R语言ggplot2一幅好看的频率分布直方图实例

推文内容来自于链接

https://www.andrewheiss.com/blog/2021/12/18/bayesian-propensity-scores-weights/

这个博文里的内容还挺多的，我们只关注其中关于频率分布直方图的实现代码。

读取数据集

nets_with_weights<-read.csv("nets_with_weights.csv")

准备作图配色

isfahan <- MetBrewer::met.brewer("Isfahan1")
length(isfahan)
isfahan[1]

image.png

这里用到的配色包是 https://github.com/BlakeRMills/MetBrewer 这个用到的都是博物馆里的油画的配色，挺有意思的，大家可以试试

使用ggplot2作图

这里频率分布直方图用到的是geom_histogram()函数，这里的代码多了一个weight参数，暂时没有想明白这个参数起到什么作用

还遇到一个新函数colorspace::lighten()操作颜色，看帮助文档是是颜色更亮。做一个散点图试试效果

library(ggplot2)
library(patchwork)

p1<-ggplot()+
  geom_point(aes(x=1,y=1),size=50,color="darkgreen")

p2<-ggplot()+
  geom_point(aes(x=1,y=1),size=50,
             color=colorspace::lighten("darkgreen",0.9))
p1+p2

image.png

频率分布直方图

ggplot() + 
  geom_histogram(data = filter(nets_with_weights, net_num == 1), 
                 bins = 50, 
                 aes(x = propensity, weight = iptw), 
                 fill = colorspace::lighten(isfahan[2], 0.35),
                 color="white")

image.png

如果要倒过来加一个负号就可以了

ggplot() + 
  geom_histogram(data = filter(nets_with_weights, net_num == 1), 
                 bins = 50, 
                 aes(x = propensity, weight = iptw), 
                 fill = colorspace::lighten(isfahan[2], 0.35),
                 color="white")+
  geom_histogram(data = filter(nets_with_weights, net_num == 0), 
                 bins = 50, aes(x = propensity, weight = iptw, 
                                y = -..count..),
                 fill = colorspace::lighten(isfahan[6], 0.35),
                 color="white")

image.png

添加文本注释

ggplot() + 
  geom_histogram(data = filter(nets_with_weights, net_num == 1), 
                 bins = 50, 
                 aes(x = propensity, weight = iptw), 
                 fill = colorspace::lighten(isfahan[2], 0.35),
                 color="white")+
  geom_histogram(data = filter(nets_with_weights, net_num == 0), 
                 bins = 50, aes(x = propensity, weight = iptw, 
                                y = -..count..),
                 fill = colorspace::lighten(isfahan[6], 0.35),
                 color="white")+
  geom_histogram(data = filter(nets_with_weights, net_num == 1), 
                 bins = 50, aes(x = propensity), 
                 fill = isfahan[2],color="white") + 
  geom_histogram(data = filter(nets_with_weights, net_num == 0), 
                 bins = 50, aes(x = propensity, y = -..count..),
                 fill = isfahan[6],
                 color="white")+
  annotate(geom = "label", 
           x = 0.8, y = 70, 
           label = "Treated (actual)",
           fill = isfahan[2], 
           color = "white", hjust = 1) +
  annotate(geom = "label", x = 0.8, 
           y = 90, label = "Treated (IPTW pseudo-population)", 
           fill = colorspace::lighten(isfahan[2], 0.35), 
           color = "white", hjust = 1) +
  annotate(geom = "label", x = 0.8, y = -60, 
           label = "Untreated (actual)", 
           fill = isfahan[6], 
           color = "white", hjust = 1) +
  annotate(geom = "label", 
           x = 0.8, y = -80, 
           label = "Untreated (IPTW pseudo-population)", 
           fill = colorspace::lighten(isfahan[6], 0.35), 
           color = "white", hjust = 1) 

image.png

对细节的一些调整

ggplot() + 
  geom_histogram(data = filter(nets_with_weights, net_num == 1), 
                 bins = 50, 
                 aes(x = propensity, weight = iptw), 
                 fill = colorspace::lighten(isfahan[2], 0.35),
                 color="white")+
  geom_histogram(data = filter(nets_with_weights, net_num == 0), 
                 bins = 50, aes(x = propensity, weight = iptw, 
                                y = -..count..),
                 fill = colorspace::lighten(isfahan[6], 0.35),
                 color="white")+
  geom_histogram(data = filter(nets_with_weights, net_num == 1), 
                 bins = 50, aes(x = propensity), 
                 fill = isfahan[2],color="white") + 
  geom_histogram(data = filter(nets_with_weights, net_num == 0), 
                 bins = 50, aes(x = propensity, y = -..count..),
                 fill = isfahan[6],
                 color="white")+
  annotate(geom = "label", 
           x = 0.8, y = 70, 
           label = "Treated (actual)",
           fill = isfahan[2], 
           color = "white", hjust = 1) +
  annotate(geom = "label", x = 0.8, 
           y = 90, label = "Treated (IPTW pseudo-population)", 
           fill = colorspace::lighten(isfahan[2], 0.35), 
           color = "white", hjust = 1) +
  annotate(geom = "label", x = 0.8, y = -60, 
           label = "Untreated (actual)", 
           fill = isfahan[6], 
           color = "white", hjust = 1) +
  annotate(geom = "label", 
           x = 0.8, y = -80, 
           label = "Untreated (IPTW pseudo-population)", 
           fill = colorspace::lighten(isfahan[6], 0.35), 
           color = "white", hjust = 1) +
  geom_hline(yintercept = 0, color = "white", size = 0.25) +
  scale_y_continuous(label = abs) +
  coord_cartesian(xlim = c(0.1, 0.8), ylim = c(-80, 100)) +
  labs(x = "Propensity", y = "Count")+
  theme_minimal() +
  theme(panel.grid.minor = element_blank(),
        plot.background = element_rect(fill = "white", color = NA),
        plot.title = element_text(face = "bold"),
        axis.title = element_text(face = "bold"),
        strip.text = element_text(face = "bold", size = rel(0.8), hjust = 0),
        strip.background = element_rect(fill = "grey80", color = NA),
        legend.title = element_text(face = "bold"))

image.png

欢迎大家关注我的公众号

小明的数据分析笔记本

小明的数据分析笔记本 公众号 主要分享：1、R语言和python做数据分析和数据可视化的简单小例子；2、园艺植物相关转录组学、基因组学、群体遗传学文献阅读笔记；3、生物信息学入门学习资料及自己的学习笔记！