In [1]:

import pandas as pd

from lets_plot import *

In [2]:

LetsPlot.setup_html()

In [3]:

mpg = pd.read_csv ("https://raw.githubusercontent.com/JetBrains/lets-plot-docs/master/data/mpg.csv")
mpg.head(3)

Out[3]:

	Unnamed: 0	manufacturer	model	displ	year	cyl	trans	drv	cty	hwy	fl	class
0	1	audi	a4	1.8	1999	4	auto(l5)	f	18	29	p	compact
1	2	audi	a4	1.8	1999	4	manual(m5)	f	21	29	p	compact
2	3	audi	a4	2.0	2008	4	manual(m6)	f	20	31	p	compact

In [4]:

subaru = mpg.loc[mpg['manufacturer'] == 'subaru'] 

p = ggplot(mpg, aes('displ', 'hwy')) \
  + geom_point(data=subaru, color='orange', size = 5) \
  + geom_point()
p

Out[4]:

In [5]:

p \
   + geom_text(x=5.05, y=35, label='subaru', hjust='left', color='#d76e00', size=10) \
   + geom_curve(x=5, y=35, xend=2.62, yend=27, 
                curvature=0.2, arrow=arrow(length=6),
                color='#d76e00')

Out[5]:

In [6]:

p \
   + geom_text(x=4.2, y=25, label='subaru', hjust='left', color='#d76e00', size=10) \
   + geom_curve(x=4.5, y=26.2, xend=2.62, yend=27, 
                curvature=0.5, angle=60, arrow=arrow(length=6),
                color='#d76e00')

Out[6]:

In [7]:

p \
    + geom_text(x=3, y=12, label='subaru', hjust='left', color='#d76e00', size=10) \
    + geom_curve(x=2.95, y=12, xend=2.5, yend=22, 
                 curvature=-0.3, arrow=arrow(length=6),
                 color='#d76e00')

Out[7]:

In [ ]:

In [8]:

mpg_cyl5 = mpg.loc[mpg['cyl'] == 5]


ggplot(mpg, aes('displ', 'hwy')) \
  + geom_point(data=mpg_cyl5, color='#de77ae', size=5) \
  + geom_point() \
  + geom_text(label="Five-cylinder engine", x=4,y=37, hjust=0, color='#c51b7d', size=10) \
  + geom_curve(x=3.95, y=37, xend=2.6, yend=29,
               curvature=0.1, arrow=arrow(length=6),
               color='#c51b7d')

Out[8]:

In [9]:

ggplot(mpg, aes('displ', 'hwy')) \
  + geom_point(data=mpg_cyl5, color='#de77ae', size=5) \
  + geom_point() \
  + geom_text(label="Five-cylinder engine", x=4, y=37, hjust=0, color='#c51b7d', size=10) \
  + geom_curve(data=mpg_cyl5, xend=3.95, yend=37,
               size_start=5,
               curvature=0.1, arrow=arrow(length=6, ends='first'),
               color='#c51b7d')

Out[9]:

In [10]:

mpg['manufacturer'].value_counts()

Out[10]:

dodge         37
toyota        34
volkswagen    27
ford          25
chevrolet     19
audi          18
hyundai       14
subaru        14
nissan        13
honda          9
jeep           8
pontiac        5
land rover     4
mercury        4
lincoln        3
Name: manufacturer, dtype: int64

In [11]:

brand = 'pontiac'
brand_df = mpg.loc[mpg['manufacturer'] == brand] 

ggplot(mpg, aes('displ', 'hwy')) \
  + geom_point(data=brand_df, color='#bd423f', size=5) \
  + geom_point() \
  + geom_text(label=brand, x=6, y=37, hjust=1, color='#bd423f', size=10) \
  + geom_curve(data=brand_df, xend=5.95, yend=35,
               size_start=5,
               curvature=-0.1, arrow=arrow(length=6, ends='first'),
               color='#bd423f') \
  + xlim(3,6)

Out[11]: