rm(list=ls())
f<-read.xlsx("Released 2019-nCoV Genome Sequences.xlsx",1, encoding = "UTF-8")
table(f$序列完整度)
f_complete<-f[f$序列完整度=="Complete",]
f_complete$nation<-unlist(lapply(f_complete$采样地点,function(x) gsub(" ","",stringr::str_split(x,"/",simplify = TRUE)[,1])))
nation<-unique(f_complete$nation)
a<-f_complete[,c('采样日期','nation')]
b<-plyr::ddply(a,.(采样日期,nation),nrow)
c<-reshape2::melt(b)
group=factor((c$nation))
ggplot2::ggplot(c,aes(采样日期,nation))+geom_point(aes(colour=group,size=value*10))+theme_bw()+theme(legend.position = "none",axis.text.x = element_text(angle = 45,hjust = 1),axis.text.y = element_text(size = 14))
大小表示数目
