ggplot条形图与分面依赖的类别顺序

Question

我见过许多关于如何（重新）在条形图中订购类别的问题（通常与Order Bars in ggplot2 bar graph相关联）。

我所追求的只是一种不同的触觉，但我还没有找到一个好的方法：我有一个多面条形图，我想要为每个面单独订购x轴，根据另一个变量（在我的例子中，该变量只是y值本身，即我只是希望每个方面的条形长度增加）。

简单的例子，例如， Order Bars in ggplot2 bar graph：

df <- data.frame(name=c('foo','bar','foo','bar'),period=c('old','old','recent','recent'),val=c(1.23,2.17,4.15,3.65))
p = ggplot(data = df, aes(x = reorder(name, val), y = val))
p = p + geom_bar(stat='identity')
p = p + facet_grid(~period)
p

我们得到的是以下内容：

而我想要的是：

Answer 1

好的，所以除了所有的哲学之外，如果有人感兴趣，这是一个丑陋的黑客去做。我的想法是使用不同的标签（想想paste(period, name)，除了我将句点替换为0空格，1空格等，以便它们不显示）。我需要这个情节，我不想安排grobs等，因为我可能想分享一个共同的传说等。

前面给出的原子示例变为：

df <- data.frame(name=c('foo','bar','foo','bar'),
  period=c('old','old','recent','recent'),
  val=c(1.23,2.17,4.15,3.65),
  stringsAsFactors=F)
df$n = as.numeric(factor(df$period))
df = ddply(df,.(period,name),transform, x=paste(c(rep(' ',n-1), name), collapse=''))
df$x = factor(df$x, levels=df[order(df$val), 'x'])
p = ggplot(data = df, aes(x = x, y = val))
p = p + geom_bar(stat='identity')
p = p + facet_grid(~period, scale='free_x')
p

另一个例子，仍然有点愚蠢，但更接近我的实际用例，将是：

df <- ddply(mpg, .(year, manufacturer), summarize, mixmpg = mean(cty+hwy))
df$manufacturer = as.character(df$manufacturer)
df$n = as.numeric(factor(df$year))
df = ddply(df, .(year,manufacturer), transform,
     x=paste(c(rep(' ',n-1), manufacturer), collapse=''))
df$x = factor(df$x, levels=df[order(df$mixmpg), 'x'])
p = ggplot(data = df, aes(x = x, y = mixmpg))
p = p + geom_bar(stat='identity')
p = p + facet_grid(~year, scale='free_x')
p = p + theme(axis.text.x=element_text(angle=90,hjust=1,vjust=.5,colour='gray50'))
p

闭上眼睛，想起帝国，尽量享受。

Answer 2

这是一个老问题，但它被用作欺骗目标。因此，建议使用ggplot2包的最新增强功能，即labels参数到scale_x_discrete()的解决方案可能是值得的。这样可以避免使用已弃用的use duplicate levels或manipulate factor labels by prepending a varying number of spaces。

准备数据

此处，mpg数据集用于与this answer进行比较。对于数据操作，此处使用data.table包，但您可以随意使用您喜欢的任何包。

library(data.table)   # version 1.10.4
library(ggplot2)      # version 2.2.1
# aggregate data
df <- as.data.table(mpg)[, .(mixmpg = mean(cty + hwy)), by = .(year, manufacturer)]
# create dummy var which reflects order when sorted alphabetically
df[, ord := sprintf("%02i", frank(df, mixmpg, ties.method = "first"))]

创建情节

# `ord` is plotted on x-axis instead of `manufacturer`
ggplot(df, aes(x = ord, y = mixmpg)) +
  # geom_col() is replacement for geom_bar(stat = "identity")
  geom_col() +
  # independent x-axis scale in each facet, 
  # drop absent factor levels (actually not required here)
  facet_wrap(~ year, scales = "free_x", drop = TRUE) +
  # use named character vector to replace x-axis labels
  scale_x_discrete(labels = df[, setNames(as.character(manufacturer), ord)]) + 
  # replace x-axis title
  xlab(NULL) +
  # rotate x-axis labels
  theme(axis.text.x = element_text(angle = 90, hjust=1, vjust=.5))

Answer 3

根据this answer

有几种不同的方法可以实现OP的目标

（1）reorder_within()函数可在name个方面对period进行重新排序。

library(tidyverse)
library(forcats)

df <- data.frame(
  name = c("foo", "bar", "foo", "bar"),
  period = c("old", "old", "recent", "recent"),
  val = c(1.23, 2.17, 4.15, 3.65)
)

reorder_within <- function(x, by, within, fun = mean, sep = "___", ...) {
  new_x <- paste(x, within, sep = sep)
  stats::reorder(new_x, by, FUN = fun)
}

scale_x_reordered <- function(..., sep = "___") {
  reg <- paste0(sep, ".+$")
  ggplot2::scale_x_discrete(labels = function(x) gsub(reg, "", x), ...)
}

ggplot(df, aes(reorder_within(name, val, period), val)) +
  geom_col() +
  scale_x_reordered() +
  facet_grid(period ~ ., scales = "free", space = "free") +
  coord_flip() +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank()) 

或者（2）类似的想法

### https://trinkerrstuff.wordpress.com/2016/12/23/ordering-categories-within-ggplot2-facets/
df %>% 
  mutate(name = reorder(name, val)) %>%
  group_by(period, name) %>% 
  arrange(desc(val)) %>% 
  ungroup() %>% 
  mutate(name = factor(paste(name, period, sep = "__"), 
                       levels = rev(paste(name, period, sep = "__")))) %>%
  ggplot(aes(name, val)) +
  geom_col() +
  facet_grid(period ~., scales = "free", space = 'free') +
  scale_x_discrete(labels = function(x) gsub("__.+$", "", x)) +
  coord_flip() +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank()) + 
  theme(axis.ticks.y = element_blank())

或者（3）对整个数据框进行排序，还对每个构面组内的类别（period）进行排序！

  ### https://drsimonj.svbtle.com/ordering-categories-within-ggplot2-facets
  # 
  df2 <- df %>% 
  # 1. Remove any grouping
  ungroup() %>% 
  # 2. Arrange by
  #   i.  facet group (period)
  #   ii. value (val)
  arrange(period, val) %>%
  # 3. Add order column of row numbers
  mutate(order = row_number())
df2
#>   name period  val order
#> 1  foo    old 1.23     1
#> 2  bar    old 2.17     2
#> 3  bar recent 3.65     3
#> 4  foo recent 4.15     4

ggplot(df2, aes(order, val)) +
  geom_col() +
  facet_grid(period ~ ., scales = "free", space = "free") +
  coord_flip() +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank()) 

# To finish we need to replace the numeric values on each x-axis 
# with the appropriate labels
ggplot(df2, aes(order, val)) +
  geom_col() +
  scale_x_continuous(
    breaks = df2$order,
    labels = df2$name) +
  # scale_y_continuous(expand = c(0, 0)) +
  facet_grid(period ~ ., scales = "free", space = "free") +
  coord_flip() +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank()) + 
  theme(legend.position = "bottom",
        axis.ticks.y = element_blank())

^{由reprex package（v0.2.1.9000）于2018-11-05创建}

Answer 4

试试这个，它非常简单（只需忽略警告）

df <-data.frame(name = c('foo', 'bar', 'foo', 'bar'),
                period = c('old', 'old', 'recent', 'recent'),
                val = c(1.23, 2.17, 4.15, 3.65))

d1 <- df[order(df$period, df$val), ]
sn <- factor(x = 1:4, labels = d1$name)
d1$sn <- sn
p <- ggplot(data = d1, aes(x = sn, y = val))
p <- p + geom_bar(stat = 'identity')
p <- p + facet_wrap(~ period, scale = 'free_x')
p