4

我正在研究一个data.table在内部使用的包。在这个包中，我有一个函数，它计算 a by 组count_by中特定变量的不同 ID 的数量。data.table在一些帮助下（R data.table: How to pass "everything possible" to by in a function?）我得到了这个按预期工作：

library(data.table)
#> Warning: package 'data.table' was built under R version 3.6.2

# create example data
sample_dt <- data.table(
    id = sort(rep(LETTERS[1:3], 3)),
    year = rep(2018L:2020L),
    x = runif(9)
)
sample_dt[id == "B" & year < 2020, x := NA_real_]

# define inner function
count_by <- function(DT, id_var, val_var, by = NULL) {
    id_var <- as.character(substitute(id_var))
    val_var <- as.character(substitute(val_var))

    eval(substitute(
        DT[!is.na(get(val_var)), .(distinct_ids = uniqueN(get(id_var))), by = by]
    ))
}

# test inner function -> works as expected
(reference <- count_by(sample_dt, id_var = id, val_var = x, by = year))
#>    year distinct_ids
#> 1: 2018            2
#> 2: 2019            2
#> 3: 2020            3

identical(count_by(sample_dt, "id", x, year)       , reference)
#> [1] TRUE
identical(count_by(sample_dt, "id", "x", year)     , reference)
#> [1] TRUE
identical(count_by(sample_dt, "id", x, "year")     , reference)
#> [1] TRUE
identical(count_by(sample_dt, "id", x, c("year"))  , reference)
#> [1] TRUE
identical(count_by(sample_dt, "id", "x", "year")   , reference)
#> [1] TRUE
identical(count_by(sample_dt, "id", "x", c("year")), reference)
#> [1] TRUE
identical(count_by(sample_dt, id, "x", year)       , reference)
#> [1] TRUE
identical(count_by(sample_dt, id, "x", "year")     , reference)
#> [1] TRUE
identical(count_by(sample_dt, id, "x", c("year"))  , reference)
#> [1] TRUE
identical(count_by(sample_dt, id, x, "year")       , reference)
#> [1] TRUE
identical(count_by(sample_dt, id, x, c("year"))    , reference)
#> [1] TRUE

由reprex 包于 2020-02-20 创建(v0.3.0)

现在我想count_by()在另一个函数中使用该函数（下面的最小示例）：

# define wrapper function
wrapper <- function(data, id_var, val_var, by = NULL) {
    data <- as.data.table(data)
    count_by(data, id_var, val_var, by)
}

# test wrapper function
wrapper(sample_dt, id_var = id, val_var = x, by = year)
#> Error in .(distinct_ids = uniqueN(get("id_var"))): could not find function "."

由reprex 包于 2020-02-20 创建(v0.3.0)

调试count_by()导致观察到，如果count_by()从 调用wrapper()，substitute(DT[...])也可以替换DT为data：

Browse[2]> substitute(
+         DT[!is.na(get(val_var)), .(distinct_ids = uniqueN(get(id_var))), by = by]
+     )
data[!is.na(get("val_var")), .(distinct_ids = uniqueN(get("id_var"))), 
    by = by]

由于data在它的功能环境中不可用，count_by()因此会对其进行评估，utils::data从而导致错误。这使问题变得清晰，但我想不出解决方案。

我需要替换整个DT[...]表达式才能by正常工作（请参阅R data.table: How to pass "everything possible" to by in a function?或将变量和名称传递给 data.table 函数）。但是我不能为了不被替换而替换整个表达式DT。

解决这个困境的方法是什么？

4

2 回答 2

1

将 NSE 排除在外适用于这个特定的示例，并大大简化了事情。但是你应该将参数作为字符串传递：

count_by <- function(DT, id_var, val_var, by = NULL) {
    DT[!is.na(get(val_var)), .(distinct_ids = uniqueN(get(id_var))), by = by]
}

wrapper <- function(data, id_var, val_var, by = NULL) {
    count_by(data, id_var, val_var, by)
}

wrapper(sample_dt, id_var = "id", val_var = "x", by = "year")

#    year distinct_ids
# 1: 2018            2
# 2: 2019            2
# 3: 2020            3
于 2020-02-20T09:03:47.377 回答
1

@chinsoon12，非常感谢！你回答几乎做到了！我仍然需要将id_var和转换val_var为字符，然后get()在调用中将这些转换为data.table- 否则，将字符串传递给id_var并且val_var不起作用。

但在更高层次上进行评估是必要的关键思想。这是供将来参考的完整答案：

# define inner function
count_by <- function(DT, id_var, val_var, by = NULL) {
    id_var <- as.character(substitute(id_var))
    val_var <- as.character(substitute(val_var))

    substitute(
        DT[!is.na(get(val_var)), .(distinct_ids = uniqueN(get(id_var))), by = by]
    )
}

# define wrapper function
wrapper <- function(data, id_var, val_var, by = NULL) {
    data <- as.data.table(data)
    expr <- eval(substitute(count_by(data, id_var, val_var, by)))
    eval(expr)
}

# test wrapper function
(reference <- (wrapper(sample_dt, id_var = id, val_var = x, by = year)))
#>    year distinct_ids
#> 1: 2018            2
#> 2: 2019            2
#> 3: 2020            3

identical(wrapper(sample_dt, "id", x, year)       , reference)
#> [1] TRUE
identical(wrapper(sample_dt, "id", "x", year)     , reference)
#> [1] TRUE
identical(wrapper(sample_dt, "id", x, "year")     , reference)
#> [1] TRUE
identical(wrapper(sample_dt, "id", x, c("year"))  , reference)
#> [1] TRUE
identical(wrapper(sample_dt, "id", "x", "year")   , reference)
#> [1] TRUE
identical(wrapper(sample_dt, "id", "x", c("year")), reference)
#> [1] TRUE
identical(wrapper(sample_dt, id, "x", year)       , reference)
#> [1] TRUE
identical(wrapper(sample_dt, id, "x", "year")     , reference)
#> [1] TRUE
identical(wrapper(sample_dt, id, "x", c("year"))  , reference)
#> [1] TRUE
identical(wrapper(sample_dt, id, x, "year")       , reference)
#> [1] TRUE
identical(wrapper(sample_dt, id, x, c("year"))    , reference)
#> [1] TRUE

# test expression in by
wrapper(sample_dt, "id", x, by = .(year_2019 = year > 2019L))
#>    year_2019 distinct_ids
#> 1:     FALSE            2
#> 2:      TRUE            3

由reprex 包于 2020-02-20 创建(v0.3.0)

于 2020-02-20T09:28:26.887 回答