我有一些数据,我正在尝试制作带有抖动点叠加的箱线图。我的问题是关键点,所以我们会坚持这一点。
以下是数据:
> 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))
我使用reshape2
来融合我的数据,用于绘图命令的分面/同化:
library(reshape2)
test_melted <- melt(test, id.var = c("var1", "var2"), na.rm = T)
这是我创作的情节:
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
产生这个:
看起来很正常,但后来我注意到每个方面/因子水平的点数似乎比应有的多。我缩小到var1
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
为7,response2
为7,response3
为4。让我们尝试一下:
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
方面计算了11个点,response2
中有8个点,response3
中有8个点。
这一定是我想念的傻事。我已经用点图进行了大量的刻面,并且从未发生过这种情况(或从未注意到!)。
我尝试过的事情
coord_flip()
test_subset <- droplevels(test_subset)
如果空因子水平搞乱了facet_grid(~variable)
与facet_grid(.~variable)
对比facet_grid(variable~)
与facet_grid(variable~.)
作为最后一点,我会得到不同数量的积分,具体取决于我是否面对。通过刻面,我得到11 + 8 + 8 = 27
,如果我删除facet_grid(~variable)
,我会得到23。
感谢您的任何建议!
答案 0 :(得分:2)
问题不在于分面,而是因为在你的情节中使用两个geoms。因此geom_point
会在一个地方绘制你的积分,然后geom_jitter
将在随机位置再次绘制它们。这就是为什么你可以在每个情节中再看到一个点。
如果您取消对geom_point
的呼叫,一切都恢复正常:
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