title: “R 基本绘图–R markdown文档”
author:

cnliutz
documentclass: ctexart
keywords:
R chart
R Markdown
output:
rticles::ctex:
fig_caption: yes
number_sections: yes
toc: yes

knitr::opts_chunk$set(echo = TRUE)

R Basic Graphs

From R in Action Third edition Chapter 6

plot(pressure)

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

Bar Chart

data(Arthritis,package = "vcd")
table(Arthritis$Improved)

library(ggplot2)

#Simple bar chart
ggplot(Arthritis, aes(x=Improved)) + geom_bar() + 
 labs(title="Simple Bar chart", 
 x="Improvement", 
 y="Frequency")      

#Horizontal bar chart
ggplot(Arthritis, aes(x=Improved)) + geom_bar() + 
 labs(title="Horizontal Bar chart", 
 x="Improvement", 
 y="Frequency") + 
 coord_flip()

Stacked, grouped, and filled bar charts

library(ggplot2)
table(Arthritis$Improved, Arthritis$Treatment)
#❶Stacked bar chart
ggplot(Arthritis, aes(x=Treatment, fill=Improved)) + 
 geom_bar(position = "stack") + 
 labs(title="Stacked Bar chart", 
 x="Treatment", 
 y="Frequency") 
#❷ Grouped bar chart
ggplot(Arthritis, aes(x=Treatment, fill=Improved)) + 
 geom_bar(position = "dodge") + 
 labs(title="Grouped Bar chart", 
 x="Treatment", 
 y="Frequency") 
#❸ Filled bar chart
ggplot(Arthritis, aes(x=Treatment, fill=Improved)) + 
 geom_bar(position = "fill") + 
 labs(title="Filled Bar chart", 
 x="Treatment", 
 y="Proportion")

summary(cars)

Bar chart for sorted mean values

❶ Generates means by region
❷ Plots means in a sorted bar chart


states <-data.frame(state.region,state.x77)
library(dplyr)
library(ggplot2)
plotdata <-states %>%
  group_by(state.region) %>%
  summarize(mean=mean(Illiteracy))   #Illiteracy文盲
plotdata
ggplot(plotdata, aes(x=reorder(state.region, mean), y=mean)) + 
 geom_bar(stat="identity") + 
 labs(x="Region", 
 y="", 
 title = "Mean Illiteracy Rate")

Bar chart label

ggplot(mpg, aes(x=model)) + 
 geom_bar() +
 labs(title="Car models in the mpg dataset", 
 y="Frequency", x="")

ggplot(mpg, aes(x=model)) + 
 geom_bar() +
 labs(title="Car models in the mpg dataset", 
 y="Frequency", x="") +
 coord_flip()

ggplot(mpg, aes(x=model)) + 
 geom_bar() +
 labs(title="Model names in the mpg dataset", 
 y="Frequency", x="") +
 theme(axis.text.x = element_text(angle = 45, hjust = 1, size=8))

Pie Chart

ggpie(data, x, by, offset, percent, legend, title)
where

data is a data frame.
x is the categorical variable to be plotted.
by is an optional second categorical variable. If present, a
pie will be produced for each level of this variable.
offset is the distance of the pie slice labels from the
origin. A value of 0.5 will place the labels in the center of
the slices, and a value greater than 1.0 will place them
outside the slice.
percent is logical. If FALSE, percentage printing is
suppressed.
legend is logical. If FALSE, the legend is omitted, and each
pie slice is labeled.
title is an option title.


if(!require(remotes)) install.packages("remotes")
{remotes::install_github("rkabacoff/ggpie") }

library(ggplot2)
library(ggpie)
ggpie(mpg, class)
ggpie(mpg, class, legend=FALSE, offset=1.3, 
 title="Automobiles by Car Class")
ggpie(mpg, class, year, 
 legend=FALSE, offset=1.3, title="Car Class by Year")


pie(table(mpg$class))

Tree maps

library(ggplot2)
library(dplyr)
library(treemapify)
#❶ Summarizes the data
plotdata <- mpg %>% count(manufacturer)
#❷ Creates the tree map
ggplot(plotdata, 
 aes(fill = manufacturer, 
 area = n, 
 label = manufacturer)) + 
geom_treemap() + 
geom_treemap_text() + 
theme(legend.position = "none")

###Tree map with subgrouping

library(ggplot2)
library(dplyr)
library(treemapify)
plotdata <- mpg %>% 
 count(manufacturer, drv)  # Computes cell counts
 plotdata$drv <- factor(plotdata$drv, 
 levels=c("4", "f", "r"), 
 labels=c("4-wheel", "front-wheel", "rear"))   # Provides better labels for drivetrains
#❸ Creates tree map
ggplot(plotdata, 
 aes(fill = manufacturer, 
 area = n, 
 label = manufacturer, 
 subgroup=drv)) + 
 geom_treemap() + 
 geom_treemap_subgroup_border() + 
 geom_treemap_subgroup_text( 
 place = "middle", 
 colour = "black", 
 alpha = 0.5, 
 grow = FALSE) + 
 geom_treemap_text(colour = "white", 
 place = "centre", 
 grow=FALSE) + 
 theme(legend.position = "none")

hist

library(lattice)
head(singer)
histogram(~height | voice.part, data = singer,
main="Distribution of Heights by Voice Pitch",
xlab="Height (inches)")

summary(women)
fit <- lm(weight ~ height, data=women)
summary(fit)
plot(women)

hist(mtcars$mpg, 
     freq=FALSE, 
     breaks=12, 
     col="red", 
     xlab="Miles Per Gallon", 
     main="Histogram, rug plot, density curve")  
rug(jitter(mtcars$mpg))   #地毯、抖动
lines(density(mtcars$mpg), col="blue", lwd=2)

Histograms

Histograms display the distribution of a continuous variable by
dividing the range of scores into a specified number of bins on
267
the x-axis and displaying the frequency of scores in each bin on
the y-axis. You can create histograms using:

ggplot(data, aes(x = contvar)) + geom_histogram()

library(ggplot2)
library(scales)
data(mpg)
#Simple histogram

cars2008 <- mpg[mpg$year == 2008, ]
ggplot(cars2008, aes(x=cty)) + 
 geom_histogram() + 
 labs(title="Default histogram") 

# Colored histogram with 20 bins
ggplot(cars2008, aes(x=hwy)) + 
 geom_histogram(bins=20, color="white", fill="steelblue") + 
 labs(title="Colored histogram with 20 bins", 
 x="City Miles Per Gallon", 
 y="Frequency")

#Histogram with percentages
ggplot(cars2008, aes(x=hwy, y=after_stat(density))) + 
 geom_histogram(bins=20, color="white", fill="steelblue") + 
 scale_y_continuous(labels=scales::percent) + 
 labs(title="Histogram with percentages", 
 y= "Percent",
 x="City Miles Per Gallon")

# Histogram with density curve
ggplot(cars2008, aes(x=cty, y=after_stat(density))) + 
 geom_histogram(bins=20, color="white", fill="steelblue") + 
 scale_y_continuous(labels=scales::percent) + 
 geom_density(color="red", size=1) + 
 labs(title="Histogram with density curve", 
 y="Percent" , 
 x="Highway Miles Per Gallon")

-《R In Action》 third edtion, page 267

R基本绘图方法ggplot2