如何创建包含所有点的箱线图，对于每个组，可以手动分配点的颜色

Question

我有一个数据框：

> dput(df2)
structure(list(Genotype = c("miR-15/16 FL", "miR-15/16 FL", "miR-15/16 FL", 
"miR-15/16 FL", "miR-15/16 FL", "miR-15/16 cKO", "miR-15/16 cKO", 
"miR-15/16 cKO", "miR-15/16 cKO", "miR-15/16 cKO"),
`Cells/SC/Live/CD8—,, CD4+/Foxp3-,Median,<BV421-A>,CD127` = c(1191L, 1325L, 1089L, 1154L, 1147L, 1735L, 1441L, 1455L, 1560L, 1623L)),
.Names = c("Genotype", "Cells/SC/Live/CD8—,, CD4+/Foxp3-,Median,<BV421-A>,CD127"),
row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"))
MFI=c(1191,1325,1089,1154,1147,1735,1441,1455,1560,1623))

我想制作一个箱线图，为每个组（miR-15/16 FL 和 miR-15/16 cKO）绘制每个点，并拥有所有的

'miR-15/16 FL' 

点被封闭的黑色圆圈和所有的

'miR-15/16 cKO' 

点是开放的红色圆圈。我希望能够手动调整每组点的颜色和形状/大小。

到目前为止，我已经尝试过：

library(ggplot2)
ggplot(data=df2, aes(x = df2$Genotype, y = df2[2])) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(position = position_jitter(width = .2), shape=1, size=5) +
ylim(0,max(df2[2])+10)

但我无法弄清楚如何独立调整颜色/形状

'miR-15/16 FL'

和

'miR-15/16 cKO'

感谢您对此的任何帮助！

Answer 1

这可能会让你开始：

ggplot(data=df2, aes(x = Genotype, y = MFI)) +
  geom_boxplot(outlier.shape = NA) +
  geom_jitter(aes(col = Genotype, shape = Genotype),position = position_jitter(width = .2), size=5) +
  ylim(0,max(df2$MFI)+10)+
  scale_shape_manual(values = c(1,16))+
  scale_color_manual(values = c('red', 'black'))

我发现这个网站非常有用： http://sape.inf.usi.ch/quick-reference/ggplot2/shape

Answer 2

@Balter 击败了我……唯一的区别是我在 ggplot 调用之外设置了颜色和形状参数，以便将来进行程序访问。

library(ggplot2)

df2 <- data.frame(Genotype = c('WT','WT','WT','WT','WT',
                               'cKO','cKO','cKO','cKO','cKO'),
                  MFI=c(1191,1325,1089,1154,1147,1735,1441,1455,1560,1623))

color.groups <- c(WT="black", cKO="red")
shape.groups <- c(WT=20, cKO=21)

ggplot(data=df2, aes(x = df2$Genotype, y = df2$MFI)) +
  geom_boxplot(outlier.shape = NA) +
  geom_point(position = position_jitter(width = .2), size=5, 
             aes(color=Genotype, shape = Genotype)) +
  ylim(0,max(df2$MFI)+10) + 
  scale_color_manual(values=color.groups) +
  scale_shape_manual(values=shape.groups)

更新：

library(ggplot2)

df2 <- data.frame(Genotype = c('miR-15/16 WT','miR-15/16 WT','miR-15/16 WT','miR-15/16 WT','miR-15/16 WT',
                               'miR-15/16 cKO','miR-15/16 cKO','miR-15/16 cKO','miR-15/16 cKO','miR-15/16 cKO'),
                  MFI=c(1191,1325,1089,1154,1147,1735,1441,1455,1560,1623))

color.groups <- c(`miR-15/16 WT`="black", `miR-15/16 cKO`="red")
shape.groups <- c(`miR-15/16 WT`=20, `miR-15/16 cKO`=21)

ggplot(data=df2, aes(x = Genotype, y = MFI)) +
  geom_boxplot(outlier.shape = NA) +
  geom_point(position = position_jitter(width = .2), size=5, 
             aes(color=Genotype, shape = Genotype)) +
  ylim(0,max(df2$MFI)+10) + 
  scale_color_manual(values=color.groups) +
  scale_shape_manual(values=shape.groups)

更新2：

df2 <- structure(list(Genotype = c("miR-15/16 FL", "miR-15/16 FL", "miR-15/16 FL", 
                                   "miR-15/16 FL", "miR-15/16 FL", "miR-15/16 cKO", "miR-15/16 cKO", 
                                   "miR-15/16 cKO", "miR-15/16 cKO", "miR-15/16 cKO"),
                      `Cells/SC/Live/CD8—,, CD4+/Foxp3-,Median,<BV421-A>,CD127` = c(1191L, 1325L, 1089L, 1154L, 1147L, 1735L, 1441L, 1455L, 1560L, 1623L)),
                 .Names = c("Genotype", "Cells/SC/Live/CD8—,, CD4+/Foxp3-,Median,<BV421-A>,CD127"),
                 row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"))
colnames(df2) <- c("Genotype", "MFI")

color.groups <- c("black","red")
names(color.groups) <- unique(df2$Genotype)
shape.groups <- c(20, 21)
names(shape.groups) <- unique(df2$Genotype)

ggplot(data=df2, aes(x = Genotype, y = MFI)) +
  geom_boxplot(outlier.shape = NA) +
  geom_point(position = position_jitter(width = .2), size=5, 
             aes(color=Genotype, shape = Genotype)) +
  ylim(0,max(df2$MFI)+10) + 
  scale_color_manual(values=color.groups) +
  scale_shape_manual(values=shape.groups)