1. 条形图
1.1 绘制简单条形图
library(ggplot2) library(gcookbook) #数据集 ggplot(pg_mean, aes(x = group, y = weight)) + geom_bar(stat = "identity")
# 没有 Time == 6 BOD
## Time demand ## 1 1 8.3 ## 2 2 10.3 ## 3 3 19.0 ## 4 4 16.0 ## 5 5 15.6 ## 6 7 19.8
# Time 是数值型(连续型)变量 str(BOD)
## 'data.frame': 6 obs. of 2 variables: ## $ Time : num 1 2 3 4 5 7 ## $ demand: num 8.3 10.3 19 16 15.6 19.8 ## - attr(*, "reference")= chr "A1.4, p. 270"
ggplot(BOD, aes(x = Time, y = demand)) + geom_bar(stat = "identity")
# 使用 factor() 将 Time 转化为离散型(分类) 变量 ggplot(BOD, aes(x = factor(Time), y = demand)) + geom_bar(stat = "identity")
#fill 改变填充颜色 colour 改变边框线颜色 ggplot(pg_mean, aes(x = group, y = weight)) + geom_bar(stat = "identity", fill = "lightblue", colour = "black")
1.2 绘制簇状条形图
library(gcookbook) # For the data set cabbage_exp
## Cultivar Date Weight sd n se ## 1 c39 d16 3.18 0.9566 10 0.30251 ## 2 c39 d20 2.80 0.2789 10 0.08819 ## 3 c39 d21 2.74 0.9834 10 0.31098 ## 4 c52 d16 2.26 0.4452 10 0.14079 ## 5 c52 d20 3.11 0.7909 10 0.25009 ## 6 c52 d21 1.47 0.2111 10 0.06675
# 通过将分类变量映射给fill参数来绘制簇状条形图。使用参数position = "dodge"，使得两组条形在水平方向错开排列，否则会输出堆积条形图。 ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(position = "dodge",stat = "identity")
# colour = "black" 为条形图添加黑色边框线 # scale_fill_brewer()或者scale_fill_manual()函数对图形颜色进行设置 # 这里使用RColorBrewer包的Pastel1调色盘进行调色 ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity"，position = "dodge", colour = "black") + scale_fill_brewer(palette = "Pastel1")
## 如果分类变量有缺失，那么绘图结果中的相应地略去不绘，同时临近的条形会自动的扩充到相应位置。
ce <- cabbage_exp[1:5, ] # 复制删除了最后一行的数据集
> ce Cultivar Date Weight sd n 1 c39 d16 3.18 0.9566144 10 2 c39 d20 2.80 0.2788867 10 3 c39 d21 2.74 0.9834181 10 4 c52 d16 2.26 0.4452215 10 5 c52 d20 3.11 0.7908505 10 se 1 0.30250803 2 0.08819171 3 0.31098410 4 0.14079141 5 0.25008887
ggplot(ce, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity"，position = "dodge", colour = "black") + scale_fill_brewer(palette = "Pastel1")
## 可以在分类变量组合缺失的那一项为变量y手动输入一个NA值，来调整。
1.3 绘制频数条形图
## diamonds 数据集共有53490行数据， 每行数据对应一颗钻石的品质信息 > diamonds # A tibble: 53,940 x 10 carat cut color clarity depth table <dbl> <ord> <ord> <ord> <dbl> <dbl> 1 0.23 Ideal E SI2 61.5 55 2 0.21 Premium E SI1 59.8 61 3 0.23 Good E VS1 56.9 65 4 0.29 Premium I VS2 62.4 58 5 0.31 Good J SI2 63.3 58 6 0.24 Very Good J VVS2 62.8 57 7 0.24 Very Good I VVS1 62.3 57 8 0.26 Very Good H SI1 61.9 55 9 0.22 Fair E VS2 65.1 61 10 0.23 Very Good H VS1 59.4 61 # ... with 53,930 more rows, and 4 more # variables: price <int>, x <dbl>, # y <dbl>, z <dbl>
## geom_bar() 函数在默认情况下将参数设定为 stat="bin",该操作会自动计算每组变量对应的观测数。
ggplot(diamonds, aes(x = cut)) + geom_bar()
## 如果x轴对应的是连续型变量，我们会得到一张直方图。
ggplot(diamonds, aes(x = carat)) + geom_bar()
1.4 条形图着色
library(gcookbook)
## 以uspopchange为例。该数据集描述了美国各州人口自2000至2010年的变化情况。选取人口增长最快的10个州进行绘图。根据地区信息进行着色。 upc <- subset(uspopchange, rank(Change)>40)
> upc State Abb Region Change 3 Arizona AZ West 24.6 6 Colorado CO West 16.9 10 Florida FL South 17.6 11 Georgia GA South 18.3 13 Idaho ID West 21.1 29 Nevada NV West 35.1 34 North Carolina NC South 18.5 41 South Carolina SC South 15.3 44 Texas TX South 20.6 45 Utah UT West 23.8
ggplot(upc, aes(x = Abb, y = Change, fill = Region)) + geom_bar(stat = "identity")
## 使用scale_fill_manual()对颜色进行重新设定
ggplot(upc, aes(x = reorder(Abb, Change), y = Change, fill = Region)) + geom_bar(stat = "identity", colour = "black") + scale_fill_manual(values = c("#669933", "#FFCC66")) + xlab("State")
1.5 对正负条形图分别着色
library(gcookbook) #以climate数据的一个子集为例 csub <- subset(climate, Source == "Berkeley" & Year >= 1900) csub$pos <- csub$Anomaly10y >= 0 head(csub)
> head(csub) Source Year Anomaly1y Anomaly5y 101 Berkeley 1900 NA NA 102 Berkeley 1901 NA NA 103 Berkeley 1902 NA NA 104 Berkeley 1903 NA NA 105 Berkeley 1904 NA NA 106 Berkeley 1905 NA NA Anomaly10y Unc10y pos 101 -0.171 0.108 FALSE 102 -0.162 0.109 FALSE 103 -0.177 0.108 FALSE 104 -0.199 0.104 FALSE 105 -0.223 0.105 FALSE 106 -0.241 0.107 FALSE
ggplot(csub, aes(x = Year, y = Anomaly10y, fill = pos)) + geom_bar(stat = "identity", position = "identity")
## 使用scale_fill_manual()对颜色进行调整，设定参数 guide = FALSE可以删除图例，通过设定边框线colour和size(宽度)，来调整边框。单位是毫米。 ggplot(csub, aes(x = Year, y = Anomaly10y, fill = pos)) + geom_bar(stat = "identity", position = "identity", colour = "black", size = 0.25) + scale_fill_manual(values = c("#CCEEFF", "#FFDDDD"), guide = FALSE)
1.6 调整条形宽度和条形间距
library(gcookbook) # geom_bar()函数的参数 width 可以使条形变得更宽或者更窄，该参数的默认值为0.9 ggplot(pg_mean, aes(x = group, y = weight)) + geom_bar(stat = "identity")
ggplot(pg_mean, aes(x = group, y = weight)) + geom_bar(stat = "identity", width = 0.5)
ggplot(pg_mean, aes(x = group, y = weight)) + geom_bar(stat = "identity", width = 1)
ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity",width = 0.5, position = "dodge")
# 增加组内条形的间距 ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity", width = 0.5, position = position_dodge(0.7))
以下4个命令是等价的：
geom_bar(position = "dodge")
geom_bar(width = 0.9, position = position_dodge())
geom_bar(position = position_dodge(0.9))
geom_bar(width = 0.9, position = position_dodge(width = 0.9))
1.7 绘制堆积条形图
library(gcookbook) ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity")
## 默认的堆积条形图的条形堆积顺序于图例顺序相反，可以通过guides()函数进行调整，并指定图例所需要调整的图形属性。
ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity") + guides(fill = guide_legend(reverse = TRUE))
# 可以通过指定映射中的参数 order = desc()来调整堆叠顺序 library(plyr) # 为了使用desc()函数 ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar, order = desc(Cultivar))) + geom_bar(stat = "identity")
# 使用cale_fill_brewer()调整颜色，设定colour = "black" 为条形添加黑色边框线 ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity", colour = "black") + guides(fill = guide_legend(reverse = TRUE)) + scale_fill_brewer(palette = "Pastel1")
1.8 绘制百分比堆积条形图
## 首先，通过plyr包中的ddply()函数和transform()函数将每组条形对应的数据标准化为
100%格式。之后，针对计算结果绘制堆积条形图即可。 library(gcookbook) library(plyr) ce <- ddply(cabbage_exp, "Date", transform, percent_weight = Weight/sum(Weight) *100) ggplot(ce, aes(x = Date, y = percent_weight, fill = Cultivar)) + geom_bar(stat = "identity")
ggplot(ce, aes(x = Date, y = percent_weight, fill = Cultivar)) + geom_bar(stat = "identity", colour = "black") + guides(fill = guide_legend(reverse = TRUE)) + scale_fill_brewer(palette = "Pastel1")
1.9 添加数据标签
## geom_text()可为条形图添加数据标签 ## 设定 vjust()可以将标签位置移动至条形图顶端的上方或者下方
library(gcookbook) # 在条形图顶端下方 ggplot(cabbage_exp, aes(x = interaction(Date, Cultivar), y = Weight)) + geom_bar(stat = "identity") + geom_text(aes(label = Weight), vjust = 1.5, colour = "white")
# 在条形图顶端上方 ggplot(cabbage_exp, aes(x = interaction(Date, Cultivar), y = Weight)) + geom_bar(stat = "identity") + geom_text(aes(label = Weight), vjust = -0.2)
# 将y轴上限变大 ggplot(cabbage_exp, aes(x = interaction(Date, Cultivar), y = Weight)) + geom_bar(stat = "identity") + geom_text(aes(label = Weight), vjust = -0.2) + ylim(0, max(cabbage_exp$Weight) * 1.05)
# 设定标签的y轴位置 ggplot(cabbage_exp, aes(x = interaction(Date, Cultivar), y = Weight)) + geom_bar(stat = "identity") + geom_text(aes(y = Weight + 0.1, label = Weight))
ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity", position = "dodge") + geom_text(aes(label = Weight), vjust = 1.5, colour = "white", position = position_dodge(0.9), size = 3)
## 向堆积条形图添加数据标签 ## 对每组条形对应的数据进行求和 可以使用plyr包的arrange()函数完成上述操作
library(plyr) # 根据日期和性别对数据进行排序 ce <- arrange(cabbage_exp, Date, Cultivar) # 计算累计和 ce <- ddply(ce, "Date", transform, label_y = cumsum(Weight)) ce
## Cultivar Date Weight sd n se label_y ## 1 c39 d16 3.18 0.9566 10 0.30251 3.18 ## 2 c52 d16 2.26 0.4452 10 0.14079 5.44 ## 3 c39 d20 2.80 0.2789 10 0.08819 2.80 ## 4 c52 d20 3.11 0.7909 10 0.25009 5.91 ## 5 c39 d21 2.74 0.9834 10 0.31098 2.74 ## 6 c52 d21 1.47 0.2111 10 0.06675 4.21
ggplot(ce, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity") + geom_text(aes(y = label_y, label = Weight), vjust = 1.5, colour = "white")
ce <- arrange(cabbage_exp, Date, Cultivar) # 计算y轴位置， 将数据标签置于条形中部 ce <- ddply(ce, "Date", transform, label_y = cumsum(Weight) - 0.5 * Weight) ggplot(ce, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity") + geom_text(aes(y = label_y, label = Weight), colour = "white")
#修饰 #paste()函数在标签后面添加"kg", format()函数 令标签保留两位小数 ggplot(ce, aes(x = Date, y = Weight, fill = Cultivar)) + geom_bar(stat = "identity", colour = "black") + geom_text(aes(y = label_y, label = paste(format(Weight,nsmall = 2), "kg")), size = 4) + guides(fill = guide_legend(reverse = TRUE)) + scale_fill_brewer(palette = "Pastel1")
1.10 绘制 Cleveland 点图
library(gcookbook) tophit <- tophitters2001[1:25, ] # 取出 tophitters 数据集中的前25个数据 ggplot(tophit, aes(x=avg, y=name)) + geom_point()
tophit[, c("name", "lg", "avg")]
## name lg avg ## 1 Larry Walker NL 0.3501 ## 2 Ichiro Suzuki AL 0.3497 ## 3 Jason Giambi AL 0.3423 ## 4 Roberto Alomar AL 0.3357 ## 5 Todd Helton NL 0.3356 ## 6 Moises Alou NL 0.3314 ## 7 Lance Berkman NL 0.3310 ## 8 Bret Boone AL 0.3307 ## 9 Frank Catalanotto AL 0.3305 ## 10 Chipper Jones NL 0.3304 ## 11 Albert Pujols NL 0.3288 ## 12 Barry Bonds NL 0.3277 ## 13 Sammy Sosa NL 0.3276 ## 14 Juan Pierre NL 0.3274 ## 15 Juan Gonzalez AL 0.3252 ## 16 Luis Gonzalez NL 0.3251 ## 17 Rich Aurilia NL 0.3239 ## 18 Paul Lo Duca NL 0.3196 ## 19 Jose Vidro NL 0.3189 ## 20 Alex Rodriguez AL 0.3180 ## 21 Cliff Floyd NL 0.3171 ## 22 Shannon Stewart AL 0.3156 ## 23 Jeff Cirillo NL 0.3125 ## 24 Jeff Conine AL 0.3111 ## 25 Derek Jeter AL 0.3111
# reorder(name, avg)先将 name 转化为因子，然后根据 avg 对其进行排序 ggplot(tophit, aes(x=avg, y=reorder(name, avg))) + geom_point(size=3) + theme_bw() + theme(panel.grid.major.x = element_blank(), panel.grid.minor.x = element_blank(), panel.grid.major.y = element_line(colour="grey60", linetype="dashed"))
# x，y轴互换 ggplot(tophit, aes(x=reorder(name, avg), y=avg)) + geom_point(size=3) + theme_bw() + theme(axis.text.x = element_text(angle=60, hjust=1), panel.grid.major.y = element_blank(), panel.grid.minor.y = element_blank(), panel.grid.major.x = element_line(colour="grey60", linetype="dashed"))
# 对分组变量进行展示 # 提取出 name 变量, 根据 lg 和 avg对其排序 nameorder <- tophit$name[order(tophit$lg, tophit$avg)] # 将 name转化为因子，因子水平与 nameorder 一致 tophit$name <- factor(tophit$name, levels=nameorder) # geom_segment()函数用"以数据点为端点的线段"代替网格线 ggplot(tophit, aes(x=avg, y=name)) + geom_segment(aes(yend=name), xend=0, colour="grey50") + geom_point(size=3, aes(colour=lg)) + scale_colour_brewer(palette="Set1", limits=c("NL","AL")) + theme_bw() + theme(panel.grid.major.y = element_blank(), legend.position=c(1, 0.55), # 将图例放在绘图区域 legend.justification=c(1, 0.5))
#分面展示分组数据 ggplot(tophit, aes(x=avg, y=name)) + geom_segment(aes(yend=name), xend=0, colour="grey50") + geom_point(size=3, aes(colour=lg)) + scale_colour_brewer(palette="Set1", limits=c("NL","AL"), guide=FALSE) + theme_bw() + theme(panel.grid.major.y = element_blank()) + facet_grid(lg ~ ., scales="free_y", space="free_y")
## 要修改分面显示的堆叠顺序 只有通过调整 lg 变量的因子水平来实现
参考书籍
R Graphics Cookbook, 2nd edition.
