tidyr的complete和expand函数

对complete和expand有新的理解

准备包和数据

if(!require(tidyr))install.packages("tidyr")
library(tidyr)
df <- data.frame(
  group = c(1:2, 1),
  item_id = c(1:2, 5),
  item_name = c("a", "a", "b"),
  value1 = 2:4,
  value2 = 4:6
)

测试函数

complete(df,group,nesting(item_id,item_name))
## # A tibble: 6 x 5
##   group item_id item_name value1 value2
##   <dbl>   <dbl> <fct>      <int>  <int>
## 1     1       1 a              2      4
## 2     1       2 a             NA     NA
## 3     1       5 b              4      6
## 4     2       1 a             NA     NA
## 5     2       2 a              3      5
## 6     2       5 b             NA     NA

nesting括号内的列名不参与扩展，但是可以跟随重复，未列在代码中的列扩展出的行成为NA

b=complete(df,group,item_id,item_name)[1:3]

a=expand(df,group,item_id,item_name)

identical(a,b)
## [1] TRUE