R 基于数据集属性将科分配给物种

这是一个很好的递归问题.这是一个矢量化的基本R解.

find_family <- function(ID, parentID, scientificName) {
  find_family_id <- function(ID, parentID) {
    ID_new <- ifelse(!is.na(parentID), parentID, ID)
    parentID_new <- parentID[match(ID_new, ID)]
    if (all(is.na(parentID_new))) return(ID_new)
    find_family_id(ID_new, parentID_new)
  }
  family_ids <- find_family_id(ID, parentID)
  scientificName[match(family_ids, ID)]
}

dat$family <- with(dat, find_family(ID, parentID, scientificName))

dat
#    ID parentID    rank scientificName family
# 1  f1     <NA>  family           FamA   FamA
# 2  f2     <NA>  family           FamB   FamB
# 3  g1       f1   genus           GenA   FamA
# 4  g2       f1   genus           GenB   FamA
# 5  g3       f2   genus           GenC   FamB
# 6  g4       f2   genus           GenD   FamB
# 7  s1       g1 species            SpA   FamA
# 8  s2       g1 species            SpB   FamA
# 9  s3       g2 species            SpC   FamA
# 10 s4       g3 species            SpD   FamB
# 11 s5       g3 species            SpE   FamB
# 12 s6       g4 species            SpF   FamB