Scribd
Upload
32 views

Tableau

This document contains R code for creating various data visualizations using the ggplot2 package. It loads vehicle mileage data and performs data wrangling steps like aggregating and sorting. It then generates several plots including scatterplots, bar charts, histograms, density plots, box plots, and pie charts to visualize relationships between variables in the data like city mileage, highway mileage, engine displacement, manufacturer, and vehicle class. The plots aim to explore different geoms and themes in ggplot2.

Uploaded by

Anonymous Tvqo13
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
32 views

Tableau

This document contains R code for creating various data visualizations using the ggplot2 package. It loads vehicle mileage data and performs data wrangling steps like aggregating and sorting. It then generates several plots including scatterplots, bar charts, histograms, density plots, box plots, and pie charts to visualize relationships between variables in the data like city mileage, highway mileage, engine displacement, manufacturer, and vehicle class. The plots aim to explore different geoms and themes in ggplot2.

Uploaded by

Anonymous Tvqo13
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

# load package and data

library(ggplot2)

mpg <- read.csv("http://goo.gl/uEeRGu")

data(mpg, package="ggplot2")

g <-ggplot(mpg, aes(cty, hwy))

# Scatterplot
g +geom_point() +
geom_smooth(method="lm", se=F) +
labs(subtitle="mpg: city vs highway mileage",
y="hwy",
x="cty",
title="Scatterplot with overlapping points",
caption="Source: midwest")

# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
g <-ggplot(mpg, aes(cty, hwy))
g +geom_jitter(width = .5, size=1) +
labs(subtitle="mpg: city vs highway mileage",
y="hwy",
x="cty",
title="Jittered Points")
# Prepare data: group mean city mileage by manufacturer.
cty_mpg<-aggregate(mpg$cty, by=list(mpg$manufacturer), FUN=mean) # aggregate
colnames(cty_mpg) <-c("make", "mileage") # change column names
cty_mpg<-cty_mpg[order(cty_mpg$mileage), ]# sort
cty_mpg$make<-factor(cty_mpg$make, levels =cty_mpg$make) # to retain the order in plot.
head(cty_mpg, 4)

The X variable is now a factor, let’s plot.

Draw plot
ggplot(cty_mpg, aes(x=make, y=mileage)) +
geom_bar(stat="identity", width=.5, fill="tomato3") +
labs(title="Ordered Bar Chart",
subtitle="Make Vs Avg. Mileage",
caption="source: mpg") +
theme(axis.text.x =element_text(angle=65, vjust=0.6))

# Plot
ggplot(cty_mpg, aes(x=make, y=mileage)) +
geom_point(col="tomato2", size=3) +# Draw points
geom_segment(aes(x=make,
xend=make,
y=min(mileage),
yend=max(mileage)),
linetype="dashed",
size=0.1) +# Draw dashed lines
labs(title="Dot Plot",
subtitle="Make Vs Avg. Mileage",
caption="source: mpg") +
coord_flip()
# Histogram on a Continuous (Numeric) Variable
g <-ggplot(mpg, aes(displ)) +scale_fill_brewer(palette ="Spectral")

g +geom_histogram(aes(fill=class),
binwidth = .1,
col="black",
size=.1) +# change binwidth
labs(title="Histogram with Auto Binning",
subtitle="Engine Displacement across Vehicle Classes")

g +geom_histogram(aes(fill=class),
bins=5,
col="black",
size=.1) +# change number of bins
labs(title="Histogram with Fixed Bins",
subtitle="Engine Displacement across Vehicle Classes")

# Histogram on a Categorical variable


g <-ggplot(mpg, aes(manufacturer))
g +geom_bar(aes(fill=class), width =0.5) +
theme(axis.text.x =element_text(angle=65, vjust=0.6)) +
labs(title="Histogram on Categorical Variable",
subtitle="Manufacturer across Vehicle Classes")
# Plot
g <-ggplot(mpg, aes(cty))
g +geom_density(aes(fill=factor(cyl)), alpha=0.8) +
labs(title="Density plot",
subtitle="City Mileage Grouped by Number of cylinders",
caption="Source: mpg",
x="City Mileage",
fill="# Cylinders")

# Plot
g <-ggplot(mpg, aes(class, cty))
g +geom_boxplot(varwidth=T, fill="plum") +
labs(title="Box plot",
subtitle="City Mileage grouped by Class of vehicle",
caption="Source: mpg",
x="Class of Vehicle",
y="City Mileage")

Important Links:

https://www.rstudio.com/wp-content/uploads/2015/03/ggplot2-cheatsheet.pdf

Doc: http://r-statistics.co/Top50-Ggplot2-Visualizations-MasterList-R-Code.html
# Source: Categorical variable.
# mpg$class
pie <-ggplot(mpg, aes(x ="", fill =factor(class))) +
geom_bar(width =1) +
theme(axis.line =element_blank(),
plot.title =element_text(hjust=0.5)) +
labs(fill="class",
x=NULL,
y=NULL,
title="Pie Chart of class",
caption="Source: mpg")

pie +coord_polar(theta ="y", start=0)

You might also like