Grammar of Graphics in Python and R

The grammar of graphics package (ggplot2) is the best data visualization library in R. The concept of grammar of graphics is also implemented in Python with the library ggplot and it has similar commands to ggplot2.

Let's see some examples.

The data used is from here.

Grammar of Graphics in Python

ggplot can be installed by simply using this command:

pip install ggplot

Learning ggplot is really easy specially for people who know how to use ggplot2 in R.

from ggplot import *

import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
clim = pd.read_csv(r'https://courses.edx.org/asset-v1:[email protected]+block/climate_change.csv')

A quick look at the data

clim.head(3)  

	Year	Month	MEI	CO2	CH4	N2O	CFC-11	CFC-12	TSI	Aerosols	Temp
0	1983	5	2.556	345.96	1638.59	303.677	191.324	350.113	1366.1024	0.0863	0.109
1	1983	6	2.167	345.52	1633.71	303.746	192.057	351.848	1366.1208	0.0794	0.118
2	1983	7	1.741	344.15	1633.22	303.795	192.818	353.725	1366.2850	0.0731	0.137

ggplot(clim, aes('Year', 'Temp'))+geom_line(color='green')+geom_point()+ggtitle('Temperature Change')+xlab('')+ylab('Temperature')+stat_smooth(colour='blue', span=0.2)

<ggplot: (33274821)>

ggplot(clim, aes('Year', 'CO2'))+geom_line(color='black')+geom_point(color='red') +ggtitle("Carbondioxide Concentration")+xlab('')+ylab('ppm')+\
geom_vline(xintercept=[1990, 2000],linetype='dashed',color='green')

<ggplot: (35118803)>

ggplot(clim, aes('CO2'))+geom_density(fill='orange')+ggtitle("Carbondioxide Concentration")+xlab('')

<ggplot: (33196734)>

Let's create a new variable whether the temperature anomaly is negative or positive.

clim['below_zero']=clim.Temp < 0

 ggplot(clim, aes('CO2',fill='below_zero'))+geom_density(alpha=0.5)+ggtitle("Carbondioxide Concentration")

<ggplot: (35690602)>

We can also use the 'meat' dataset that comes with ggplot.

ggplot(pd.melt(meat, id_vars=['date']), aes(x='date', y='value', color='variable')) +\
    geom_line()

<ggplot: (35162965)>

meat_lng = pd.melt(meat[['date', 'beef', 'broilers', 'pork']], id_vars=['date'])
p = ggplot(aes(x='value', colour='variable', fill=True, alpha=0.3), data=meat_lng)
p + geom_density()

Grammar of Graphics in R

Let's re-generate the figures above with minor changes to the codes in ggplot in python.

library(ggplot2)

setwd("C:/Fish/Python/Python_vs_R")
options(jupyter.plot_mimetypes = 'image/png')

clim<-read.csv("climate_change.csv")

names(clim)

1. "Year"
2. "Month"
3. "MEI"
4. "CO2"
5. "CH4"
6. "N2O"
7. "CFC.11"
8. "CFC.12"
9. "TSI"
10. "Aerosols"
11. "Temp"

options(repr.plot.width = 8)
options(repr.plot.height = 6)

ggplot(clim, aes(Year, Temp))+geom_line(color='green')+geom_point()+ggtitle('Temperature Change')+xlab('')+ylab('Temperature')+stat_smooth(colour='blue', span=0.2)

options(repr.plot.width = 8)
options(repr.plot.height = 6)

ggplot(clim, aes(Year, CO2))+geom_line(color='black')+geom_point(color='red') +ggtitle("Carbondioxide Concentration")+xlab('')+ylab('ppm')+
geom_vline(xintercept = c(1990,2000),colour="green", linetype = "longdash")

clim$below_zero=clim$Temp < 0

options(repr.plot.width = 6)
options(repr.plot.height = 4)

ggplot(clim, aes(CO2,fill=below_zero))+geom_density(alpha=0.5)+ggtitle("Carbondioxide Concentration")

data(mpg)

g<-ggplot(mpg, aes(displ, hwy, color=factor(year)))

g+geom_point()

g+geom_point()+facet_grid(drv~cyl, margins=TRUE)

g+geom_point()+facet_grid(drv~cyl, margins=TRUE)+geom_smooth(method="lm", se=FALSE,size=2, color="black")+labs(x="Displacement",y="Highway Mileage") 

data(diamonds)

g<-ggplot(diamonds, aes(depth, price))

g+geom_point(alpha=1/3)

cutpoints<-quantile(diamonds$carat,seq(0,1,length=4),na.rm=TRUE)

diamonds$car2<-cut(diamonds$carat,cutpoints)

g<-ggplot(diamonds, aes(depth, price))
g+geom_point(alpha=1/3)+facet_grid(cut~car2)

g+geom_point(alpha=1/3)+facet_grid(cut~car2)+geom_smooth(method="lm",size=3,color="pink")

ggplot(diamonds,aes(carat,price))+geom_boxplot()+facet_grid(.~cut)