问多条件去重

EN

library(dplyr)
myDF %>%
     group_by(Tissue, Food, Group) %>%
     mutate(n = n()) %>% arrange(Tissue, Food, Eggphase, Name, desc(n)) %>% 
     ungroup %>%
     distinct(Tissue, Food, Eggphase, Name, .keep_all = TRUE) %>%
     select(-n)

myDF <- read.table(text="Tissue Food Eggphase Name Group
  wb fl after Kia a
  wb fl after Kia c
  wb wf before Kia b
  wb fl before Lucy c
  wb fl after Lucy b
  wb fl after Lucy c
  wb fl yolkdep Jess c
  wb fl yolkdep Betty a
  wb fl yolkdep Betty b", header = TRUE)

# I usually have the following setting active: options(stringsAsFactors=F)
# The following might error without such a setting

# Create a var that indicates a duplicate or a record with a duplicate
myDF$duplicate <- duplicated(myDF[,c('Name','Eggphase','Tissue','Food')])
myDF$duplicate <- ifelse(duplicated(myDF[,c('Name','Eggphase','Tissue','Food')],fromLast=T),yes=T, no=myDF$duplicate)

# Count eggphases by group 
eggphaseCount <- with(myDF,aggregate(x=list(Group_phaseCt=Eggphase),by=list(Group=Group),FUN=function(x) length(unique(x))))
# Merge to DF
myDF <- merge(myDF,eggphaseCount,by='Group',all=T)

# Get the max # of egphases by name
scale <- with(myDF,aggregate(x=list(PhaseMax=Group_phaseCt),by=list(Name=Name),FUN=max))
# Add to DF
myDF <- merge(myDF,scale,by='Name',all=T)

# Take the ratio
myDF$bestRatio <- with(myDF,Group_phaseCt/PhaseMax)
# Keep only those that aren't a duplicate, or are a duplicate and have the highest ratio
myDF2 <- myDF[with(myDF,which(duplicate==FALSE | (duplicate==TRUE & bestRatio==1))),]

# Create a var that indicates a duplicate or a record with a duplicate
myDF$duplicate <- duplicated(myDF[,c('Name','Eggphase','Tissue','Food')])
#this won't tell you that the first entry og the combination is double
# so need to make them check against the previous row
myDF$duplicate <- ifelse(duplicated(myDF[,c('Name','Eggphase','Tissue','Food')],fromLast=T),yes=T, no=myDF$duplicate)

# Count eggphases by group 
eggphaseCount <- with(myDF,aggregate(x=list(Group_phaseCt=Eggphase),by=list(Group=Group),FUN=function(x) length(unique(x))))
# Merge to DF
myDF <- merge(myDF,eggphaseCount,by='Group',all=T)

# Get the max # of egphases by name
scale <- with(myDF,aggregate(x=list(PhaseMax=Group_phaseCt),by=list(Name=Name),FUN=max))
# Add to DF
myDF <- merge(myDF,scale,by='Name',all=T)

# Take the ratio
myDF$bestRatio <- with(myDF,Group_phaseCt/PhaseMax)

# make new df without duplicates
myDF2 <- myDF %>% 
#arrange in a way that the first duplicate is from the group with the most eggphases
#and the name appears in the most egg phases 
  arrange(Tissue, Food, Eggphase, Name, Group, desc(Group_phaseCt), desc(PhaseMax)) %>% 
#select only distinct rows according to specified var keep all others
  distinct(Tissue, Food, Eggphase, Name, .keep_all = TRUE)