ggplot2绘图--类别比较型图表

本文所用代码来自于《R语言数据可视化之美》，我也是学习借鉴 。

ggplot2绘图--类别比较型图表

沈益

7/18/2019

library(ggplot2)
library(RColorBrewer)
library(reshape2)

类别比较型图标–柱形图系列

1. 单数据系列柱形图

# 绘图数据
mydata <- data.frame(Cut = c("Fair", "Good", "Very Good", "premium", "Ideal"), 
                     Price = c(4300, 3800, 3950, 4700, 3500))
# 对数据进行排序
mydata$Cut <- factor(mydata$Cut, levels = mydata$Cut[order(mydata$Price, decreasing = TRUE)])
# 绘制单数据系列柱形图
ggplot(mydata, aes(Cut, Price)) + 
  geom_bar(stat = "identity", 
           width = 0.8, colour = "black", size = 0.25, 
           fill = "#FC4E07", alpha = 1) + 
  ylim(0, 6000) + 
  theme(axis.title = element_text(size = 15, face = "plain", colour = "blue"), 
        axis.text = element_text(size = 12, face = "plain", colour = "red"))

2. 双数据系列柱形图

# 读取绘图数据
mydata <- read.csv("配套资源/第3章_类别比较型图表/MultiColumn_Data.csv", check.names = FALSE, 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
# 将二维数据转为一维数据
mydata <- reshape2::melt(mydata, id.vars = "Catergory")
# 绘制双数据系列柱形图
ggplot(data = mydata, aes(Catergory, value, fill = variable)) + 
  geom_bar(stat = "identity", position = position_dodge(), 
           color = "black", width = 0.7, size = 0.25) + 
  scale_fill_manual(values = c("#00AFBB", "#FC4E07")) + 
  ylim(0, 10) + 
  theme(
    axis.title = element_text(size = 15, face = "plain", color = "black"), 
    axis.text = element_text(size = 12, face = "plain", color = "black"), 
    legend.title = element_text(size = 14, face = "plain", color = "black"), 
    legend.background = element_blank(), 
    legend.position = c(0.88, 0.88)
  )

3. 堆积柱形图

# 读取数据
mydata <- read.csv("配套资源/第3章_类别比较型图表/StackedColumn_Data.csv", sep = ",", 
                   na.strings = "NA", stringsAsFactors = FALSE)
# 将二维表转换为一维表
mydata <- melt(mydata, id.vars = "Clarity")
# 绘制堆积柱形图
ggplot(data = mydata, aes(variable, value, fill = Clarity)) + 
  geom_bar(stat = "identity", position = position_stack(), 
           color = "black", width = 0.7, size = 0.25) +
  scale_fill_manual(values = brewer.pal(9, "YlOrRd")[c(6:2)]) + 
  ylim(0, 15000) + 
  
  theme(
    axis.title = element_text(size = 15, face = "plain", color = "black"), 
    axis.text = element_text(size = 12, face = "plain", color = "black"), 
    legend.title = element_text(size = 14, face = "plain", color = "black"), 
    legend.background = element_rect(colour = "blue", fill = "skyblue", linetype = 2, size = 0.8),
    legend.position = c(0.85, 0.75)
  )

4. 百分比堆积柱形图

# 读取绘图数据
mydata <- read.csv("配套资源/第3章_类别比较型图表/StackedColumn_Data.csv", 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
# 将多维表转换为一维表
mydata <- melt(mydata, id.vars = "Clarity")
# 绘图
ggplot(mydata, aes(variable, value, fill = Clarity)) + 
  geom_bar(position = "fill", stat = "identity", 
           color = "black", width = 0.8, size = 0.25) + 
  scale_fill_manual(values = brewer.pal(9, "GnBu")[c(7:2)]) + 
  theme(
    axis.title = element_text(size = 15, face = "plain", color = "black"), 
    axis.text = element_text(size = 12, face = "plain", color = "black"), 
    legend.title = element_text(size = 14, face = "plain", color = "black"), 
    legend.position = "right"
  )

5. 条形图

添加 coord_flip()即可将 x-y转换

# 读取绘图数据
mydata <- read.csv("配套资源/第3章_类别比较型图表/StackedColumn_Data.csv", 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
# 将多维表转换为一维表
mydata <- melt(mydata, id.vars = "Clarity")
# 绘图
ggplot(mydata, aes(variable, value, fill = Clarity)) + 
  geom_bar(position = "fill", stat = "identity", 
           color = "black", width = 0.8, size = 0.25) + 
  scale_fill_manual(values = brewer.pal(9, "GnBu")[c(7:2)]) + 
  coord_flip() +
  theme(
    axis.title = element_text(size = 15, face = "plain", color = "black"), 
    axis.text = element_text(size = 12, face = "plain", color = "black"), 
    legend.title = element_text(size = 14, face = "plain", color = "black"), 
    legend.position = "right"
  )

6. 不等宽条形图

# 读取绘图数据
mydata <- data.frame(Name=paste0("Project", 1:5), 
                     Scale=c(35, 30, 20, 10, 5), 
                     ARPU=c(56, 37, 63, 57, 59))
mydata$xmin <- 0
# 构造每个柱子的起点
for (i in 2:5){
  mydata$xmin[i] <- sum(mydata$Scale[1:i-1])
}
# 构造每个柱子的终点
for (i in 1:5){
  mydata$xmax[i] <- sum(mydata$Scale[1:i])
}
# 构造标签的位置
for (i in 1:5){
  mydata$label[i] <- sum(mydata$Scale[1:i]) - mydata$Scale[i]/2
}

ggplot(mydata) + 
  geom_rect(aes(xmin = xmin, xmax = xmax, ymin = 0, ymax = ARPU, fill = Name),
            colour = "black", size = 0.25) + 
  geom_text(aes(x = label, y = ARPU+3, label = ARPU), size = 4, col = "black") + 
  geom_text(aes(x = label, y = -7, label = Name), size = 3, col = "black", angle = 90) + 
  ylab("ARPU") + 
  xlab("scale") + 
  ylim(-10, 80) + 
  theme(
    panel.background = element_rect(fill = "white", colour = NA), 
    panel.grid.major = element_line(colour = "grey60", size = .25, linetype = "dotted"),
    panel.grid.minor = element_line(colour = "grey60", size = .25, linetype = "dotted"), 
    text = element_text(size = 15), 
    plot.title = element_text(size = 15, hjust = .5), 
    legend.position = "none"
  )

7. 克利夫兰点图

mydata <- read.csv("配套资源/第3章_类别比较型图表/DotPlots_Data.csv", 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
mydata$sum <- rowSums(mydata[, 2:3])
mydata$City <- factor(mydata$City, 
                      levels = mydata$City[order(mydata$sum)])
ggplot(mydata, aes(sum, City)) + 
  geom_point(shape = 21, size = 3, colour = "black", fill = "#FC4E07") + 
  theme(
    axis.title = element_text(size = 13, face = "plain", color = "black"), 
    axis.text = element_text(size = 10, face = "plain", color = "black"), 
    legend.title = element_text(size = 14, face = "plain", color = "black")
  )

8. 棒棒糖图

mydata <- read.csv("配套资源/第3章_类别比较型图表/DotPlots_Data.csv", 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
mydata$sum <- rowSums(mydata[, 2:3])
mydata$City <- factor(mydata$City, levels = mydata$City[order(mydata$sum)])
ggplot(mydata, aes(sum, City)) + 
  geom_segment(aes(x=0, xend=sum, y = City, yend = City)) + 
  geom_point(shape = 21, size = 3, colour = "black", fill = "#FC4E07") + 
  theme(
    axis.title = element_text(size = 13, face = "plain", color = "black"), 
    axis.text = element_text(size = 10, face = "plain", color = "black"), 
    legend.title = element_text(size = 14, face = "plain", color = "black")
  )

9. 哑铃图

mydata <- read.csv("配套资源/第3章_类别比较型图表/DotPlots_Data.csv", 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
mydata$City <- factor(mydata$City, levels = mydata$City[order(mydata$Female)])
mydata <- melt(mydata, id.vars = "City")

ggplot(mydata, aes(value, City, fill = variable)) + 
  geom_line(aes(group = City)) + 
  geom_point(shape = 21, size = 3, colour = "black") + 
  scale_fill_manual(values = c("red", "black")) + 
  theme(
    axis.title = element_text(size = 13, face = "plain", color = "black"), 
    axis.text = element_text(size = 10, face = "plain", color = "black"), 
    legend.title = element_text(size = 12, face = "plain", color = "black"), 
    legend.background = element_blank(), 
    legend.position = c(0.85, 0.12)
  )

10. 坡度图

mydata <- read.csv("配套资源/第3章_类别比较型图表/Slopecharts_Data1.csv", 
                   sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
colnames(mydata) <- c("continent", "1952", "1957")
left_label <- paste(mydata$continent, round(mydata$`1952`), sep = ", ")
right_label <- paste(mydata$continent, round(mydata$`1957`),sep=", ")
mydata$class <- ifelse((mydata$`1957` - mydata$`1952`) < 0, "red", "green")

p <- ggplot(mydata) + 
  geom_segment(aes(x=1, xend=2, y=`1952`, yend=`1957`, col=class), size=.75, show.legend=F) +  #连接线
  geom_vline(xintercept=1, linetype="solid", size=.1) + # 1952年的垂直直线
  geom_vline(xintercept=2, linetype="solid", size=.1) + # 1957年的垂直直线
  geom_point(aes(x=1, y=`1952`), size=3,shape=21,fill="grey80",color="black") + # 1952年的数据点
  geom_point(aes(x=2, y=`1957`), size=3,shape=21,fill="grey80",color="black") + # 1957年的数据点
  scale_color_manual(labels = c("Up", "Down"), values = c("green"="#A6D854","red"="#FC4E07")) +  
  xlim(.5, 2.5) 

# 添加文本信息
p <- p + geom_text(label=left_label, y=mydata$`1952`, x=rep(1, NROW(mydata)), hjust=1.1, size=3.5)
p <- p + geom_text(label=right_label, y=mydata$`1957`, x=rep(2, NROW(mydata)), hjust=-0.1, size=3.5)
p <- p + geom_text(label="1952", x=1, y=1.02*(max(mydata$`1952`, mydata$`1957`)), hjust=1.2, size=5)   
p <- p + geom_text(label="1957", x=2, y=1.02*(max(mydata$`1952`, mydata$`1957`)), hjust=-0.1, size=5) 

p<-p+theme_void()
p

11 多年份坡度图

library(ggalt)

## Registered S3 methods overwritten by 'ggalt':
##   method                  from   
##   grid.draw.absoluteGrob  ggplot2
##   grobHeight.absoluteGrob ggplot2
##   grobWidth.absoluteGrob  ggplot2
##   grobX.absoluteGrob      ggplot2
##   grobY.absoluteGrob      ggplot2

# 读取数据

df <- read.csv("配套资源/第3章_类别比较型图表/Slopecharts_Data2.csv")
colnames(df) <- c("continent", 2007:2013)


df2<-melt(df, id="continent")

df2$value<-as.numeric(df2$value)
df2$variable<-as.numeric(df2$variable)

left_label<-paste(df2$continent,  round(df2$value),sep=", ")
right_label<-paste(df2$continent, round(df2$value),sep=", ")

left_point<-df2$value
right_point<-df2$value
class<-df2$variable
  
for (i in 1:nrow(df2))
{
  if (df2$variable[i]!=1)
  {
    left_label[i]<-""
    left_point[i]<-NaN
  }
  if (df2$variable[i]!=7)
  {
    right_label[i]<-""
    right_point[i]<-NaN
  }
  
  if (df[df$continent==df2$continent[i],2]>df[df$continent==df2$continent[i],8])
  {
    class[i]<-"green"
  }
  else
  {
    class[i]<-"red"
  }
  
}

p <- ggplot(df2) + 
  geom_xspline(aes(x=variable, y=value,group=continent, colour=class),size=.75) + 
  geom_vline(xintercept=1, linetype="solid", size=.1) + 
  geom_vline(xintercept=7, linetype="solid", size=.1) +
  geom_point(aes(x=variable, y=left_point), size=3,shape=21,fill="grey80",color="black") + 
  geom_point(aes(x=variable, y=right_point), size=3,shape=21,fill="grey80",color="black") + 
  scale_color_manual(labels = c("Up", "Down"), values = c("green"="#FC4E07",  "red"="#A6D854")) +  
  xlim(-4, 12) 

p <- p + geom_text(label=left_label, y=df2$value, x=rep(1, NROW(df2)), hjust=1.1, size=3.5)
p <- p + geom_text(label=right_label, y=df2$value, x=rep(7, NROW(df2)), hjust=-0.1, size=3.5)
p <- p + geom_text(label="2007", x=1, y=1.02*(max(df2$value)), hjust=1.2, size=5)  # title
p <- p + geom_text(label="2013", x=7, y=1.02*(max(df2$value)), hjust=-0.1, size=5)  # title

p<-p+theme_void()+
  theme(legend.position = "none")
p

12 单数据系列极坐标柱形图

mydata <- data.frame(a=c("Monday","Tuesday","Wednesday","Thursday","Friday","Saturday","Sunday"), b=c(50, 60, 70, 20,90,110,30))
myAngle <- seq(-20, -340, length.out = 7)

ggplot(mydata) + 
  geom_bar(aes(x = a, y = b), width = 1, stat = "identity", 
           colour = "black", fill = "#F8766D") + 
  geom_text(aes(x = a, y = b-8, label = b), color = "white") + 
  coord_polar(theta = "x", start = 0) + 
  ylim(c(0, 120)) + 
  theme_light() + 
  theme(
    panel.background = element_blank(), 
    panel.grid.major = element_line(colour = "grey80", size=.25), 
    axis.text.y = element_text(size = 12, colour = "black"), 
    axis.line.y = element_line(size = 0.25), 
    axis.text.x = element_text(size = 13, colour = "black", angle = myAngle)
  )

13 多数据系列极坐标柱形图

df <- data.frame(item = rep(LETTERS[1:10], 5), # LETTERS 表示 26 个大写字母
                 score = rep(letters[1:5], each = 10), #letters 表示小写字母
                 value = rep((1:5), each = 10) + rnorm(50, 0, 0.5))
myAng <- seq(-20, -340, length.out = 10)

ggplot(df, aes(item, value, fill = score)) + 
  geom_bar(stat = "identity", color = "black", position = position_dodge(), 
           width = 0.7, size = 0.25) + 
  coord_polar(theta = "x", start = 0) + 
  ylim(c(-3, 6)) + # 控制极坐标显示半径
  scale_fill_brewer(palette = "YlGnBu") + # 使用调色板调色
  theme_light() + # 设置主题线为灰色
  theme(
    panel.background = element_blank(),
    panel.grid.major = element_line(color = "grey80", size = .25), 
    axis.text.y = element_text(size = 12, color = "black"), 
    axis.line.y = element_line(size = 0.25), 
    axis.text.x = element_text(size = 13, colour = "black", angle = myAng)
  )

14. 极坐标跨度图

ggplot2 提供了线性范围函数：geom_linerange(), 主要包括三个参数（x, ymin, ymax）

library(viridis)

df <- read.csv("配套资源/第3章_类别比较型图表/PloarRange_Data.csv", 
               sep = ",", na.strings = "NA", stringsAsFactors = FALSE)
df$date <- as.Date(df$date)
myAngle <- seq(-20, -340, length.out = 12)

ggplot(df, aes(date, 
               ymin = min.temperaturec, 
               ymax = max.temperaturec, 
               color = mean.temperaturec)) + 
  geom_linerange() + 
  scale_color_viridis("Temperature", option = "D") +  # 为连续变量付颜色
  ylim(-10, 35) + 
  coord_polar() + 
  theme_light() + 
  scale_x_date(date_breaks = "month", date_labels = "%m") +  # 设置坐标轴标签为月份
  theme(panel.background = element_blank(), 
        panel.grid.major = element_line(color = "grey80", size = .25), 
        axis.text.y = element_text(size = 12, color = "black"), 
        axis.line.y = element_line(size = .25), 
        axis.text.x = element_text(size = 13, color = "black", angle = myAngle))

15. 雷达图

mydata <- data.frame(car = c("Math", "English", "Biology", "Music", "R-Coding"), 
                     value = c(12,2,14,20,18), id = c(1:5))
ggplot(mydata, aes(x = id, y = value)) + 
  geom_polygon(color = "black", fill = brewer.pal(7, "Set1")[3], alpha = 0.1) + 
  geom_point(size = 5, shape = 21, color = "black", fill = brewer.pal(7, "Set1")[1]) +
  coord_polar()

label_data<-data.frame(
  car=c("biology" , "english" ,"math" ,  "music" , "R-coding" ),
  id=c(1:5) ,
  v1=sample( 0:20,5, replace=T),
  v2=sample( 0:20,5, replace=T)
)

AddRow<-c(NA,nrow(label_data)+1,label_data[1,ncol(label_data)-1],label_data[1,ncol(label_data)])
mydata<-rbind(label_data,AddRow)

myAngle<- 360- 360 * (label_data$id-1) /nrow(label_data)  

mydata<-melt(mydata,id=c("car", "id"))

ggplot(data=mydata,aes(x=id, y=value,group=variable,fill=variable)) + 
  geom_polygon(colour="black",alpha=0.1)+
  geom_point(size=4,shape=21,color = 'black')+
  #coord_radar()+
  coord_polar() +
  scale_x_continuous(breaks =label_data$id,labels=label_data$car)+
  theme_bw() +
  ylim(0,22)+
  theme(axis.text.x=element_text(size = 11,colour="black",angle = myAngle),
        axis.title=element_text(size=15,face="plain",color="black"),
        axis.text = element_text(size=12,face="plain",color="black"),
        panel.grid.major = element_line(color="grey80"),
        axis.line = element_line(color="black"),
        axis.ticks =  element_line(color="black"))