ggplot/GGally - 平行坐标 - y轴标签

Question

有谁知道是否有办法ggparcoord在GGally中为函数添加变量标签？我尝试了很多方法geom_text,但没有任何结果.

为了更明确,我希望row.names(mtcars)通过geom_text.我可以区分汽车的唯一方法是row.names(mtcars)通过groupColumn论证,但我不喜欢这种看法.

不起作用:

mtcars$carName <- row.names(mtcars) # This becomes column 12
library(GGally)
# Attempt 1
ggparcoord(mtcars, 
           columns = c(12, 1, 6), 
           groupColumn = 1) +
geom_text(aes(label = carName))

# Attempt 2
ggparcoord(mtcars, 
           columns = c(12, 1, 6),
           groupColumn = 1,
           mapping = aes(label = carName))

任何想法,将不胜感激!

Answer 1

解决方案 1：如果您想坚持最初的尝试，您可以计算汽车名称的适当 y 坐标，并将其添加为单独的数据源。使用inherit.aes = FALSE此 geom_text 图层不会从使用以下命令创建的 ggplot 对象继承任何内容ggparcoord()：

library(dplyr)

p1 <- ggparcoord(mtcars, 
                 columns = c(12, 1, 6), 
                 groupColumn = 1) +

  geom_text(data = mtcars %>%
              select(carName) %>%
              mutate(x = 1,
                     y = scale(as.integer(factor(carName)))),
            aes(x = x, y = y, label = carName),
            hjust = 1.1,
            inherit.aes = FALSE) +

  # optional: remove "carName" from x-axis labels
  scale_x_discrete(labels = function(x) c("", x[-1])) + 

  # also optional: hide legend, which doesn't really seem relevant here
  theme(legend.position = "none")
p1

解决方案 2：此替代方案使用 carName 作为组列，并且不将其作为并行坐标列之一传递。data（我认为这可能更接近此函数预期的用例...）指定 carName 作为组列允许在此时创建的 ggplot 对象的槽中捕获汽车名称值ggparcoord()，因此我们的geom_text标签可以直接继承它，甚至仅过滤对应的行variable == "mpg"（或者在实际用例中命名的第一个平行坐标列）。y 坐标不像上面那样均匀分布，但是geom_text_repelggrepel 包在将重叠的文本标签相互移开方面做得很好。

library(dplyr)
library(ggrepel)

p2 <- ggparcoord(mtcars, 
           columns = c(1, 6), 
           groupColumn = "carName") +
  geom_text_repel(data = . %>%
                    filter(variable == "mpg"),
                  aes(x = variable, y = value, label = carName),
                  xlim = c(NA, 1)) + # limit repel region to the left of the 1st column
  theme(legend.position = "none") # as before, hide legend since the labels 
                                  # are already in the plot
p2

解决方案 3 / 4：您实际上可以使用 绘制相同的图ggplot()，而无需依赖可能在幕后执行意外操作的扩展：

library(dplyr)
library(tidyr)
library(ggrepel)

# similar output to solution 1

p3 <- mtcars %>%
  select(carName, mpg, wt) %>%
  mutate(carName.column = as.integer(factor(carName))) %>%
  gather(variable, value, -carName) %>%
  group_by(variable) %>%
  mutate(value = scale(value)) %>%
  ungroup() %>%

  ggplot(aes(x = variable, y = value, label = carName, group = carName)) +
  geom_line() +
  geom_text(data = . %>% filter(variable == "carName.column"),
            hjust = 1.1) +
  scale_x_discrete(labels = function(x) c("", x[-1]))
p3

# similar output to solution 2

p4 <- mtcars %>%
  select(carName, mpg, wt) %>%
  gather(variable, value, -carName) %>%
  group_by(variable) %>%
  mutate(value = scale(value)) %>%
  ungroup() %>%

  ggplot(aes(x = variable, y = value, label = carName, group = carName)) +
  geom_line() +
  geom_text_repel(data = . %>% filter(variable == "mpg"),
                  xlim = c(NA, 1))
p4

编辑

您还可以为上述每个内容在右侧添加文本标签。请注意，标签的位置可能不会很好地间隔开，因为它们是根据 的wt缩放值定位的：

p1 +
  geom_text(data = mtcars %>%
              select(carName, wt) %>%
              mutate(x = 3,
                     y = scale(wt)),
            aes(x = x, y = y, label = carName),
            hjust = -0.1,
            inherit.aes = FALSE)

p2 +
  geom_text_repel(data = . %>%
                    filter(variable == "wt"),
                  aes(x = variable, y = value, label = carName),
                  xlim = c(2, NA))

p3 +
  geom_text(data = . %>% filter(variable == "wt"),
            hjust = -0.1)

p4 +
  geom_text_repel(data = . %>% filter(variable == "wt"),
                  xlim = c(2, NA))