点击关注，桓峰基因
桓峰基因公众号推出基于R语言绘图教程并配有视频在线教程，目前整理出来的教程目录如下：
FigDraw 1. SCI 文章的灵魂 之 简约优雅的图表配色
FigDraw 2. SCI 文章绘图必备 R 语言基础
FigDraw 3. SCI 文章绘图必备 R 数据转换
FigDraw 4. SCI 文章绘图之散点图 (Scatter)
FigDraw 5. SCI 文章绘图之柱状图 (Barplot)
FigDraw 6. SCI 文章绘图之箱线图 (Boxplot)
FigDraw 7. SCI 文章绘图之折线图 (Lineplot)
FigDraw 8. SCI 文章绘图之饼图 (Pieplot)
FigDraw 9. SCI 文章绘图之韦恩图 (Vennplot)
FigDraw 10. SCI 文章绘图之直方图 (HistogramPlot)
FigDraw 11. SCI 文章绘图之小提琴图 (ViolinPlot)
FigDraw 12. SCI 文章绘图之相关性矩阵图(Correlation Matrix)
FigDraw 13. SCI 文章绘图之桑葚图及文章复现(Sankey)
FigDraw 14. SCI 文章绘图之和弦图及文章复现（Chord Diagram)
FigDraw 15. SCI 文章绘图之多组学圈图(OmicCircos)
FigDraw 16. SCI 文章绘图之树形图(Dendrogram)
FigDraw 17. SCI 文章绘图之主成分绘图(pca3d)
FigDraw 18. SCI 文章绘图之矩形树状图 (treemap)
FigDraw 19. SCI 文章中绘图之坡度图(Slope Chart)
FigDraw 20. SCI文章中绘图之马赛克图 (mosaic)
FigDraw 21. SCI文章中绘图之三维散点图 (plot3D)
FigDraw 22. SCI文章中绘图之核密度及山峦图 (ggridges)
前 言
核密度估计图 (kernel density plot)用干显示数据在X轴连续数据段内的分布状况。这种图表是直方图的变种，使用平滑曲线来绘制水平数值，从而得出更平滑的分布。核密度估计图比直方图优胜的地方，在于它们不受所使用分组数量的影响，所以能更好地界定分布形状。核密度估计（kernel density estimation)是在概率论中用来估计未知的密度函数，属于非参数检验方法之一，由Rosenblatt(1955)和Emanuel Parzen( 1962)提出，又名 Parzen窗(Parzen window ).所谓核密度估计，就是采用平滑的峰值函数（核)来拟合观察到的数据点，从而对真实的概率分布曲线进行模拟。核密度估计，是一种用于估计概率密度函数的非参数方法
软件包安装
一般密度图我们使用ggplot2 中的 geom_density()函数就可以实现，另外我们可以利用核密度估计的思想绘制山峦图，其实也就是数据的组合，使用 ggridges 软件包，下载安装如下：
if(!require(ggridges))
install.packages("ggridges")实例操作
核密度估计图
一般核密度图绘制：
library(ggplot2)
ggplot(diamonds, aes(carat)) + geom_density() + theme_bw()添加颜色并修改X轴范围：
ggplot(diamonds, aes(depth, colour = cut)) + geom_density() + theme_bw() + xlim(55,
70)使用填充色并增加分组信息及设置透明度：
ggplot(diamonds, aes(depth, fill = cut, colour = cut)) + geom_density(alpha = 0.1) +
theme_bw()+xlim(55, 70)核密度估计山峦图
山脊线图是部分重叠的线图，形成山脉的印象。它们对于可视化随时间或空间的分布变化非常有用。
一般山峦图绘制
library(ggplot2)
library(ggridges)
library(RColorBrewer)
# set the `rel_min_height` argument to remove tails
ggplot(iris, aes(x = Sepal.Length, y = Species)) + geom_density_ridges(rel_min_height = 0.005) +
scale_y_discrete(expand = c(0.01, 0)) + scale_x_continuous(expand = c(0.01, 0)) +
theme_ridges()设置“比例尺”来确定这些图之间有多少重叠
# set the `scale` to determine how much overlap there is among the plots
ggplot(diamonds, aes(x = price, y = cut)) + geom_density_ridges(scale = 4) + scale_y_discrete(expand = c(0.01,
0)) + scale_x_continuous(expand = c(0.01, 0)) + theme_ridges()相同的图使用颜色，并使用ggplot2密度属性
# the same figure with colors, and using the ggplot2 density stat
ggplot(diamonds, aes(x = price, y = cut, fill = cut, height = ..density..)) + geom_density_ridges(scale = 4,
stat = "density") + scale_y_discrete(expand = c(0.01, 0)) + scale_x_continuous(expand = c(0.01,
0)) + scale_fill_brewer(palette = 4) + theme_ridges() + theme(legend.position = "none")对于实体多边形，使用geom_density_ridges2()而不是geom_density_脊()
# use geom_density_ridges2() instead of geom_density_ridges() for solid
# polygons
ggplot(iris, aes(x = Sepal.Length, y = Species)) + geom_density_ridges2() + scale_y_discrete(expand = c(0.01,
0)) + scale_x_continuous(expand = c(0.01, 0)) + theme_ridges()一般需要设置“扩展”选项，coord_cartesian()避免修剪山脊线的最顶端
ggplot(diamonds, aes(x = price, y = cut)) +
geom_density_ridges(scale = 4) +
scale_y_discrete(expand = c(0, 0)) + # will generally have to set the `expand` option
scale_x_continuous(expand = c(0, 0)) + # for both axes to remove unneeded padding
coord_cartesian(clip = "off") + # to avoid clipping of the very top of the top ridgeline
theme_ridges()修改带宽
# > Picking joint bandwidth of 458
ggplot(lincoln_weather, aes(x = `Mean Temperature [F]`, y = Month, fill = ..density..)) +
geom_density_ridges_gradient(scale = 3, rel_min_height = 0, size = 0.3) + scale_fill_gradientn(colours = colorRampPalette(rev(brewer.pal(11,
"Spectral")))(32))修改颜色
ggplot(lincoln_weather, aes(x = `Mean Temperature [F]`, y = Month, fill = stat(x))) +
geom_density_ridges_gradient(scale = 3, rel_min_height = 0.01) + scale_fill_viridis_c(name = "Temp. [F]",
option = "C") + labs(title = "Temperatures in Lincoln NE in 2016")分位数线和用分位数或概率着色
# Quantile lines and coloring by quantiles or probabilities
ggplot(iris, aes(x = Sepal.Length, y = Species)) + stat_density_ridges(quantile_lines = TRUE)我们也可以通过切点而不是数字来指定分位数。例如，我们可以表示2.5%和97.5%的尾。
ggplot(iris, aes(x = Sepal.Length, y = Species)) + stat_density_ridges(quantile_lines = TRUE,
quantiles = c(0.025, 0.975), alpha = 0.7)使用geom geom_density_ridges_gradient，我们也可以通过计算的统计(分位数)美学按分位数着色。注意，只有当calc_ecdf = TRUE时才会计算此美观值。
ggplot(iris, aes(x = Sepal.Length, y = Species, fill = factor(stat(quantile)))) +
stat_density_ridges(geom = "density_ridges_gradient", calc_ecdf = TRUE, quantiles = 4,
quantile_lines = TRUE) + scale_fill_viridis_d(name = "Quartiles")我们可以使用相同的方法来突出显示分布的尾部。
ggplot(iris, aes(x = Sepal.Length, y = Species, fill = factor(stat(quantile)))) +
stat_density_ridges(geom = "density_ridges_gradient", calc_ecdf = TRUE, quantiles = c(0.025,
0.975)) + scale_fill_manual(name = "Probability", values = c("#FF0000A0",
"#A0A0A0A0", "#0000FFA0"), labels = c("(0, 0.025]", "(0.025, 0.975]", "(0.975, 1]"))最后，当calc_ecdf = TRUE时，我们还可以获得一个计算的美学属性(ecdf)，它表示分布的经验累积密度函数。这使得我们可以将概率直接映射到颜色上。
ggplot(iris, aes(x = Sepal.Length, y = Species, fill = 0.5 - abs(0.5 - stat(ecdf)))) +
stat_density_ridges(geom = "density_ridges_gradient", calc_ecdf = TRUE) + scale_fill_viridis_c(name = "Tail probability",
direction = -1)增加抖动点：stat_density_ridges还提供了可视化生成分布的原始数据点的选项。这可以通过在geom_density_ridges或geom_density_ridges中设置jittered_points = TRUE来实现:
ggplot(iris, aes(x = Sepal.Length, y = Species)) + geom_density_ridges(jittered_points = TRUE)在显示点的位置可以通过位置选项进行控制，例如，“raincloud”用于雨云效果:
ggplot(iris, aes(x = Sepal.Length, y = Species)) + geom_density_ridges(jittered_points = TRUE,
position = "raincloud", alpha = 0.7, scale = 0.9)我们还可以模拟rug:
ggplot(iris, aes(x = Sepal.Length, y = Species)) + geom_density_ridges(jittered_points = TRUE,
position = position_points_jitter(width = 0.05, height = 0), point_shape = "|",
point_size = 3, point_alpha = 1, alpha = 0.7, )注意，我们在这里使用的是position_points_jitter()，而不是position_jitter()。我们这样做是因为position_points_jitter()知道只抖动脊线图中的点，而不触及密度线。造型抖动点有点棘手，但是可能的特殊规模提供的ggridge。首先，scale_discrete_manual()可以用于为任意美学制作任意的离散尺度。在下一个示例中，我们将使用它来设置点形状的样式。其次，有各种各样的点美学尺度，如scale_point_color_hue()。
ggplot(iris, aes(x = Sepal.Length, y = Species, fill = Species)) + geom_density_ridges(aes(point_color = Species,
point_fill = Species, point_shape = Species), alpha = 0.2, point_alpha = 1, jittered_points = TRUE) +
scale_point_color_hue(l = 40) + scale_discrete_manual(aesthetics = "point_shape",
values = c(21, 22, 23))所有常见的点美学都可以应用于抖动点。然而，美学名称以point_开头。在下一个示例中，我们将一个附加变量映射到点的大小上。
ggplot(iris, aes(x = Sepal.Length, y = Species, fill = Species)) + geom_density_ridges(aes(point_shape = Species,
point_fill = Species, point_size = Petal.Length), alpha = 0.2, point_alpha = 1,
jittered_points = TRUE) + scale_point_color_hue(l = 40) + scale_point_size_continuous(range = c(0.5,
4)) + scale_discrete_manual(aesthetics = "point_shape", values = c(21, 22, 23))类似地，我们有垂直线 vline_size。垂直线也可以移动，这样它们就和抖动点对齐了。这允许我们生成如下的数字:
ggplot(iris, aes(x = Sepal.Length, y = Species)) + geom_density_ridges(jittered_points = TRUE,
quantile_lines = TRUE, scale = 0.9, alpha = 0.7, vline_size = 1, vline_color = "red",
point_size = 0.4, point_alpha = 1, position = position_raincloud(adjust_vlines = TRUE))澳大利亚运动员的身高
ggplot(Aus_athletes, aes(x = height, y = sport, color = sex, point_color = sex, fill = sex)) +
geom_density_ridges(jittered_points = TRUE, scale = 0.95, rel_min_height = 0.01,
point_shape = "|", point_size = 3, size = 0.25, position = position_points_jitter(height = 0)) +
scale_y_discrete(expand = c(0, 0)) + scale_x_continuous(expand = c(0, 0), name = "height [cm]") +
scale_fill_manual(values = c("#D55E0050", "#0072B250"), labels = c("female",
"male")) + scale_color_manual(values = c("#D55E00", "#0072B2"), guide = "none") +
scale_discrete_manual("point_color", values = c("#D55E00", "#0072B2"), guide = "none") +
coord_cartesian(clip = "off") + guides(fill = guide_legend(override.aes = list(fill = c("#D55E00A0",
"#0072B2A0"), color = NA, point_color = NA))) + ggtitle("Height in Australian athletes") +
theme_ridges(center = TRUE)软件包里面自带的例子，我这里都展示了一遍为了方便大家选择适合自己的图形，另外需要代码的将这期教程转发朋友圈，并配文“学生信，找桓峰基因，铸造成功的你！”即可获得！
References:
Wilke C (2022). ggridges: Ridgeline Plots in 'ggplot2'. R package version 0.5.4, https://wilkelab.org/ggridges/.
本文使用 文章同步助手 同步