R 如何使用split和sapply在ggplot中组合多个数据源？

这个问题与@Rui Barradas和@Duck之前回答的问题有关，但我需要更多帮助。上一链接：

基本上，我需要将3个数据集组合成一个带有次要y轴的图。所有数据集都需要按SITENAME拆分，并将按Sampling.Year进行分面换行。我正在使用split和sapply。在进行面换行时，图的外观如下所示：

但是，我现在尝试将另外两个数据源添加到绘图中，如下所示：

但我正在努力添加另外两个数据源，并让它们按SITENAME进行拆分。她是我目前的密码

将记录打印格式作为应用于拆分列表df的函数（理想情况下，“df”将添加为带有次要y轴的几何图形线，“FF_开始日期”将添加为垂直虚线）：

---

SITENAME\u plot您可以尝试下一个代码。我使用了你共享的数据。请注意所有数据集的名称。理想情况下，在进行拆分之前，所有数据帧中都应该出现关键列，如
DATE
和
Sampling.Year
。还有一些变量，如
风险
，也不存在，所以我添加了一个同名的示例var。在这段代码中，我为您想要的绘图添加了一个函数：

library(tidyverse)
library(readxl)
#Data
df1 <- read_excel('Sample data.xlsx',1)
#Create var
df1$Risk <- c(rep(c("Very Low","Low","Moderate","High","Very High"),67),"Very High")
#Other data
df2 <- read_excel('Sample data.xlsx',2)
df3 <- read_excel('Sample data.xlsx',3)
#Split 1
L1 <- split(df1,df1$SITENAME)
L2 <- split(df2,df2$SITENAME)
L3 <- split(df3,df3$`Site Name`)
#Function to create plots
myplot <- function(x,y,z)
{
  #Merge x and y
  #Check for duplicates and avoid column
  y <- y[!duplicated(paste(y$DATE,y$Sampling.Year)),]
  y$SITENAME <- NULL
  xy <- merge(x,y,by.x = c('Sampling.Year','DATE'),by.y = c('Sampling.Year','DATE'),all.x=T)
  #Format to dates
  xy$DATE <- as.Date(xy$DATE)
  #Scale factor
  scaleFactor <- max(xy$Daily.Ave.PAF) / max(xy$Height)
  #Rename for consistency in names
  names(z)[4] <- 'DATE'
  #Format date
  z$DATE <- as.Date(z$DATE)
  #Plot
  #Plot
  G <- ggplot(xy, aes(DATE, Daily.Ave.PAF)) +
    geom_point(aes(colour = Risk), size = 3) +
    scale_colour_manual(values=c("Very Low" = "dark green","Low" = "light green", 
                                 "Moderate" = "yellow", "High" = "orange", "Very High" = "red"), drop = FALSE) +
    scale_x_date(breaks = "1 month", labels = scales::date_format("%b %Y")) +
    geom_line(aes(x=DATE,y=Height*scaleFactor))+
    scale_y_continuous(name="Total PAF (% affected)", sec.axis=sec_axis(~./scaleFactor, name="Water level (m)"))+
    labs(x = "Month") +
    geom_vline(data = z,aes(xintercept = DATE),linetype="dashed")+
    facet_wrap(~Sampling.Year, ncol = 1, scales = "free")+
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1)) +
    theme(legend.text=element_text(size=15)) +
    theme(axis.text=element_text(size=15),
          axis.title=element_text(size=15,face="bold")) +
    guides(color = guide_legend(reverse = TRUE))+
    theme_bw() +
    ggtitle(unique(xy$SITENAME))
  return(G)
}
#Create a list of plots
Lplots <- mapply(FUN = myplot,x=L1,y=L2,z=L3,SIMPLIFY = FALSE)
#Now format names
vnames <- paste0(names(Lplots),'.png')
mapply(ggsave, Lplots,filename = vnames,width = 30,units = 'cm')

库（tidyverse）
图书馆（readxl）
#资料
df1鸭子又来营救了！你太棒了，非常感谢你！我现在正在试用。@CatN请注意数据，我在您的样本中发现了重复的数据！其中一个变量（上面代码中的水位=df2）的数据点比另一个在x轴上绘制的数据点多，这有关系吗？我一直收到这个错误消息，但在代码中找不到修复它的地方：警告消息：在mapply中（FUN=myplot，x=L1，y=L2，z=L3，SIMPLIFY=FALSE）：较长的参数不是较短长度的倍数。实际上，忽略我最后的注释-我意识到我做错了什么。再次感谢Duck，此代码有效。你救了我一天！我学到了一些新的东西：）@CatN太棒了，它起作用了，而且总是很乐意帮助你：）
SITENAME_plot_write <- function(name, g, dir = "N:/abc/"){
  flname <- file.path(dir, name)
  flname <- paste0(flname, ".jpg")
  png(filename = flname, width = 1500, height = 1000)
  print(g)
  dev.off()
  flname
}

sp1 <- split(AllDates_TPAF, AllDates_TPAF$SITENAME)
gg_list <- sapply(sp1, SITENAME_plot, simplify = FALSE)
mapply(SITENAME_plot_write, names(gg_list), gg_list, MoreArgs = list(dir = getwd()))
dev.off()

library(tidyverse)
library(readxl)
#Data
df1 <- read_excel('Sample data.xlsx',1)
#Create var
df1$Risk <- c(rep(c("Very Low","Low","Moderate","High","Very High"),67),"Very High")
#Other data
df2 <- read_excel('Sample data.xlsx',2)
df3 <- read_excel('Sample data.xlsx',3)
#Split 1
L1 <- split(df1,df1$SITENAME)
L2 <- split(df2,df2$SITENAME)
L3 <- split(df3,df3$`Site Name`)
#Function to create plots
myplot <- function(x,y,z)
{
  #Merge x and y
  #Check for duplicates and avoid column
  y <- y[!duplicated(paste(y$DATE,y$Sampling.Year)),]
  y$SITENAME <- NULL
  xy <- merge(x,y,by.x = c('Sampling.Year','DATE'),by.y = c('Sampling.Year','DATE'),all.x=T)
  #Format to dates
  xy$DATE <- as.Date(xy$DATE)
  #Scale factor
  scaleFactor <- max(xy$Daily.Ave.PAF) / max(xy$Height)
  #Rename for consistency in names
  names(z)[4] <- 'DATE'
  #Format date
  z$DATE <- as.Date(z$DATE)
  #Plot
  #Plot
  G <- ggplot(xy, aes(DATE, Daily.Ave.PAF)) +
    geom_point(aes(colour = Risk), size = 3) +
    scale_colour_manual(values=c("Very Low" = "dark green","Low" = "light green", 
                                 "Moderate" = "yellow", "High" = "orange", "Very High" = "red"), drop = FALSE) +
    scale_x_date(breaks = "1 month", labels = scales::date_format("%b %Y")) +
    geom_line(aes(x=DATE,y=Height*scaleFactor))+
    scale_y_continuous(name="Total PAF (% affected)", sec.axis=sec_axis(~./scaleFactor, name="Water level (m)"))+
    labs(x = "Month") +
    geom_vline(data = z,aes(xintercept = DATE),linetype="dashed")+
    facet_wrap(~Sampling.Year, ncol = 1, scales = "free")+
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1)) +
    theme(legend.text=element_text(size=15)) +
    theme(axis.text=element_text(size=15),
          axis.title=element_text(size=15,face="bold")) +
    guides(color = guide_legend(reverse = TRUE))+
    theme_bw() +
    ggtitle(unique(xy$SITENAME))
  return(G)
}
#Create a list of plots
Lplots <- mapply(FUN = myplot,x=L1,y=L2,z=L3,SIMPLIFY = FALSE)
#Now format names
vnames <- paste0(names(Lplots),'.png')
mapply(ggsave, Lplots,filename = vnames,width = 30,units = 'cm')