r - 通过ggplot在密度图中添加部分数据

Question

我有一个包含两个不同类别的文件，其中大部分属于一个类别。类别是:in 和 out。

file1_ggplot.txt

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

为了绘制密度分布图，我正在使用这段代码，但我想添加类别摘要和具有 in 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()

哪个输出:

我想添加一个框，其中包含 in 行:

in     44
in     55

还有，

> summary(data1$scores)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  12.00   15.50   33.50   41.00   52.25   99.00 

为此，我正在尝试使用 tableGrob:

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))

但它给出了上面相同的图，其中只有 summary 的数字。

然后，我用 in.

搜索了这些行

cat file1_ggplot.txt | grep -w "in" > only-in.txt

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))

它输出:

如果不先在 bash 中使用 grep，我该怎么做才能在绘图旁边正确查看这些表格，以及带有 in 的行？

Answer 1

这是一个解决方案，假设您想要的表格格式:

个别情节

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)

应用于数据框列表

# 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()

您现在应该有一个“plot.pdf”文件，每个图有 3 页。

注意tableGrob的位置要根据你的日期来调整，我不知道把表格放在哪里，你也可以根据汇总值计算位置。