二维数据空间R绘图
最后发布时间:2020-06-06 13:13:50
浏览量:
类别变量与类别变量
library(tidyverse)
library(treemap)
# install.packages("treemap")
cjb <- read.csv("/home/wy/Downloads/cjb.csv",
header = TRUE,
stringsAsFactors = FALSE,
fileEncoding = "UTF-8")
cjb %>%
group_by(wlfk,bj,xb) %>%
summarise(count=n()) %>%
as.data.frame() %>%
treemap(
index = c("wlfk","bj","xb"),
vSize = "count",
vColor="count",
type = "value"
)
数值变量与数值变量
ggplot(cjb,aes(
x=sx,
y=sw,
shape = wlfk,
color =wlfk
))+
geom_point(size = 2)+
labs(x= "数学",
y="生物",
color="文理分科",
shape="文理分科")
GGally::ggpairs(cjb,columns =4:12 )
计算相关系数以及绘图
cor_coef <- cor(cjb[,4:12])
cor_coef <- round(cor_coef,2)
cor_coef %>%
as.data.frame()
添加列
cor_coef %>%
as.data.frame() %>%
rownames_to_column(var="km1")
行宽变换
cor_coef %>%
as.data.frame() %>%
rownames_to_column(var="km1") %>%
gather(key = km2,value = cor_num,-km1)
数据分箱
cor_coef %>%
as.data.frame() %>%
rownames_to_column(var="km1") %>%
gather(key = km2,value = cor_num,-km1) %>%
mutate(cor_level = cut(cor_num,
breaks = c(0,0.3,0.5,0.8,1),
right = FALSE))
绘图
cor_coef %>%
as.data.frame() %>%
rownames_to_column(var="km1") %>%
gather(key = km2,value = cor_num,-km1) %>%
mutate(cor_level = cut(cor_num,
breaks = c(0,0.3,0.5,0.8,1),
right = FALSE)) %>%
ggplot(aes(x=km1,y=km2,fill=cor_level))+
geom_tile(color="white",size=1.5)+
geom_text(aes(label=format(cor_num,digits = 2)))+
scale_fill_brewer(palette = "YlGn",name="相关系数区间")
类别变量与数值变量
看看不同班级数学成绩分布
cjb$bj <- factor(cjb$bj)
ggplot(cjb,aes(x=bj,y=sx,fill=bj))+
geom_boxplot(outlier.colour = "red",
outlier.shape = 3,
outlier.size = 1)+
labs(x="班级",y="数学成绩")+
theme(legend.position = "none")
library(ggridges)
library(viridis)
ggplot(cjb,aes(x=sx,y=bj,fill = ..x..))+
geom_density_ridges_gradient(scale=2,
rel_min_height=0.01,
gradient_lwd = 1)+
scale_fill_viridis(name="数学成绩",
option = "C")+
labs(x="数学",y="班级")