有趣的数据可视化:R语言ggplot2包画云雨图展示不同地质时代恐龙的体长

用户7010445

发布于 2024-04-22 12:48:47

820

发布于 2024-04-22 12:48:47

文章被收录于专栏：小明的数据分析笔记本小明的数据分析笔记本

数据来源

https://www.kaggle.com/datasets/kjanjua/jurassic-park-the-exhaustive-dinosaur-dataset?resource=download

部分数据截图

读取数据对数据进行预处理

library(tidyverse)

read_csv("2024.data/20240421/data.csv") %>% 
  mutate(X1=str_extract(period,"^[A-z]+ [A-z]+"),
         X2=str_extract(period,"[0-9]+") %>% as.numeric(),
         X3=str_extract(period,"-[0-9]+") %>% 
           str_replace("-","") %>% as.numeric()) %>% 
  mutate(X4=(X2+X3)/2) %>% 
  mutate(X5=str_replace(length,"m","") %>% 
           as.numeric()) %>% 
  na.omit() -> dat

dat %>% pull(X1) %>% table()

这里的地质时期有

Late Triassic 三叠纪晚期 Early Jurassic 侏罗纪早期 Mid Jurassic Late Jurassic Early Cretaceous 白垩纪早期 Late Cretaceous 白垩纪晚期

箱线图展示这几个地质时期的时间

dat %>% 
  mutate(X6="A") %>% 
  mutate(X1=factor(X1,levels = c("Late Triassic","Early Jurassic",
                                 "Mid Jurassic","Late Jurassic",
                                 "Early Cretaceous","Late Cretaceous"))) %>% 
  ggplot(aes(x=X6,y=X4))+
  geom_boxplot(aes(fill=X1),position = position_dodge(0),
               show.legend = FALSE) +
  scale_y_continuous(breaks = dat %>% 
                       group_by(X1) %>% 
                       summarise(median_value=median(X4)) %>% 
                       arrange(median_value) %>% 
                       ungroup() %>% 
                       pull(median_value),
                     labels = dat %>% 
                       group_by(X1) %>% 
                       summarise(median_value=median(X4)) %>% 
                       arrange(median_value) %>% 
                       mutate(new_col=paste0(X1,"\n",median_value)) %>% 
                       pull(new_col))+
  theme_bw(base_size = 20)+
  theme(panel.grid = element_blank(),
        axis.text.x = element_blank(),
        axis.ticks.x = element_blank())+
  geom_segment(data=dat %>% 
              group_by(X1) %>% 
              summarise(median_value=median(X4)) %>% 
              arrange(median_value) %>% 
              ungroup(),
            aes(x=-Inf,xend=Inf,y=median_value,yend=median_value),
            lty="dashed")+
  # geom_rect(data = dat %>% 
  #             group_by(X1) %>% 
  #             summarise(max_value=max(X4),
  #                       min_value=min(X4)) %>% 
  #             ungroup(),
  #           aes(xmin=-Inf,xmax=Inf,ymin=min_value,ymax=max_value,fill=X1),
  #           inherit.aes = FALSE,
  #           alpha=0.4)+
  labs(x=NULL,y="Million years ago")

云雨图展示恐龙的体长

dat %>% 
  mutate(X1=factor(X1,levels = c("Late Triassic","Early Jurassic",
                                 "Mid Jurassic","Late Jurassic",
                                 "Early Cretaceous","Late Cretaceous"))) -> dat
dat
ggplot(dat, aes(x = X1, y = X5, fill = X1)) + 
  sm_raincloud() +
  theme(text = element_text(size = 13),
        axis.text.x = element_text(angle=30,hjust=1,vjust=1))+
  labs(x=NULL,y=NULL)+
  ggwater2(text = "小明的数据分析笔记本",
           scale=0.6)