将连接手段的线条添加到ggplot (雨云图)

Question

我有一个ggplot，我想在其中添加一条连接均值的线。然而，我一直收到一个错误消息："geom_path:每个组只包含一个观察值。您需要调整组美学吗？“

我尝试了这里建议的解决方案，但这些似乎在几年前就不起作用了。因此，我开了一个新的帖子。

#some packages
if (!require("pacman")) install.packages("pacman")
pacman::p_load(here, readr, cowplot, tidyr, ggplot2, dplyr)
#some functions from https://github.com/RainCloudPlots/RainCloudPlots
source("R_rainclouds.R")
source("summarySE.R")
source("simulateData.R")

#some data
df3 <- structure(list(participant = c(1L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 
11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 
24L, 25L, 26L, 1L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 
14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 
1L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 
17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L), condition = structure(c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("RT_Cau", "RT_Moro", 
"RT_Asi"), class = "factor"), RT = c(1.44248448543333, 2.73934002973517, 
1.89927013090706, 1.32510448686595, 2.44101598069973, 2.84290772015973, 
1.19419819108836, 2.12124958877175, 1.14707311860052, 2.72286767178203, 
1.15914495363538, 1.5340050993702, 1.62616192435053, 1.32694796283192, 
1.2720800304128, 0.99275928310549, 1.04329096409593, 1.43288644582691, 
1.60302970699442, 1.3393626055176, 1.24088162033185, 2.42448868318791, 
1.6398716779282, 1.53816275909702, 1.51033130413559, 3.226993255043, 
2.1915727996463, 1.39240057519678, 3.0538809712989, 2.52658416881183, 
1.16366335020089, 2.33377114484134, 1.39357978132538, 2.691606623485, 
1.21999657945028, 1.72195011524003, 1.38834235226937, 1.44350802586345, 
1.29563539425317, 0.909762618509679, 1.13583585924538, 1.58240957515452, 
1.82142351906117, 1.3644415734435, 1.32141664778601, 2.23277562688125, 
1.5773976029336, 1.43200172590417, 1.68991681725, 2.9617422858462, 
1.60886625604519, 1.38647850513866, 3.46156610375971, 2.96950698342897, 
1.17905107770577, 2.36256332626113, 1.31254065801458, 3.204902618708, 
1.21067325368702, 1.80371515914087, 1.57816183853565, 1.40761655308155, 
1.27304559913463, 1.07621914272144, 1.04203150853998, 1.58958820979388, 
1.79859778873147, 1.19249820050996, 1.4116357628608, 2.15806795062162, 
1.70597872926531, 1.66135756110131)), row.names = c(NA, -72L), class = "data.frame")

#make a summary of the data 
df4 <- summarySE(df3, measurevar = "RT", groupvars = c("condition"))

#a working plot that shows dots, boxplot, distribution, and mean+SE
#I want to have lines connecting the mean dots.

ggplot(df3,aes(x=condition,y=RT,fill=condition,col=condition))+
  geom_flat_violin(position = position_nudge(x = .2, y = 0), alpha = .6,adjust =4)+
  geom_point(aes(x = as.numeric(condition)-.15, y = RT, colour = condition),position = position_jitter(width = .05), size = .25, shape = 20)+
  geom_boxplot(aes(x = condition, y = RT, fill = condition),outlier.shape = NA, alpha = .5, width = .1, colour = "black") +
  geom_point(data = df4, aes(x = as.numeric(condition)+.1, y = RT_mean, group = condition, colour = condition), shape = 18) + 
  geom_errorbar(data = df4, aes(x = as.numeric(condition)+.1, y = RT_mean, group = condition, colour = condition, ymin = RT_mean-se, ymax = RT_mean+se), width = .05) +
  ylab('RT')+
  scale_fill_brewer(palette = "Dark2")+scale_colour_brewer(palette = "Dark2")+
  guides(fill = FALSE, col = FALSE) +
    theme_bw() +
    theme(
      panel.grid.major = element_blank(), 
      panel.grid.minor = element_blank(),
      panel.background = element_rect(fill = "transparent",colour = NA),
      plot.background = element_rect(fill = "transparent",colour = NA)
    ) # +
  #  geom_line(data = df4, aes(x = as.numeric(condition)+.1, #y = RT_mean, group = condition, colour = condition), #linetype = 3)
#The commented outpart is my attempt to connect it with lines, which produces the described error.

#If you do not want to load the package from github, here is the raw code of the summariseSE function:

# summarySE function
summarySE <- function(data = NULL, measurevar, groupvars = NULL, na.rm = FALSE,
                      conf.interval = .95, .drop = TRUE) {
  library(plyr)

  # New version of length which can handle NA's: if na.rm==T, don't count them
  length2 <- function(x, na.rm = FALSE) {
    if (na.rm) {
      sum(!is.na(x))
    } else {
      length(x)
    }
  }

  # This does the summary. For each group's data frame, return a vector with
  # N, mean, median, and sd

  datac <- plyr::ddply(data, groupvars, .drop=.drop,
                   .fun = function(xx, col) {
                       c(N      = length2(xx[[col]], na.rm=na.rm),
                         mean   = mean(xx[[col]], na.rm=na.rm),
                         median = median(xx[[col]], na.rm=na.rm),
                         sd      = sd(xx[[col]], na.rm=na.rm)
                       )
                   },
                   measurevar
  )
  
  # Rename the "mean" and "median" columns    
 datac <- plyr::rename(datac, c("mean" = paste(measurevar, "_mean", sep = "")))
 datac <- plyr::rename(datac, c("median" = paste(measurevar, "_median", sep = "")))
  
 datac$se <- datac$sd / sqrt(datac$N)  # Calculate standard error of the mean

  # Confidence interval multiplier for standard error
  # Calculate t-statistic for confidence interval:
  # e.g., if conf.interval is .95, use .975 (above/below), and use df=N-1
  ciMult <- qt(conf.interval / 2 + .5, datac$N - 1)
  datac$ci <- datac$se * ciMult

  return(datac)
}

最终的曲线图应该有连接均值的线，类似于https://wellcomeopenresearch.org/articles/4-63/v2的曲线图11。

谢谢你的帮助！

Answer 1

这可能很有用：

#Code
ggplot(df3,aes(x=condition,y=RT,fill=condition,col=condition))+
  geom_flat_violin(position = position_nudge(x = .2, y = 0),
                   alpha = .6,adjust =4)+
  geom_point(aes(x = as.numeric(condition)-.15, y = RT,
                 colour = condition),
             position = position_jitter(width = .05), size = .25, shape = 20)+
  geom_boxplot(aes(x = condition, y = RT, fill = condition),
               outlier.shape = NA, alpha = .5,
               width = .1, colour = "black") +
  geom_point(data = df4, aes(x = as.numeric(condition)+.1,
                             y = RT_mean,
                             group = condition, colour = condition), shape = 18) + 
  geom_errorbar(data = df4, aes(x = as.numeric(condition)+.1, y = RT_mean, group = condition, colour = condition, ymin = RT_mean-se, ymax = RT_mean+se), width = .05) +
  ylab('RT')+
  scale_fill_brewer(palette = "Dark2")+scale_colour_brewer(palette = "Dark2")+
  guides(fill = FALSE, col = FALSE) +
  theme_bw() +
  theme(
    panel.grid.major = element_blank(), 
    panel.grid.minor = element_blank(),
    panel.background = element_rect(fill = "transparent",colour = NA),
    plot.background = element_rect(fill = "transparent",colour = NA)
  ) +
  geom_line(data = df4, aes(x = as.numeric(condition)+.1,
                           y = RT_mean, group = 1)

输出：

​

​