

In [1]:

    
from ggplot import *
import pandas as pd
import numpy as np

Datasets



In [2]:

    
meat.tail()









    Out[2]:






  
    
      
      date
      beef
      veal
      pork
      lamb_and_mutton
      broilers
      other_chicken
      turkey
    
  
  
    
      822
      2012-07-01 00:00:00
       2200.8
        9.5
       1721.8
       12.5
       3127.0
       43.4
       497.2
    
    
      823
      2012-08-01 00:00:00
       2367.5
       10.1
       1997.9
       14.2
       3317.4
       51.0
       530.1
    
    
      824
      2012-09-01 00:00:00
       2016.0
        8.8
       1911.0
       12.5
       2927.1
       43.7
       453.1
    
    
      825
      2012-10-01 00:00:00
       2343.7
       10.3
       2210.4
       14.2
       3335.0
       43.8
       579.9
    
    
      826
      2012-11-01 00:00:00
       2206.6
       10.1
       2078.7
       12.4
       3006.7
       37.5
       515.3



In [3]:

    
diamonds.head()



In [4]:

    
pageviews.head()









    Out[4]:






  
    
      
      date_hour
      pageviews
    
  
  
    
      0
      2013-02-11 21:00:00
       8860.982383
    
    
      1
      2013-02-11 22:00:00
       8637.474753
    
    
      2
      2013-02-11 23:00:00
       9020.593099
    
    
      3
      2013-02-12 00:00:00
       8437.500380
    
    
      4
      2013-02-12 01:00:00
       9157.399672



In [5]:

    
mtcars.head()









    Out[5]:






  
    
      
      name
      mpg
      cyl
      disp
      hp
      drat
      wt
      qsec
      vs
      am
      gear
      carb
    
  
  
    
      0
               Mazda RX4
       21.0
       6
       160
       110
       3.90
       2.620
       16.46
       0
       1
       4
       4
    
    
      1
           Mazda RX4 Wag
       21.0
       6
       160
       110
       3.90
       2.875
       17.02
       0
       1
       4
       4
    
    
      2
              Datsun 710
       22.8
       4
       108
        93
       3.85
       2.320
       18.61
       1
       1
       4
       1
    
    
      3
          Hornet 4 Drive
       21.4
       6
       258
       110
       3.08
       3.215
       19.44
       1
       0
       3
       1
    
    
      4
       Hornet Sportabout
       18.7
       8
       360
       175
       3.15
       3.440
       17.02
       0
       0
       3
       2

`ggplot`



In [6]:

    
aes(x='wt', y='mpg')









    Out[6]:





{'y': 'mpg', 'x': 'wt'}



In [7]:

    
ggplot(aes(x='wt', y='mpg'))









    



---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-7-4c191f620be2> in <module>()
----> 1 ggplot(aes(x='wt', y='mpg'))

TypeError: __init__() takes exactly 3 arguments (2 given)



In [8]:

    
p = ggplot(mtcars, aes(x='wt', y='mpg'))



In [9]:

    
p = ggplot(aes(x='wt', y='mpg'), data=mtcars)

This is blank because we didn't pass the plot any "layers"



In [10]:

    
p









    












    Out[10]:





<ggplot: (281312861)>

Let's add some points...



In [11]:

    
p + geom_point()









    












    Out[11]:





<ggplot: (281840941)>

The geoms

You can see all of them here.



In [12]:

    
p + geom_point()









    












    Out[12]:





<ggplot: (277318757)>

`geom_line`



In [13]:

    
ggplot(aes(x='date', y='beef'), data=meat) + geom_line()









    












    Out[13]:





<ggplot: (281848029)>

`geom_step`



In [14]:

    
df = pd.DataFrame({"x": range(100)})
df['y'] = np.random.choice([-1, 1], 100)
df.y = df.y.cumsum()



In [15]:

    
ggplot(aes(x='x', y='y'), data=df) + geom_step()









    












    Out[15]:





<ggplot: (281895749)>

`geom_histogram`



In [16]:

    
ggplot(aes(x='carat'), data=diamonds) + geom_histogram()









    



binwidth defaulted to range/30. Use 'binwidth = x' to adjust this.






    












    Out[16]:





<ggplot: (281900621)>

`geom_density`



In [17]:

    
df = pd.DataFrame(dict(x=np.random.normal(0, 1, 10000)))
ggplot(df, aes(x='x')) + geom_density()









    












    Out[17]:





<ggplot: (281459473)>

Combining Geoms



In [18]:

    
ggplot(aes(x='date', y='beef'), data=meat) +\
    geom_point(color='red', alpha=0.3) +\
    geom_line()









    












    Out[18]:





<ggplot: (282659613)>



In [19]:

    
ggplot(aes(x='wt', y='mpg'), data=mtcars) +\
    geom_point() +\
    geom_abline(color='blue', slope=-5, intercept=40)









    












    Out[19]:





<ggplot: (281458785)>



In [20]:

    
ggplot(aes(x='wt', y='mpg'), data=mtcars) +\
    geom_point(color="blue", size=200) +\
    geom_point(color="white", size = 100) +\
    geom_point(color="red", size = 25)









    












    Out[20]:





<ggplot: (281900649)>



In [21]:

    
ggplot(aes(x='wt', y='mpg'), data=mtcars) +\
    geom_point(color="blue", size=200) +\
    geom_point(color="white", size = 100) +\
    geom_point(color="red", size = 25) +\
    geom_vline(x=4.5)









    












    Out[21]:





<ggplot: (281896157)>



In [22]:

    
ggplot(aes(x='wt', y='mpg'), data=mtcars) +\
    geom_point(color="blue", size=200) +\
    geom_point(color="white", size = 100) +\
    geom_point(color="red", size = 25) +\
    geom_hline(y=12.5) +\
    geom_vline(x=4.5)









    












    Out[22]:





<ggplot: (278820309)>

	carat	cut	color	clarity	depth	table	price	x	y	z
0	0.23	Ideal	E	SI2	61.5	55	326	3.95	3.98	2.43
1	0.21	Premium	E	SI1	59.8	61	326	3.89	3.84	2.31
2	0.23	Good	E	VS1	56.9	65	327	4.05	4.07	2.31
3	0.29	Premium	I	VS2	62.4	58	334	4.20	4.23	2.63
4	0.31	Good	J	SI2	63.3	58	335	4.34	4.35	2.75

	date	beef	veal	pork	lamb_and_mutton	broilers	other_chicken	turkey
822	2012-07-01 00:00:00	2200.8	9.5	1721.8	12.5	3127.0	43.4	497.2
823	2012-08-01 00:00:00	2367.5	10.1	1997.9	14.2	3317.4	51.0	530.1
824	2012-09-01 00:00:00	2016.0	8.8	1911.0	12.5	2927.1	43.7	453.1
825	2012-10-01 00:00:00	2343.7	10.3	2210.4	14.2	3335.0	43.8	579.9
826	2012-11-01 00:00:00	2206.6	10.1	2078.7	12.4	3006.7	37.5	515.3

	date_hour	pageviews
0	2013-02-11 21:00:00	8860.982383
1	2013-02-11 22:00:00	8637.474753
2	2013-02-11 23:00:00	9020.593099
3	2013-02-12 00:00:00	8437.500380
4	2013-02-12 01:00:00	9157.399672

	name	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160	110	3.90	2.620	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	160	110	3.90	2.875	17.02	0	1	4	4
2	Datsun 710	22.8	4	108	93	3.85	2.320	18.61	1	1	4	1
3	Hornet 4 Drive	21.4	6	258	110	3.08	3.215	19.44	1	0	3	1
4	Hornet Sportabout	18.7	8	360	175	3.15	3.440	17.02	0	0	3	2