r - ggplot2 绘制比数据框中更多的点，geom_point + facet_grid

Question

我有一些数据，正在尝试制作带有抖动点叠加的箱线图。我的问题是分数，所以我们会坚持下去。

这是数据:

> dput(test)
structure(list(var1 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 8L, 8L, 
8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L), .Label = c("A", "B", "C", "D", 
"E", "F", "G", "H", "I"), class = "factor"), var2 = structure(c(1L, 
2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 
4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 
6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 
1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L), .Label = c("V1", 
"V2", "V3", "V4", "V5", "V6", "V7"), class = "factor"), response1 = c(5L, 
6L, 5L, 5L, 5L, 5L, 4L, 6L, 6L, 5L, 5L, 6L, 6L, 4L, 1L, 1L, NA, 
1L, NA, NA, 1L, 1L, 1L, NA, 1L, NA, NA, 1L, 5L, 5L, 4L, 5L, 3L, 
2L, 3L, 1L, 1L, NA, 1L, NA, NA, 1L, NA, NA, 2L, NA, 3L, 1L, NA, 
NA, NA, 4L, NA, 4L, 5L, NA, NA, NA, 1L, NA, 1L, 1L, NA), response2 = c(2L, 
2L, 2L, 2L, 2L, 2L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 5L, 5L, NA, 
5L, NA, NA, 5L, 5L, 5L, NA, 5L, NA, NA, 5L, 5L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, NA, 5L, NA, NA, 5L, NA, NA, 5L, NA, 5L, 5L, NA, 
NA, NA, 5L, NA, 5L, 5L, NA, NA, NA, 5L, NA, 5L, 5L, NA), response3 = c(4L, 
5L, 1L, 1L, 4L, 1L, 1L, 4L, 5L, 1L, 1L, 5L, NA, 1L, 4L, NA, NA, 
NA, 3L, 2L, NA, 4L, NA, NA, NA, 3L, NA, NA, 4L, NA, 1L, NA, 3L, 
NA, 2L, 4L, NA, NA, NA, NA, NA, NA, NA, 2L, 1L, 1L, NA, NA, 1L, 
NA, 3L, 1L, NA, NA, NA, 1L, NA, 3L, 1L, NA, NA, NA, 1L)), .Names = c("var1", 
"var2", "response1", "response2", "response3"), class = "data.frame", row.names = c(NA, 
-63L))

我用了reshape2融化我的数据以分面/简化绘图命令:

library(reshape2)
test_melted <- melt(test, id.var = c("var1", "var2"), na.rm = T)

这是我创建的情节:

library(ggplot2)
p <- ggplot(test_melted, aes(x = var1, y = value)) + geom_point()
p <- p + facet_grid(~variable) + coord_flip()
p <- p + geom_jitter(position = position_jitter(width=0.2, height = 0.2))
p

这产生了这个:

看起来很正常，但后来我注意到每个方面/因素级别的点数似乎比应有的要多。我将 var1 缩小到一个级别

test_subset <- test_melted[test_melted$var1 == "E", ]

nrow(test_subset)
[1] 18

summary(test_subset)
      var1    var2        variable     value  
 E      :18   V1:3   response1:7   Min.   :1  
 A      : 0   V2:2   response2:7   1st Qu.:3  
 B      : 0   V3:3   response3:4   Median :5  
 C      : 0   V4:2                 Mean   :4  
 D      : 0   V5:3                 3rd Qu.:5  
 F      : 0   V6:2                 Max.   :5  
 (Other): 0   V7:3 

因此，我们应该总共绘制 18 个点(response1 7 个，response2 7 个，response3 4 个。让我们试试看:

p <- ggplot(test_subset, aes(x = var1, y = value)) + geom_point()
p <- p + facet_grid(~variable) + coord_flip()
p <- p + geom_jitter(position = position_jitter(width=0.2, height = 0.2))
p

我在 response1 中数了 11 分刻面，8 英寸 response2 , 和 8 在 response3 .

这一定是我想念的愚蠢的东西。我已经用点图做了很多分面，但从未发生过(或从未注意到!)。

我尝试过的事情

• 删除 coord_flip()
• test_subset <- droplevels(test_subset)以防空因子水平出现问题
• 玩facet_grid(~variable)与 facet_grid(.~variable)与 facet_grid(variable~)与 facet_grid(variable~.)

最后一点，根据我是否分面，我得到不同数量的分数。通过分面，我得到 11 + 8 + 8 = 27 ，如果我删除 facet_grid(~variable) ，我得到 23。

感谢您的任何建议!

Answer 1

问题不是因为分面，而是因为在您的绘图中使用了两个几何图形。所以 geom_point 会在一个地方绘制所有点，然后 geom_jitter 会在随机位置再次绘制它们。这就是为什么您可以在每个图中多看到一个点。

如果您删除对 geom_point 的调用，一切都会恢复正常:

p <- ggplot(test_subset, aes(x = var1, y = value))
p <- p + facet_grid(~variable) + coord_flip()
p <- p + geom_jitter(position = position_jitter(width=0.2, height = 0.2))
p