【R语言】两个/N个数据合并merge函数

两个数据框合并

data1=data.frame(
  names = c('AAA',       'CCC', 'DDD', 'EEE',  'FFF' ),
  logFC = c(3, -0.4, 5, 0.4, -3 ),
  bmi = c('正常',        '正常','超重','肥胖','正常')
)
data2=data.frame(
  names = c('AAA','BBB',  'CCC', 'DDD', 'EEE'          ),
  gender = c(1, 2, 1, 2, 1),    #1=男 2=女
  bmi = c('正常','低体重','正常','超重','肥胖'          )
)

merge(data1,data2,all=TRUE)
# 同样结果，可以不用加by
merge(data1,data2,all=TRUE,by = intersect(names(data1), names(data2)))

names	bmi	logFC	gender
AAA	正常	3	1
BBB	低体重	NA	2
CCC	正常	-0.4	1
DDD	超重	5	2
EEE	肥胖	0.4	1
FFF	正常	-3	NA

dplyr::full_join函数情况

dplyr::full_join(data1,data2)

dplyr::full_join函数情况，如果加by，会出现重复的变量名为 .x .y

dplyr::full_join(data1,data2,by=c("names"))

> dplyr::full_join(data1,data2)      
Joining, by = c("names", "bmi")
  names logFC    bmi gender
1   AAA   3.0   正常      1
2   CCC  -0.4   正常      1
3   DDD   5.0   超重      2
4   EEE   0.4   肥胖      1
5   FFF  -3.0   正常     NA
6   BBB    NA 低体重      2

names	logFC	bmi.x	gender	bmi.y
AAA	3	正常	1	正常
CCC	-0.4	正常	1	正常
DDD	5	超重	2	超重
EEE	0.4	肥胖	1	肥胖
FFF	-3	正常	NA	NA
BBB	NA	NA	2	低体重

R merge() 与dplyr join()

dplyr	base
inner_join(df1, df2)	merge(df1, df2)
left_join(df1, df2)	merge(df1, df2, all.x = TRUE)
right_join(df1, df2)	merge(df1, df2, all.y = TRUE)
full_join(df1, df2)	merge(df1, df2, all = TRUE)
semi_join(df1, df2)	df1[df1$x$x, , drop = FALSE]
anti_join(df1, df2)	df1[!df1$x$x, , drop = FALSE]

# 假设相同变量，里面得内容不一样，如AAA-BMI-常1
data2=data.frame(
  names = c('AAA','BBB',  'CCC', 'DDD', 'EEE'          ),
  gender = c(1, 2, 1, 2, 1),    #1=男 2=女
  bmi = c('正常1','低体重','正常','超重','肥胖'          )
)

merge(data1,data2,all=TRUE,by = intersect(names(data1), names(data2)))
# 结果会另起一行

names	bmi	logFC	gender
AAA	正常	3	NA
AAA	正常1	NA	1
BBB	低体重	NA	2
CCC	正常	-0.4	1
DDD	超重	5	2
EEE	肥胖	0.4	1
FFF	正常	-3	NA

多个数据框合并

data1=data.frame(
  names = c('AAA',       'CCC', 'DDD', 'EEE',  'FFF' ),
  logFC = c(3, -0.4, 5, 0.4, -3 ),
  bmi = c('正常',        '正常','超重','肥胖','正常')
)
data2=data.frame(
  names = c('AAA','BBB',  'CCC', 'DDD', 'EEE'          ),
  gender = c(1, 2, 1, 2, 1),    #1=男 2=女
  bmi = c('正常','低体重','正常','超重','肥胖'          )
)

data3=data.frame(
  names = c('GGG'         ),
  gender = c("男"),    #1=男 2=女
  bmi = c('正常'      )
)

file=ls(pattern = "data")
ALL1=list(data1,data2,data3)

multimerge<-function(dat=list(),...){
  if(length(dat)<2)return(as.data.frame(dat))
  mergedat<-dat[[1]]
  dat[[1]]<-NULL
  for(i in dat){
    mergedat<-merge(all=TRUE,mergedat,i,...)
  }
  return(mergedat)
}
multimerge(ALL1)