r - 使用查找表创建新变量

如果我们left_join基于“性别”，“年龄”在第一个和查找数据集之间进行比较，则会得到两个“长度”列，在这些列之间进行比较，并使用ifelse或创建一个新列case_when

library(dplyr)
left_join(df1, lookup, by = c('sex', 'age')) %>%
    transmute(id, sex, age, 
      growth.rate = case_when(length.x <= length.y ~ "Low", 
        TRUE ~ "Normal"), length = length.x)
#   id    sex age growth.rate length
#1   1 Female   1         Low     45
#2   2 Female   2      Normal     54
#3   3 Female   3         Low     56
#4   4 Female   4      Normal     60
#5   5 Female   5         Low     60
#6   6 Female   6         Low     61
#7   7 Female   7         Low     63
#8   8   Male   1      Normal     55
#9   9   Male   2         Low     54
#10 10   Male   3      Normal     58
#11 11   Male   4      Normal     61
#12 12   Male   5      Normal     65
#13 13   Male   6         Low     63
#14 14   Male   7         Low     65
#15 15   Male   8      Normal     67
#16 16   Male   9      Normal     68
#17 17   Male  10         Low     69

在中data.table，可以使其更紧凑

library(data.table)
setDT(df1)[lookup, growth.rate := fcase(length <= i.length, "Low", 
           "Normal"), on = .(sex, age)]

或带有索引

setDT(df1)[lookup, growth.rate := 
       c("Normal", "Low")[1 + (length <= i.length)], on = .(sex, age)]

数据

df1 <- structure(list(id = 1:17, sex = c("Female", "Female", "Female", 
"Female", "Female", "Female", "Female", "Male", "Male", "Male", 
"Male", "Male", "Male", "Male", "Male", "Male", "Male"), age = c(1L, 
2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L
), length = c(45L, 54L, 56L, 60L, 60L, 61L, 63L, 55L, 54L, 58L, 
61L, 65L, 63L, 65L, 67L, 68L, 69L)), class = "data.frame", row.names = c(NA, 
-17L))

lookup <- structure(list(sex = c("Female", "Female", "Female", "Female", 
"Female", "Female", "Female", "Male", "Male", "Male", "Male", 
"Male", "Male", "Male", "Male", "Male", "Male"), age = c(1L, 
2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L
), length = c(50L, 53L, 56L, 58L, 60L, 61L, 63L, 50L, 54L, 57L, 
60L, 62L, 63L, 65L, 66L, 67L, 69L)), class = "data.frame", row.names = c(NA, 
-17L))