10. 'length' is the animal's length in cm. Create a new column called inches that is the length in inches.



In [39]:

    
df['length'].head()









    Out[39]:





0    35
1    45
2    65
3    50
4    32
Name: length, dtype: int64



In [42]:

    
inch = df['length'] * 0.393701
inch









    Out[42]:





0    13.779535
1    17.716545
2    25.590565
3    19.685050
4    12.598432
5    13.779535
Name: length, dtype: float64



In [41]:

    
inch = df['length'] / 2.54
inch









    Out[41]:





0    13.779528
1    17.716535
2    25.590551
3    19.685039
4    12.598425
5    13.779528
Name: length, dtype: float64



In [43]:

    
df['length_inch'] = inch
df.head()









    Out[43]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      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

11. Save the cats to a separate variable called "cats." Save the dogs to a separate variable called "dogs."



In [44]:

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









    Out[44]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      2
      dog
      Egglesburg
      65
      25.590565
    
    
      3
      dog
      Devon
      50
      19.685050
    
    
      5
      dog
      Fontaine
      35
      13.779535



In [45]:

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









    Out[45]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      0
      cat
      Anne
      35
      13.779535
    
    
      1
      cat
      Bob
      45
      17.716545
    
    
      4
      cat
      Charlie
      32
      12.598432

13. Display all of the animals that are cats and above 12 inches long. First do it using the "cats" variable, then do it using your normal dataframe.



In [48]:

    
cat = df['animal'] == "cat"
twelve_inch = df['length_inch'] > 12


df[cat & twelve_inch].head()









    Out[48]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      0
      cat
      Anne
      35
      13.779535
    
    
      1
      cat
      Bob
      45
      17.716545
    
    
      4
      cat
      Charlie
      32
      12.598432



In [49]:

    
df[(df['animal'] == "cat") & (df['length_inch'] > 12)].head()









    Out[49]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      0
      cat
      Anne
      35
      13.779535
    
    
      1
      cat
      Bob
      45
      17.716545
    
    
      4
      cat
      Charlie
      32
      12.598432

13. What's the mean length of a cat?



In [59]:

    
df[cat].describe()









    Out[59]:






  
    
      
      length
      length_inch
    
  
  
    
      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

14. What's the mean length of a dog



In [63]:

    
dog = df['animal'] == "dog"
df[dog].describe()









    Out[63]:






  
    
      
      length
      length_inch
    
  
  
    
      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

15. Use groupby to accomplish both of the above tasks at once.



In [64]:

    
df.groupby('animal').describe()









    Out[64]:






  
    
      
      
      length
      length_inch
    
    
      animal
      
      
      
    
  
  
    
      cat
      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
    
    
      dog
      count
      3.000000
      3.000000
    
    
      mean
      50.000000
      19.685050
    
    
      std
      15.000000
      5.905515
    
    
      min
      35.000000
      13.779535
    
    
      25%
      42.500000
      16.732292
    
    
      50%
      50.000000
      19.685050
    
    
      75%
      57.500000
      22.637808
    
    
      max
      65.000000
      25.590565

16. Make a histogram of the length of dogs.



In [68]:

    
dogs.hist()









    Out[68]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x06CEDD30>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x06D0DE30>]], dtype=object)

17 Change your graphing style to be something else (anything else!)



In [69]:

    
dogs.plot(kind='line')









    Out[69]:





<matplotlib.axes._subplots.AxesSubplot at 0x6e685d0>

18. Make a horizontal bar graph of the length of the animals, with their name as the label



In [72]:

    
df['length'].plot(kind='barh', x='lenth', y='name')









    Out[72]:





<matplotlib.axes._subplots.AxesSubplot at 0x6e798b0>



In [73]:

    
df['length'].plot(kind='barh', labels= df['name'])









    



---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-73-6c8df178f6a4> in <module>()
----> 1 df['length'].plot(kind='barh', labels= df['name'])

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\pandas\tools\plotting.py in __call__(self, kind, ax, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, label, secondary_y, **kwds)
   3564                            colormap=colormap, table=table, yerr=yerr,
   3565                            xerr=xerr, label=label, secondary_y=secondary_y,
-> 3566                            **kwds)
   3567     __call__.__doc__ = plot_series.__doc__
   3568 

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\pandas\tools\plotting.py in plot_series(data, kind, ax, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, label, secondary_y, **kwds)
   2643                  yerr=yerr, xerr=xerr,
   2644                  label=label, secondary_y=secondary_y,
-> 2645                  **kwds)
   2646 
   2647 

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\pandas\tools\plotting.py in _plot(data, x, y, subplots, ax, kind, **kwds)
   2439         plot_obj = klass(data, subplots=subplots, ax=ax, kind=kind, **kwds)
   2440 
-> 2441     plot_obj.generate()
   2442     plot_obj.draw()
   2443     return plot_obj.result

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\pandas\tools\plotting.py in generate(self)
   1026         self._compute_plot_data()
   1027         self._setup_subplots()
-> 1028         self._make_plot()
   1029         self._add_table()
   1030         self._make_legend()

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\pandas\tools\plotting.py in _make_plot(self)
   1969                 rect = self._plot(ax, self.ax_pos + (i + 0.5) * w, y, w,
   1970                                   start=start, label=label,
-> 1971                                   log=self.log, **kwds)
   1972             self._add_legend_handle(rect, label, index=i)
   1973 

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\pandas\tools\plotting.py in _plot(cls, ax, x, y, w, start, log, **kwds)
   2003     @classmethod
   2004     def _plot(cls, ax, x, y, w, start=0, log=False, **kwds):
-> 2005         return ax.barh(x, y, w, left=start, log=log, **kwds)
   2006 
   2007     def _decorate_ticks(self, ax, name, ticklabels, start_edge, end_edge):

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\matplotlib\axes\_axes.py in barh(self, bottom, width, height, left, **kwargs)
   2287 
   2288         patches = self.bar(left=left, height=height, width=width,
-> 2289                            bottom=bottom, orientation='horizontal', **kwargs)
   2290         return patches
   2291 

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\matplotlib\__init__.py in inner(ax, *args, **kwargs)
   1810                     warnings.warn(msg % (label_namer, func.__name__),
   1811                                   RuntimeWarning, stacklevel=2)
-> 1812             return func(ax, *args, **kwargs)
   1813         pre_doc = inner.__doc__
   1814         if pre_doc is None:

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\matplotlib\axes\_axes.py in bar(self, left, height, width, bottom, **kwargs)
   2129                 label='_nolegend_'
   2130                 )
-> 2131             r.update(kwargs)
   2132             r.get_path()._interpolation_steps = 100
   2133             #print r.get_label(), label, 'label' in kwargs

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\matplotlib\artist.py in update(self, props)
    854                 func = getattr(self, 'set_' + k, None)
    855                 if func is None or not six.callable(func):
--> 856                     raise AttributeError('Unknown property %s' % k)
    857                 func(v)
    858             changed = True

AttributeError: Unknown property labels

19. Make a sorted horizontal bar graph of the cats, with the larger cats on top.



In [74]:

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









    Out[74]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      0
      cat
      Anne
      35
      13.779535
    
    
      1
      cat
      Bob
      45
      17.716545
    
    
      4
      cat
      Charlie
      32
      12.598432



In [76]:

    
sort_cat = cats.sort_values('length', ascending=False)
sort_cat









    Out[76]:






  
    
      
      animal
      name
      length
      length_inch
    
  
  
    
      1
      cat
      Bob
      45
      17.716545
    
    
      0
      cat
      Anne
      35
      13.779535
    
    
      4
      cat
      Charlie
      32
      12.598432



In [79]:

    
sort_cat['length'].plot(kind='barh', x='length', y='name')









    Out[79]:





<matplotlib.axes._subplots.AxesSubplot at 0x7e82210>



In [ ]:

	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

	animal	name	length	length_inch
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

	length	length_inch
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

		length	length_inch
animal
cat	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
dog	count	3.000000	3.000000
	mean	50.000000	19.685050
	std	15.000000	5.905515
	min	35.000000	13.779535
	25%	42.500000	16.732292
	50%	50.000000	19.685050
	75%	57.500000	22.637808
	max	65.000000	25.590565