gghalves包-你五毛我五毛

庄闪闪

发布于 2021-04-09 11:02:21

1K0

发布于 2021-04-09 11:02:21

介绍

gghalves可以通过ggplot2轻松地编写自己想要的一半一半（half-half plots）的图片。比如：在散点旁边显示箱线图、在小提琴图旁边显示点图。

gghalves[1]将_half_扩展添加到选定的geom。比如：geom_half_violin()函数，相当于geom_violin()函数的变体，该函数主要作用就是展示一半的小提琴图，然后与其他图形组合。还包含以下函数：

geom_half_boxplot
geom_half_violin
geom_half_point

安装

gghalves通过GitHub安装:

if (!require(devtools)) {
    install.packages('devtools')
}
devtools::install_github('erocoar/gghalves')

函数介绍

geom_half_violin(mapping = NULL, data = NULL, stat = "half_ydensity",
  position = "dodge", ..., side = "l", nudge = 0,
  draw_quantiles = NULL, trim = TRUE, scale = "area",
  na.rm = FALSE, show.legend = NA, inherit.aes = TRUE)

其参数包括：翻译来源生信玩家[2]

参数	解释
mapping	通过aes()指定图形属性映射。默认为NULL，使用ggplot()中aes()指定的映射。
data	指定数据框。默认为NULL，使用ggplot()中的数据。
stat	覆盖geom_density()和stat_density()之间的默认连接。
position	位置调整，可以是字符串，默认为"dodge"，也可以是位置调整函数的调用结果。
side	画半小提琴图的一侧。“ l”代表左，“ r”代表右，默认为“ l”。
nudge	在小提琴图和分配给x轴上给定因子的空间中间之间添加空间。
draw_quantiles	如果不是MULL（默认为NULL），在给定的密度估计分位数处绘制水平线。
trim	若为TRUE（默认），将小提琴的尾部修整到数据范围。若为FALSE，不修剪尾巴。
scale	如果为"area"（默认），则所有小提琴都具有相同的面积（修剪尾部之前）。
na.rm	如果为FALSE（默认），则会使用警告删除缺失值。如果为TRUE，则会自动删除缺少的值。
show.legend	逻辑值，默认为NA，若为FALSE，不显示该图层的图例；若为TRUE，则显示该图层的图例。它也可以是带有名称（图形属性）的逻辑向量，用来选择要显示的图形属性。如show.legend = c(size = TRUE,color = FALSE)表示显示size对应的图例，而不显示color对应的图例。
inherit.aes	默认为TRUE，若为FALSE，覆盖ggplot()中aes()默认属性，而不是与他们组合。
geom	覆盖geom_density()和stat_density()之间的默认连接。
bw	要使用的平滑带宽度。如果是数字，则为平滑内核的标准差。
adjust	多次带宽调整。这使得可以在仍使用带宽估计器的情况下调整带宽。例如，adjust = 1/2表示使用默认带宽的一半。

示例

单个函数

我们以iris数据集作为本例数据，先使用单个函数进行绘制。

if (!require(devtools)) {
	install.packages('devtools')
}
devtools::install_github('erocoar/gghalves')

geom_half_boxplot

library(gghalves)

ggplot(iris, aes(x = Species, y = Petal.Width, fill = Species)) + 
	geom_half_boxplot()

默认为箱子在右，使用center = TRUE将箱子居中。下面函数参数调整类似，就不再绘制结果了，就把最原始的进行展示。

ggplot(iris, aes(x = Species, y = Petal.Width, fill = Species)) + 
	geom_half_boxplot(center = TRUE)

geom_half_violin

ggplot(iris, aes(x = Species, y = Petal.Width, fill = Species)) + 
	geom_half_violin()

geom_half_point

ggplot(iris, aes(x = Species, y = Petal.Width, fill = Species)) + 
	geom_half_point()

综合案例

云雨图

该案例来自官网案例，但并没有对代码进行解释。这里小编对代码进行详细解释，喜欢的伙伴，可以按照解释自己理解，并用到自己实际所需的复合图中。

先将数据的统计摘要进行计算存到了summ_iris中，包含了均值，标准差，数量标准误差。iris_plot为所需数据，这里将Species变量设置为因子，因为要用它作为分类变量。

library(tidyverse)
# 统计摘要
summ_iris <- iris %>% 
	group_by(Species) %>% 
	summarise(
		mean = mean(Sepal.Length),
		sd = sd(Sepal.Length),
		n = n()
	) %>% 
	mutate(se = sd/sqrt(n),
				 Species = factor(Species, levels = c('versicolor', 'setosa', 'virginica')))
summ_iris

## # A tibble: 3 x 5
##   Species     mean    sd     n     se
##   <fct>      <dbl> <dbl> <int>  <dbl>
## 1 setosa      5.01 0.352    50 0.0498
## 2 versicolor  5.94 0.516    50 0.0730
## 3 virginica   6.59 0.636    50 0.0899


# 数据转换  
iris_plot <- iris %>% 
	mutate(Species = factor(Species, levels = c('versicolor', 'setosa', 'virginica')))
head(iris_plot)

接下来进行绘图，我们想要得到Species与Sepal.Length的关系，其中Species为离散变量，Sepal.Length为连续变量。并绘制了半边的小提琴图，并将该图往右移了0.15，上下位置不变（position_nudge(x = .15, y = 0)），为了后面绘制其他图形留位置。

library(gghalves)
library(ggsignif)
library(ggsci)
library(ggpubr)
ggplot(iris_plot , aes(x = Species, y = Sepal.Length, fill = Species))+
	geom_half_violin(aes(fill = Species),
									 position = position_nudge(x = .15, y = 0),
									  side = 'r')

接下来加入散点图，并使x坐标往左移动0.1（x = as.numeric(Species)-0.1），使用position_jitter使得重复的点分散开。

ggplot(iris_plot , aes(x = Species, y = Sepal.Length, fill = Species))+
	geom_half_violin(aes(fill = Species),
									 position = position_nudge(x = .15, y = 0),
									 side = 'r') +
	geom_point(aes(x = as.numeric(Species)-0.1,
								 y = Sepal.Length,color = Species),
						 position = position_jitter(width = .05),size = .25, shape = 20)

在原来基础上加入箱子图，位置放在正中间

ggplot(iris_plot , aes(x = Species, y = Sepal.Length, fill = Species))+
	geom_half_violin(aes(fill = Species),
									 position = position_nudge(x = .15, y = 0),
									 adjust=1.5, trim=FALSE, colour=NA, side = 'r') +
	geom_point(aes(x = as.numeric(Species)-0.1,
								 y = Sepal.Length,color = Species),
						 position = position_jitter(width = .05),size = .25, shape = 20) +
	geom_boxplot(aes(x = Species,y = Sepal.Length, fill = Species),
							 outlier.shape = NA,
							 width = .05,
							 color = "black")

这里比较有趣的是，作者还通过geom_point和geom_errorbar加入和汇总信息以及对应的误差项。

ggplot(iris_plot , aes(x = Species, y = Sepal.Length, fill = Species))+
	geom_half_violin(aes(fill = Species),
									 position = position_nudge(x = .15, y = 0),
									 adjust=1.5, trim=FALSE, colour=NA, side = 'r') +
	geom_point(aes(x = as.numeric(Species)-0.1,
								 y = Sepal.Length,color = Species),
						 position = position_jitter(width = .05),size = .25, shape = 20) +
	geom_boxplot(aes(x = Species,y = Sepal.Length, fill = Species),
							 outlier.shape = NA,
							 width = .05,
							 color = "black")+
	geom_point(data=summ_iris,
						 aes(x=Species,y = mean,group = Species, color = Species),
						 shape=18,
						 size = 1.5,
						 position = position_nudge(x = .1,y = 0)) +
	geom_errorbar(data = summ_iris,
								aes(x = Species, y = mean, group = Species, colour = Species,
										ymin = mean-se, ymax = mean+se),
								width=.05,
								position=position_nudge(x = .1, y = 0)
	)

使用ggsci包的scale_color_aaas(),scale_fill_aaas()将尺度的颜色进行改变（非常好用！)在下面展示另外一种配色（scale_color_jco）

ggplot(iris_plot , aes(x = Species, y = Sepal.Length, fill = Species))+
	geom_half_violin(aes(fill = Species),
									 position = position_nudge(x = .15, y = 0),
									 adjust=1.5, trim=FALSE, colour=NA, side = 'r') +
	geom_point(aes(x = as.numeric(Species)-0.1,
								 y = Sepal.Length,color = Species),
						 position = position_jitter(width = .05),size = .25, shape = 20) +
	geom_boxplot(aes(x = Species,y = Sepal.Length, fill = Species),
							 outlier.shape = NA,
							 width = .05,
							 color = "black")+
	geom_point(data=summ_iris,
						 aes(x=Species,y = mean,group = Species, color = Species),
						 shape=18,
						 size = 1.5,
						 position = position_nudge(x = .1,y = 0)) +
	geom_errorbar(data = summ_iris,
								aes(x = Species, y = mean, group = Species, colour = Species,
										ymin = mean-se, ymax = mean+se),
								width=.05,
								position=position_nudge(x = .1, y = 0)
	) +
	scale_color_aaas() +
	scale_fill_aaas()

最后使用ggpubr包的geom_signif加入显著性结果，ggsave保存图片。

# 绘图
ggplot(iris_plot , aes(x = Species, y = Sepal.Length, fill = Species))+
	geom_half_violin(aes(fill = Species),
									 position = position_nudge(x = .15, y = 0),
									 adjust=1.5, trim=FALSE, colour=NA, side = 'r') +
	geom_point(aes(x = as.numeric(Species)-0.1,
								 y = Sepal.Length,color = Species),
						 position = position_jitter(width = .05),size = .25, shape = 20) +
	geom_boxplot(aes(x = Species,y = Sepal.Length, fill = Species),
							 outlier.shape = NA,
							 width = .05,
							 color = "black")+
	geom_point(data=summ_iris,
						 aes(x=Species,y = mean,group = Species, color = Species),
						 shape=18,
						 size = 1.5,
						 position = position_nudge(x = .1,y = 0)) +
	geom_errorbar(data = summ_iris,
								aes(x = Species, y = mean, group = Species, colour = Species,
										ymin = mean-se, ymax = mean+se),
								width=.05,
								position=position_nudge(x = .1, y = 0)
	) +
	scale_color_jco() +
	scale_fill_jco() +
	geom_signif(comparisons = list(c("versicolor", "setosa"),
																 c("versicolor", "virginica"),
																 c("setosa", "virginica")),
							y_position = c(8.2, 8.6, 8.4),
							map_signif_level = c("***" = 0.001, "**" = 0.01, "*" = 0.05)) +
	ggsave('云雨图.pdf', width = 6, height = 8)

混合图

最后是混合图，根据自己想要的图，可以自行添加。相信这个代码简单的图给大家学术作图上省了不少时间。

library(tidyverse)
ggplot() +
	geom_half_boxplot(
		data = iris %>% filter(Species=="setosa"), 
		aes(x = Species, y = Sepal.Length, fill = Species), outlier.color = NA) +
	ggbeeswarm::geom_beeswarm(
		data = iris %>% filter(Species=="setosa"),
		aes(x = Species, y = Sepal.Length, fill = Species, color = Species), beeswarmArgs=list(side=+1)
	) +
	geom_half_violin(
		data = iris %>% filter(Species=="versicolor"), 
		aes(x = Species, y = Sepal.Length, fill = Species), side="r") +
	geom_half_dotplot(
		data = iris %>% filter(Species=="versicolor"), 
		aes(x = Species, y = Sepal.Length, fill = Species), method="histodot", stackdir="down") +
	geom_half_boxplot(
		data = iris %>% filter(Species=="virginica"), 
		aes(x = Species, y = Sepal.Length, fill = Species), side = "r", errorbar.draw = TRUE,
		outlier.color = NA) +
	geom_half_point(
		data = iris %>% filter(Species=="virginica"), 
		aes(x = Species, y = Sepal.Length, fill = Species, color = Species), side = "l") +
	scale_fill_manual(values = c("setosa" = "#cba1d2", "versicolor"="#7067CF","virginica"="#B7C0EE")) +
	scale_color_manual(values = c("setosa" = "#cba1d2", "versicolor"="#7067CF","virginica"="#B7C0EE")) +
	theme(legend.position = "none") +	
	ggsave('综合图.pdf', width = 6, height = 8)