带数据点的 ggplot boxplot：如何根据两个因素控制点 COLOR 和 SHAPE？

Question

我可以成功地将颜色分配给一个因素（性别）水平。但我无法弄清楚如何将形状也分配给其他因素 (age_cat) 级别并在所需位置添加第二个图例。我尝试在不同位置添加 'shape=age_cat'...但无论我尝试什么，都会扭曲情节！

我的示例数据、代码和图表如下。

df = data.frame(sex = c(1,1,1,1,1, 2,2,2,2,2),
                age_cat = c(1,1,1, 2,2,2,  1,1,1, 2),
                score_type = c(1,2, 1,2, 1,2, 1,2, 1,2),
                score = c(25,28,18,20,30, 37,40,35,43,45))

df$sex <- factor((df$sex))
df$age_cat <- factor((df$age_cat))
df$score_type <- factor((df$score_type))

windows(width=7, height=7 )

df %>%
  ggplot( aes(x=score_type, y=score)) +
  geom_boxplot(aes(color=sex),outlier.shape = NA, size=1.5, show.legend = F) +
  geom_point(aes(color=sex), position=position_jitterdodge(dodge.width=0.9), size=3) +
  scale_color_manual(values=c("#0072B2", "#CC79A7"), name="", labels=c("Male", "Female")) +
  
  scale_shape_manual(name="", labels=c('Younger', 'Older'), values=c(1, 17)) +   # ??? How to assign shape ???
  
  theme_bw()+
  theme(panel.border = element_blank(), axis.ticks = element_blank(),
        legend.position=c(0.9, 0.65), legend.text=element_text(size=11), legend.title=element_text(size=11.5),
        panel.grid.major.x = element_blank() ,
        plot.title = element_text(size=11, face = "bold"), axis.title=element_text(size=13),
        axis.text.y = element_text(size=11),
        axis.text.x = element_text(size=11),
        plot.margin = unit(c(0.5,0.2,0,0.2), "cm")) +
  
  labs(title= "", x = "",y = "Score") +
  scale_y_continuous(breaks=c(0, 20, 40, 60, 80, 100), labels=c('0', '20', '40', '60', '80', '100')) +
  expand_limits(x=5, y=70) +
  scale_x_discrete(labels = c("A", "B")) + 
 
  coord_cartesian(clip = "off")

Answer 1

你只需要在geom_point的美学中指定shape = age_cat和group = sex即可。

library(purrr)
library(ggplot2)

df %>%
  ggplot( aes(x=score_type, y=score)) +
  geom_boxplot(aes(color=sex),outlier.shape = NA, size=1.5, show.legend = F) +
  geom_point(aes(color=sex, shape = age_cat, group = sex),
 position=position_jitterdodge(dodge.width=0.9), size=3) +
  scale_color_manual(values=c("#0072B2", "#CC79A7"), name="",
 labels=c("Male", "Female")) +
  scale_shape_manual(name="", labels=c('Younger', 'Older'),
values=c(1, 17)) +
  theme_bw()+
  theme(panel.border = element_blank(), axis.ticks = element_blank(),
        legend.position=c(0.9, 0.65), legend.text=element_text(size=11),
 legend.title=element_text(size=11.5),
        panel.grid.major.x = element_blank() ,
        plot.title = element_text(size=11, face = "bold"),
 axis.title=element_text(size=13),
        axis.text.y = element_text(size=11),
        axis.text.x = element_text(size=11),
        plot.margin = unit(c(0.5,0.2,0,0.2), "cm")) +
  labs(title= "", x = "",y = "Score") +
  scale_y_continuous(breaks=c(0, 20, 40, 60, 80, 100),
labels=c('0', '20', '40', '60', '80', '100')) +
  expand_limits(x=5, y=70) +
  scale_x_discrete(labels = c("A", "B")) + 
  coord_cartesian(clip = "off")

带数据点的 ggplot boxplot：如何根据两个因素控制点 COLOR 和 SHAPE？

ggplot boxplot with data points: how to control both point COLOR and SHAPE based on two factors?

r

ggplot2

boxplot