notebook.community

Edit and run



In [4]:

    
import pandas as pd



In [5]:

    
import matplotlib.pyplot as plt
%matplotlib inline



In [7]:

    
#for encoding the command would look smth like this:
#df = pd.read_csv("XXXXXXXXXXXXXXXXX.csv", encoding='mac_roman')
df = pd.read_csv("Animal_Data/07-hw-animals.csv")



In [8]:

    
df.columns









    Out[8]:





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



In [9]:

    
df.head(3)









    Out[9]:






  
    
      
      animal
      name
      length
    
  
  
    
      0
      cat
      Anne
      35
    
    
      1
      cat
      Bob
      45
    
    
      2
      dog
      Egglesburg
      65



In [10]:

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









    Out[10]:






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



In [11]:

    
df['animal'].value_counts()









    Out[11]:





cat    3
dog    3
Name: animal, dtype: int64



In [14]:

    
#df['animal'] == 'dog' this just tests, whether row is a dog or not, True or False
#is_dog = df['animal'] == 'dog'
#df[is_dog]
df[df['animal'] == 'dog']









    Out[14]:






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



In [15]:

    
df[df['length'] > 40]









    Out[15]:






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



In [18]:

    
#del df['feet']



In [19]:

    
df['inches'] = df['length'] * 0.394
df.head()



In [23]:

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



In [24]:

    
cats[cats['inches'] > 12]



In [25]:

    
#df[df[df[df['animal'] == 'cat']'inches'] > 12]
#df[df['animal'] == 'cat']&
#df[df['inches'] > 12]

#pd.read_csv('imdb.txt')
#  .sort(columns='year')
#  .filter('year >1990')
#  .to_csv('filtered.csv')

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

#3 > 2 & 4 > 3
#true  & true
#true

#3 > 2 & 4 > 3
#true  & 4 > 3

#(3 > 2) & (4 > 3)



In [26]:

    
df[df['animal'] == 'cat'].describe()



In [27]:

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



In [29]:

    
df.groupby(['animal'])['inches'].describe()









    Out[29]:





animal       
cat     count     3.000000
        mean     14.709333
        std       2.681903
        min      12.608000
        25%      13.199000
        50%      13.790000
        75%      15.760000
        max      17.730000
dog     count     3.000000
        mean     19.700000
        std       5.910000
        min      13.790000
        25%      16.745000
        50%      19.700000
        75%      22.655000
        max      25.610000
Name: inches, dtype: float64



In [30]:

    
df[df['animal'] == 'dog'].hist()









    Out[30]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x1134ae7b8>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x113652a58>]], dtype=object)



In [31]:

    
import matplotlib.pyplot as plt
plt.style.available









    Out[31]:





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



In [32]:

    
plt.style.use('ggplot')



In [33]:

    
dogs['inches'].hist()









    Out[33]:





<matplotlib.axes._subplots.AxesSubplot at 0x1136bda90>



In [35]:

    
df['length'].plot(kind='bar')









    Out[35]:





<matplotlib.axes._subplots.AxesSubplot at 0x113901160>



In [ ]:

    
#or:



In [34]:

    
df.plot(kind='barh', x='name', y='length', legend=False)









    Out[34]:





<matplotlib.axes._subplots.AxesSubplot at 0x1138328d0>



In [36]:

    
cats_sorted = cats.sort_values(by='length', ascending=True).head(3)
cats_sorted.plot(kind='barh', x='name', y='length', legend=False)









    Out[36]:





<matplotlib.axes._subplots.AxesSubplot at 0x11397b5f8>



In [ ]:

    
#or:



In [40]:

    
df[df['animal'] == 'cat'].sort_values(by='length', ascending=True).plot(kind='barh', x='name', y='length')









    Out[40]:





<matplotlib.axes._subplots.AxesSubplot at 0x113d6b400>



In [ ]:

	animal	name	length	inches
0	cat	Anne	35	13.790
1	cat	Bob	45	17.730
2	dog	Egglesburg	65	25.610
3	dog	Devon	50	19.700
4	cat	Charlie	32	12.608

	length	inches
count	3.000000	3.000000
mean	37.333333	14.709333
std	6.806859	2.681903
min	32.000000	12.608000
25%	33.500000	13.199000
50%	35.000000	13.790000
75%	40.000000	15.760000
max	45.000000	17.730000

	length	inches
count	3.0	3.000
mean	50.0	19.700
std	15.0	5.910
min	35.0	13.790
25%	42.5	16.745
50%	50.0	19.700
75%	57.5	22.655
max	65.0	25.610