将形状编号映射到图例

Question

我需要ggplot2语法方面的一些帮助。我有一些看起来像这样的数据：

> dput(SOData)
structure(list(Compound = c("cmpd1", "cmpd2", "cmpd3", "cmpd2", 
"cmpd3", "cmpd3", "cmpd4", "cmpd5", "cmpd6", "cmpd1", "cmpd5", 
"cmpd6", "cmpd1", "cmpd1", "cmpd1", "cmpd1", "cmpd2", "cmpd2", 
"cmpd1", "cmpd1", "cmpd1", "cmpd1", "cmpd2", "cmpd2", "cmpd2", 
"cmpd2", "cmpd2", "cmpd2", "cmpd4", "cmpd1", "cmpd1", "cmpd1", 
"cmpd1", "cmpd2", "cmpd2", "cmpd2", "cmpd2", "cmpd2", "cmpd2", 
"cmpd2", "cmpd1", "cmpd1", "cmpd1", "cmpd1", "cmpd5", "cmpd7", 
"cmpd7", "cmpd4", "cmpd4", "cmpd4", "cmpd6", "cmpd5", "cmpd6", 
"cmpd5", "cmpd6", "cmpd7", "cmpd3", "cmpd5", "cmpd3", "cmpd6", 
"cmpd5", "cmpd6", "cmpd5", "cmpd3", "cmpd5", "cmpd7", "cmpd3", 
"cmpd7", "cmpd8", "cmpd8", "cmpd8", "cmpd6", "cmpd5", "cmpd6", 
"cmpd7", "cmpd1", "cmpd2", "cmpd3", "cmpd2", "cmpd3", "cmpd3", 
"cmpd4", "cmpd5", "cmpd6", "cmpd1", "cmpd5", "cmpd6", "cmpd1", 
"cmpd1", "cmpd1", "cmpd1", "cmpd2", "cmpd2", "cmpd1", "cmpd1", 
"cmpd1", "cmpd1", "cmpd2", "cmpd2", "cmpd2", "cmpd2", "cmpd2", 
"cmpd2", "cmpd4", "cmpd1", "cmpd1", "cmpd1", "cmpd1", "cmpd2", 
"cmpd2", "cmpd2", "cmpd2", "cmpd2", "cmpd2", "cmpd2", "cmpd1", 
"cmpd1", "cmpd1", "cmpd1", "cmpd5", "cmpd7", "cmpd7", "cmpd4", 
"cmpd4", "cmpd4", "cmpd6", "cmpd5", "cmpd6", "cmpd5", "cmpd6", 
"cmpd7", "cmpd3", "cmpd5", "cmpd3", "cmpd6", "cmpd5", "cmpd6", 
"cmpd5", "cmpd3", "cmpd5", "cmpd7", "cmpd3", "cmpd7", "cmpd8", 
"cmpd8", "cmpd8", "cmpd6", "cmpd5", "cmpd6", "cmpd7"), variable = structure(c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L), class = "factor", .Label = c("Avg SS (pA)", 
"Min Peak (pA)")), value = c(274, 109, 175, 113, 86, 121, 80, 
112, 311, 110, 101, 312, 97, 419, 494, 454, 169, 80, 114, 119, 
105, 392, 207, 103, 84, 102, 100, 86, 96, 79, 339, 356, 394, 
317, 227, 158, 54, 136, 104, 107, 86, 58, 66, 84, 72, 90, 111, 
95, 134, 89, 285, 50, 69, 78, 89, 249, 90, 80, 62, 248, 72, 85, 
96, 97, 108, 85, 31, 53, 482, 551, 388, 323, 59, 74, 233, 193, 
206, 162, 79, 97, 21, 72, 170, 144, 57, 21, 68, 94, 310, 223, 
262, 191, 116, 107, 108, 116, 149, 185, 153, 76, 99, 111, 103, 
129, 119, 395, 181, 203, 293, 192, 340, 74, 130, 107, 132, 284, 
93, 72, 92, 140, 75, 57, 71, 63, 141, 154, 21, 52, 50, 106, 63, 
184, 369, 89, 223, 173, 120, 111, 191, 298, 62, 65, 72, 325, 
286, 194, 339, 128, 91, 110), Conc = c("10.0", "10.0", "10.0", 
"1.00", "1.00", "0.1", ".3", "10.0", "10.0", "1.00", "1.00", 
"1.00", "0.1", "10.0", "10.0", "10.0", "10.0", "1.00", "1.00", 
"1.00", "0.1", "10.0", "10.0", "10.0", "1.00", "1.00", "1.00", 
"0.1", ".3", "1.00", "10.0", "10.0", "10.0", "10.0", "10.0", 
"10.0", "1.00", "1.00", "0.1", "0.1", "1.00", "1.00", "0.1", 
"0.1", "10.0", "1.00", "0.1", ".3", ".3", ".3", "10.0", "1.00", 
"1.00", "0.1", "0.1", "10.0", "1.00", "10.0", "0.1", "10.0", 
"1.00", "1.00", "0.1", "10.0", "10.0", "1.00", "0.1", "0.1", 
"10.0", "1.00", "0.1", "10.0", "1.00", "0.1", "10.0", "10.0", 
"10.0", "10.0", "1.00", "1.00", "0.1", ".3", "10.0", "10.0", 
"1.00", "1.00", "1.00", "0.1", "10.0", "10.0", "10.0", "10.0", 
"1.00", "1.00", "1.00", "0.1", "10.0", "10.0", "10.0", "1.00", 
"1.00", "1.00", "0.1", ".3", "1.00", "10.0", "10.0", "10.0", 
"10.0", "10.0", "10.0", "1.00", "1.00", "0.1", "0.1", "1.00", 
"1.00", "0.1", "0.1", "10.0", "1.00", "0.1", ".3", ".3", ".3", 
"10.0", "1.00", "1.00", "0.1", "0.1", "10.0", "1.00", "10.0", 
"0.1", "10.0", "1.00", "1.00", "0.1", "10.0", "10.0", "1.00", 
"0.1", "0.1", "10.0", "1.00", "0.1", "10.0", "1.00", "0.1", "10.0"
)), .Names = c("Compound", "variable", "value", "Conc"), row.names = c(NA, 
-150L), class = c("data.table", "data.frame"), .internal.selfref = <pointer: 0x0000000000110788>)

我的GGplot看起来像这样：

    FinalPlot = ggplot(data=SOData,aes(x=Conc,y=value,color=variable))+
geom_point(size =2,aes(x=Conc,y=value,color=variable), shape=16)+
stat_summary(aes(group=variable),fun.y=mean,geom='point',size=4,shape=9)+
scale_shape_manual('Legend',values =c(9,16))+
facet_wrap(~Compound)+
ylab('Current (pA)')+
xlab('Concentration (µM)')+
theme(text= element_text(size=14,face='bold'))+
theme(strip.text.x = element_text(size = 16,face = 'bold'))+
theme()

关于情节：

每个方面都是一个单独的化合物。在每个方面，我想要给定条件（变量）的所有值，然后是每个变量的平均值。现在我有geom_point映射值然后stat_summary做平均值。每个都有一个单独的形状编号。这很好用，但传说没有信息。如何拆分图例以将点颜色显示为变量，然后将形状样式显示为Raw或Mean？

Answer 1

如果您希望在图例中显示某些内容，则 通常必须将其添加到aes。您只需将形状映射到信息丰富的名称，然后将scale_shape_manual调用中的名称映射到实际形状。

ggplot(data=SOData,aes(x=Conc,y=value,color=variable))+
  geom_point(size =2,aes(x=Conc,y=value,color=variable, shape='raw'))+
  stat_summary(aes(group=variable,shape='mean'),fun.y=mean,geom='point',size=4)+
  scale_shape_manual('Legend',values =c(mean = 9, raw = 16))+
  facet_wrap(~Compound)+
  ylab('Current (pA)')+
  xlab('Concentration (µM)')+
  theme(text= element_text(size=14,face='bold'))+
  theme(strip.text.x = element_text(size = 16,face = 'bold'))

（请注意， minimal 示例可能包含一个小得多的数据集，包含data.frame而不是data.table，没有构面，没有标签和没有主题调用。）