多元数据直观表示

各省消费项目均值条形图

省份过多,各省的名称均不能全部显示

barplot(apply(data,1,mean))#按行做均值条形图

将横轴左边旋转90度,各省的名称均可显示

barplot(apply(data,1,mean),las=3)#按行做均值条形图

利用ggplot2包作图较为美观

data %>%
  mutate(Average_Consumption = rowMeans(select(., -1), na.rm = TRUE)) %>% 
  ggplot(aes(x = reorder(row.names(data), -Average_Consumption), y = Average_Consumption)) +
  geom_bar(stat = "identity", position = position_dodge(), colour = "black", fill = "steelblue") +
  labs(title = "各省消费项目均值条形图", x = "", y = "均值") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) 

各消费项目均值条形图

按消费项目做均值图条形图

barplot(apply(data,2,mean))#按列做均值图条形图

对不同项目的条形添加不同颜色

 barplot(apply(data,2,mean),col=1:8) #按列做彩色均值图条形图

去掉食品列后的数据按列做均值条形图

barplot(apply(data[,2:8],2,mean))

按消费项目做中位数条形图

barplot(apply(data,2,median))

利用ggplot作均值条形图

data %>% summarise(across(everything(), mean, na.rm = TRUE)) %>% 
  pivot_longer(cols = everything(), names_to = "Consumption_Type", values_to = "Average") %>% 
  mutate(
    Consumption_Type=factor(Consumption_Type,level=c('食品','衣着','设备','医疗','交通','教育','居住','杂项')),
  ) %>% 
  ggplot(aes(x = Consumption_Type, y = Average, fill = Consumption_Type)) +
  geom_bar(stat = "identity", position = position_dodge(), colour = "black") +
  theme_minimal() +
  labs(title = "各消费项目均值条形图", x = "类别", y = "均值",fill = "消费种类")
Warning: There was 1 warning in `summarise()`.
ℹ In argument: `across(everything(), mean, na.rm = TRUE)`.
Caused by warning:
! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
Supply arguments directly to `.fns` through an anonymous function instead.

  # Previously
  across(a:b, mean, na.rm = TRUE)

  # Now
  across(a:b, \(x) mean(x, na.rm = TRUE))

使各条形的颜色相同

data %>% summarise(across(everything(), mean, na.rm = TRUE)) %>% 
  pivot_longer(cols = everything(), names_to = "Consumption_Type", values_to = "Average") %>% 
  mutate(
    Consumption_Type=factor(Consumption_Type,level=c('食品','衣着','设备','医疗','交通','教育','居住','杂项')),
  ) %>% 
  ggplot(aes(x = Consumption_Type, y = Average)) +
  geom_bar(stat = "identity", position = position_dodge(), colour = "black", fill = "steelblue") +
  theme_minimal() +
  labs(title = "各消费项目均值条形图", x = "类别", y = "均值")

各消费项目箱线图

boxplot函数直接作箱线图,默认每个变量(列)作一个箱线,并将全部变量的箱线在同一个图中展示。

boxplot(data)#按列做箱线图

boxplot(data,horizontal=T,las=1)#箱线图中图形按水平放置

利用ggplot函数作箱线图,需要对数据转化为长结果数据

data %>% pivot_longer(cols = 1:8, names_to = "Consumption_Type", values_to = "Value") %>% 
  mutate(
    Consumption_Type=factor(Consumption_Type,level=c('食品','衣着','设备','医疗','交通','教育','居住','杂项')),
  ) %>% 
  ggplot(aes(x = Consumption_Type, y = Value)) +
  geom_boxplot() +
  labs(title = "各消费项目箱线图", x = "", y = "消费水平") +
  theme_minimal() #  + coord_flip() 

各消费项目星相图

下图图形没有图例且部分图形的比例较小,看不到其各种变量所占比例

stars(data)                #具有图例的360度星相图

下图则有图例,可以清楚知道各省份的消费变量是什么

stars(data,key.loc=c(17,7))                #具有图例的360度星相图

此图为180度的星相图

stars(data,full=F,key.loc=c(17,7))                #具有图例的180度星相图

此图为加了颜色分辨的星相图,可以清楚看出各省份的消费变量占比

stars(data,draw.segments=T,key.loc=c(17,7))#具有图例的360度彩色圆形星相图

stars(data,full=F,draw.segments=T,key.loc=c(17,7))#具有图例的180度彩色圆形星相图

各消费项目脸谱图

下图为利用脸谱图显示各省份的消费分布图

aplpack::faces(data)

effect of variables:
 modified item       Var   
 "height of face   " "食品"
 "width of face    " "衣着"
 "structure of face" "设备"
 "height of mouth  " "医疗"
 "width of mouth   " "交通"
 "smiling          " "教育"
 "height of eyes   " "居住"
 "width of eyes    " "杂项"
 "height of hair   " "食品"
 "width of hair   "  "衣着"
 "style of hair   "  "设备"
 "height of nose  "  "医疗"
 "width of nose   "  "交通"
 "width of ear    "  "教育"
 "height of ear   "  "居住"

下图则整理了顺序

aplpack::faces(data[,2:8],ncol.plot=7)#去掉第一个变量按每行7个做脸谱图

effect of variables:
 modified item       Var   
 "height of face   " "衣着"
 "width of face    " "设备"
 "structure of face" "医疗"
 "height of mouth  " "交通"
 "width of mouth   " "教育"
 "smiling          " "居住"
 "height of eyes   " "杂项"
 "width of eyes    " "衣着"
 "height of hair   " "设备"
 "width of hair   "  "医疗"
 "style of hair   "  "交通"
 "height of nose  "  "教育"
 "width of nose   "  "居住"
 "width of ear    "  "杂项"
 "height of ear   "  "衣着"

下图挑选了六省份的消费分布图

aplpack::faces(data[c(1,9,19,28,29,30),])#选择第1,9,19,28,29,30个观测的多元数据做脸谱图

effect of variables:
 modified item       Var   
 "height of face   " "食品"
 "width of face    " "衣着"
 "structure of face" "设备"
 "height of mouth  " "医疗"
 "width of mouth   " "交通"
 "smiling          " "教育"
 "height of eyes   " "居住"
 "width of eyes    " "杂项"
 "height of hair   " "食品"
 "width of hair   "  "衣着"
 "style of hair   "  "设备"
 "height of nose  "  "医疗"
 "width of nose   "  "交通"
 "width of ear    "  "教育"
 "height of ear   "  "居住"

各消费项目雷达图

ggplot2的扩展包ggiraphExtra能作雷达图

data[c(1,9,19,28,29,30),] %>% 
  mutate(省份=rownames(.)) %>% 
  ggRadar(aes(group = 省份)) 

各消费项目调和曲线图

下图为所有省份的消费调和曲线图

source("msaR.R")#加自定义函数
msa.andrews(data)#绘制调和曲线图

下图为筛选出来的六个省份曲线图

msa.andrews(data[c(1,9,19,28,29,30),])

下图为全部省份的调和曲线图,该图的部分曲线过于密集,不便于观察

library(andrews) 
Warning: package 'andrews' was built under R version 4.3.3
See the package vignette with `vignette("andrews")`
andrews(data,clr=5,ymax=6)

选择第1,9,19,28,29,30个观测的多元数据做调和曲线图,下图则更为清晰的显示出所选六个省份的曲线,其中

andrews(data[c(1,9,19,28,29,30),],clr=5,ymax=6)