ggsankey绘制桑基图(2)

R语言数据分析指南

发布于 2022-12-20 19:48:30

6570

发布于 2022-12-20 19:48:30

❝本节再来介绍使用「ggsankey」绘制桑基图，下面小编就通过一个具体案例来介绍如何绘制此图；

library(tidyverse)
library(ggsankey)
library(wesanderson)

导入数据

records <- read_csv('records.txt')
drivers <- read_csv('drivers.txt')

定义调色板

pal <- wes_palette("Zissou1")

设置主题

theme_set(
  theme_minimal() +
    theme(
      legend.title = element_blank(),
      legend.key.size = unit(1, "line"),
      axis.title = element_blank(),
      plot.background = element_rect(fill = "grey97", color = NA),
      plot.margin = margin(10, 10, 10, 10),
      plot.title = element_text(face = "bold"),
      plot.subtitle = element_text(color = "grey30")
    )
)

数据清洗

drivers_top <- drivers %>%
  filter(position < 6) %>% 
  mutate(
    player_rec = paste0(player, " - ", total, " records"),
    player_rec = fct_reorder(player_rec, -total)
  )

转换数据格式

df <- records %>% 
  filter(player %in% drivers_top$player) %>% 
  make_long(player, track) %>%  #使用make_long函数转化为ggsankey所需要的格式，
  left_join(drivers_top %>% 
              distinct(player,position),
            by = c("node" = "player")) %>% 
  mutate(color = if_else(!is.na(next_node), pal[position], "white"))

数据可视化

ggplot(df,aes(x = x, next_x = next_x, node = node,
                           next_node = next_node, fill = color,label = node)) +
  geom_sankey() +
  # 设置文本
  geom_sankey_text(aes(hjust = if_else(x == "track", 1, 0)),size = 3) +
  scale_fill_identity() +
  coord_cartesian(expand = FALSE, clip = "off") + 
  theme(
    legend.position = "none",
    axis.text = element_blank(),
    panel.grid = element_blank(),
    plot.title = element_text(hjust = 0.5, size = 23, face = "bold"),
    plot.caption = element_text(hjust = 0.5)
  )