Exploring the Grammar of Graphics
Charles Pierre
2017-07-25
Vis 1
This graphic is a traditional stacked bar chart. This graphic works on the mpg dataset, which is built into the ggplot2 library. This means that you can access it simply by ggplot(mpg, ….). There is one modification above default in this graphic, I renamed the legend for more clarity.
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 3.3.3
library(dplyr)
## Warning: package 'dplyr' was built under R version 3.3.3
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
data(mpg)
head(mpg)
## # A tibble: 6 x 11
## manufacturer model displ year cyl trans drv cty hwy fl
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr>
## 1 audi a4 1.8 1999 4 auto(l5) f 18 29 p
## 2 audi a4 1.8 1999 4 manual(m5) f 21 29 p
## 3 audi a4 2.0 2008 4 manual(m6) f 20 31 p
## 4 audi a4 2.0 2008 4 auto(av) f 21 30 p
## 5 audi a4 2.8 1999 6 auto(l5) f 16 26 p
## 6 audi a4 2.8 1999 6 manual(m5) f 18 26 p
## # ... with 1 more variables: class <chr>
summary(mpg)
## manufacturer model displ year
## Length:234 Length:234 Min. :1.600 Min. :1999
## Class :character Class :character 1st Qu.:2.400 1st Qu.:1999
## Mode :character Mode :character Median :3.300 Median :2004
## Mean :3.472 Mean :2004
## 3rd Qu.:4.600 3rd Qu.:2008
## Max. :7.000 Max. :2008
## cyl trans drv cty
## Min. :4.000 Length:234 Length:234 Min. : 9.00
## 1st Qu.:4.000 Class :character Class :character 1st Qu.:14.00
## Median :6.000 Mode :character Mode :character Median :17.00
## Mean :5.889 Mean :16.86
## 3rd Qu.:8.000 3rd Qu.:19.00
## Max. :8.000 Max. :35.00
## hwy fl class
## Min. :12.00 Length:234 Length:234
## 1st Qu.:18.00 Class :character Class :character
## Median :24.00 Mode :character Mode :character
## Mean :23.44
## 3rd Qu.:27.00
## Max. :44.00
ggplot(data=mpg) +
geom_bar(mapping=aes(x=class))
ggplot(data=mpg) +
aes(x=class) +
geom_bar(aes(color = trans, fill=trans))
Vis 2
Boxplot using the mpg dataset.
ggplot(data=mpg, aes(x=manufacturer,y=hwy)) + geom_boxplot() + theme_classic()
ggplot(data=mpg, aes(x=manufacturer,y=hwy)) + geom_boxplot() + theme_classic() + labs(x="manufacturer",y="hwy(miles/gallon)") + coord_flip()
ggplot(data=mpg,mapping = aes(x=reorder(manufacturer,hwy,median,na.rm=FALSE),y=hwy))+geom_boxplot()+labs(x="manufacturer",y="hwy(miles/gallon)")+coord_flip()
VIS 3
require(reshape2)
## Loading required package: reshape2
## Warning: package 'reshape2' was built under R version 3.3.3
library(ggthemes)
## Warning: package 'ggthemes' was built under R version 3.3.3
require(stringr)
## Loading required package: stringr
require(diamonds)
## Loading required package: diamonds
## Warning in library(package, lib.loc = lib.loc, character.only = TRUE,
## logical.return = TRUE, : there is no package called 'diamonds'
summary(diamonds)
## carat cut color clarity
## Min. :0.2000 Fair : 1610 D: 6775 SI1 :13065
## 1st Qu.:0.4000 Good : 4906 E: 9797 VS2 :12258
## Median :0.7000 Very Good:12082 F: 9542 SI2 : 9194
## Mean :0.7979 Premium :13791 G:11292 VS1 : 8171
## 3rd Qu.:1.0400 Ideal :21551 H: 8304 VVS2 : 5066
## Max. :5.0100 I: 5422 VVS1 : 3655
## J: 2808 (Other): 2531
## depth table price x
## Min. :43.00 Min. :43.00 Min. : 326 Min. : 0.000
## 1st Qu.:61.00 1st Qu.:56.00 1st Qu.: 950 1st Qu.: 4.710
## Median :61.80 Median :57.00 Median : 2401 Median : 5.700
## Mean :61.75 Mean :57.46 Mean : 3933 Mean : 5.731
## 3rd Qu.:62.50 3rd Qu.:59.00 3rd Qu.: 5324 3rd Qu.: 6.540
## Max. :79.00 Max. :95.00 Max. :18823 Max. :10.740
##
## y z
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 4.720 1st Qu.: 2.910
## Median : 5.710 Median : 3.530
## Mean : 5.735 Mean : 3.539
## 3rd Qu.: 6.540 3rd Qu.: 4.040
## Max. :58.900 Max. :31.800
##
ggplot(data=diamonds, mapping=aes(x=price, y=..density..)) + labs(x="Diamond Price(USD)", y = "Density") + geom_density(mapping = aes(color = cut, fill = cut), binwidth = 500) + theme_economist() + ggtitle("Diamond Price Density")
## Warning: Ignoring unknown parameters: binwidth
Vis 4
head(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
fit = lm(iris$Petal.Length~iris$Sepal.Length, data=iris)
ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length)) + geom_point() + geom_smooth(method="lm") + ylab("Iris Petal Length") + xlab("Iris Sepal Length")
Vis 5
require(iris)
## Loading required package: iris
## Warning in library(package, lib.loc = lib.loc, character.only = TRUE,
## logical.return = TRUE, : there is no package called 'iris'
summary(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
##
ggplot(data=iris, aes(x = Sepal.Length, y = Petal.Length)) + aes(color=Species) + geom_point() + geom_smooth(method = "lm", se = 0) + xlab("Iris Sepal Length") + ylab("Iris Petal Length") + theme_tufte()
