R 逐ggplot在密度图中添加部分数据

我有一个文件有两个不同的类别，其中大多数都在一个类别中。这些类别是：

in

和

out

file1_ggplot.txt

status scores
in     44
in     55
out    12
out    23
out    99
out    13

为了绘制密度分布，我使用了这段代码，但我想添加一个类别的摘要以及在中带有has

的行：

library(data.table)
library(ggplot2)
library(plyr)
filenames <- list.files("./scores",pattern="*ggplot.txt", full.names=TRUE)
pdf("plot.pdf")
for(file in filenames){
     library(tools)
     bases <- file_path_sans_ext(file)
     data1 <- fread(file)
     cdat <- ddply(data1, "status", summarise, scores.mean=mean(scores))
     data1ggplot <- ggplot(data1, aes(x=scores, colour=status)) + geom_density() + geom_vline(data=cdat, aes(xintercept=scores.mean, colour=status), linetype="dashed", size=1)
     print(data1ggplot + ggtitle(basename(bases)))

    }
dev.off()

以及

为此，我尝试使用
表grob
：

data1ggplot <- ggplot(data1, aes(x=scores, colour=status)) + geom_density() + geom_vline(data=cdat, aes(xintercept=scores.mean, colour=status), linetype="dashed", size=1) +  annotation_custom(tableGrob(summary(data1$scores))

然后在
R
中：

data2<-fread("only-in.txt")

trs <- as.data.frame(t(data2))
trs
       V1 V2
    V1 in in
    V2 44 55
data1ggplot <- ggplot(data1, aes(x=scores, colour=status)) + geom_density() + geom_vline(data=cdat, aes(xintercept=scores.mean, colour=status), linetype="dashed", size=1) +  annotation_custom(tableGrob(trs))

data2这里有一个解决方案，假设您想要的表的格式：


单个绘图

library(tidyverse)
library(gridExtra) # tableGrob
library(broom) # glance

df_summary <- t(broom::glance(summary(data1$scores)))
data1 %>%
  ggplot(., aes(x = scores, colour = status)) + 
  geom_density() + 
  geom_vline(data = . %>% 
               group_by(status) %>%
               summarise(scores.mean = mean(scores)), 
             aes(xintercept = scores.mean, colour = status), 
             linetype = "dashed", 
             size = 1) +
  annotation_custom(tableGrob(rbind(data.frame(data1 %>% filter(status == "in") %>% rename(var = status, val = scores)),
                                    data.frame(var = row.names(df_summary), val = df_summary, row.names = NULL)), 
                                    rows = NULL, cols = NULL),
                    xmin = 60, xmax = 100,
                    ymin = 0.1, ymax = 0.4)

现在应该有一个“plot.pdf”文件，每个plot有3页

请注意，您应该根据您的日期调整
表格GROB的位置，我不知道将表格放在哪里，您也可以根据汇总值计算位置。
您能否提供一个可复制的示例，使用最小的数据集，请参见：但我已经做了..？数据集在这里，但这个例子目前还无法重现。顺便说一句，我需要对这里的
文件名进行一些修改，我不清楚您想要的输出，一个在
和
摘要中包含
的表，其中包含摘要的图例@bVa
/scores
是您为
ggplot
放置输入文件的目录（在本例中为
file1\u ggplot.txt
）。是的！ggplot中的行在
中有
，并且
摘要
它抱怨此错误：
attr（数据，“tsp”）中有错误问题可能与数据的格式有关。不幸的是，如果没有关于错误的更多信息（测试的代码、产生错误的行、使用的数据等等），就很难提供帮助。
cat file1_ggplot.txt | grep -w "in" > only-in.txt

data2<-fread("only-in.txt")

trs <- as.data.frame(t(data2))
trs
       V1 V2
    V1 in in
    V2 44 55
data1ggplot <- ggplot(data1, aes(x=scores, colour=status)) + geom_density() + geom_vline(data=cdat, aes(xintercept=scores.mean, colour=status), linetype="dashed", size=1) +  annotation_custom(tableGrob(trs))

library(tidyverse)
library(gridExtra) # tableGrob
library(broom) # glance

df_summary <- t(broom::glance(summary(data1$scores)))
data1 %>%
  ggplot(., aes(x = scores, colour = status)) + 
  geom_density() + 
  geom_vline(data = . %>% 
               group_by(status) %>%
               summarise(scores.mean = mean(scores)), 
             aes(xintercept = scores.mean, colour = status), 
             linetype = "dashed", 
             size = 1) +
  annotation_custom(tableGrob(rbind(data.frame(data1 %>% filter(status == "in") %>% rename(var = status, val = scores)),
                                    data.frame(var = row.names(df_summary), val = df_summary, row.names = NULL)), 
                                    rows = NULL, cols = NULL),
                    xmin = 60, xmax = 100,
                    ymin = 0.1, ymax = 0.4)

# Mock data
set.seed(1)
data_list = list(data1, 
                 data.frame(status = data1$status, scores = c(40, 60, 15, 21, 97, 10)),
                 data.frame(status = data1$status, scores = c(45, 56, 11, 25, 95, 14)))

# Create a function 

your_function <- function(df) {
  df_summary <- t(broom::glance(summary(df$scores)))
  df %>%
  ggplot(., aes(x = scores, colour = status)) + 
  geom_density() + 
  geom_vline(data = . %>% 
               group_by(status) %>%
               summarise(scores.mean = mean(scores)), 
             aes(xintercept = scores.mean, colour = status), 
             linetype = "dashed", 
             size = 1) +
  annotation_custom(tableGrob(rbind(data.frame(df %>% filter(status == "in") %>% rename(var = status, val = scores)),
                                    data.frame(var = row.names(df_summary), val = df_summary, row.names = NULL)), rows = NULL, cols = NULL),
                    xmin = 60, xmax = 100,
                    ymin = 0.1, ymax = 0.4)

}

# Check if it works 
your_function(data_list[[2]])
your_function(data_list[[3]])

# Map it
pdf("plot.pdf")
map(data_list, your_function)
dev.off()