在 r 中使用 lapply 函数和列表

d1 <- data.frame(col_one = c(1,2,3),col_two = c(4, 5, 6))
d2 <- data.frame(col_one = c(1, 1, 1), col_two = c(6, 5, 4))
d3 <- data.frame(col_one = c(7, 1, 1), col_two = c(8, 5, 4))
my.list <- list(d1, d2,d3)

for (i in 1:3) {
  table<- lapply(my.list, function(data, count) {
    sql <-
      #sqldf(
        paste0(
          "select *,count(col_one) from data where col_one = ",
          count," group by col_one"
        )
      #)
    print(sql)
  },
  count = i)
}

output:

[1] "select *,count(col_one) from data where col_one = 1 group by col_one"
[1] "select *,count(col_one) from data where col_one = 1 group by col_one"
[1] "select *,count(col_one) from data where col_one = 1 group by col_one"
[1] "select *,count(col_one) from data where col_one = 2 group by col_one"
[1] "select *,count(col_one) from data where col_one = 2 group by col_one"
[1] "select *,count(col_one) from data where col_one = 2 group by col_one"
[1] "select *,count(col_one) from data where col_one = 3 group by col_one"
[1] "select *,count(col_one) from data where col_one = 3 group by col_one"
[1] "select *,count(col_one) from data where col_one = 3 group by col_one"

期待：

[1] "select *,count(col_one) from data where col_one = 1 group by col_one"
[1] "select *,count(col_one) from data where col_one = 2 group by col_one"
[1] "select *,count(col_one) from data where col_one = 3 group by col_one"

我该如何改进？我希望运行 SQL 来创建我想要的新数据集，但它不成功，我可以指定了解与 SQL 语句相关的列表的索引。还有其他简单的方法吗？

我已经尝试过其中一种方法。

d1 <- data.frame(col_one = c(1,2,3),col_two = c(4, 5, 6))
d2 <- data.frame(col_one = c(3, 2, 1), col_two = c(6, 5, 4))
d3 <- data.frame(col_one = c(7, 2, 1), col_two = c(8, 5, 4))
my.list <- list(d1, d2,d3)
seq_along(x)
#for (i in 1:3) {
  table<- lapply(seq_along(my.list), function(index) {
    sql <-
      sqldf(
        paste0(
          "select *,count(col_one) from my.list where col_one = ",
          index," group by col_one"
        )
      )
    print(sql)
  })
#}

output:

[1] "select *,count(col_one) from my.list where col_one = 1 group by col_one"
[1] "select *,count(col_one) from my.list where col_one = 2 group by col_one"
[1] "select *,count(col_one) from my.list where col_one = 3 group by col_one"

但是，它不会找到运行 SQL 的数据集。

d1 <- data.frame(col_one = c(1,2,3),col_two = c(4, 5, 6))
d2 <- data.frame(col_one = c(1, 1, 1), col_two = c(6, 5, 4))
d3 <- data.frame(col_one = c(7, 1, 1), col_two = c(8, 5, 4))
my.list <- list(d1, d2,d3)
table<- mapply(function(data, count) {
  sql <-
    sqldf(
    paste0(
      "select *,count(col_one) from data where col_one = ",
      count," group by col_one"
    )
  )
  print(sql)
}, my.list, 1
)

如果我理解正确的话，OP想要创建列联表col_one对于每个 data.framesmy.list，即他想知道值 1、2 或 3 分别出现了多少次col_one在每个数据帧中。

正如中所解释的我的答案 to OP的另一个问题并按照建议G·格洛腾迪克，将 data.frames 与结构相同在一个大的 data.table 中，而不是将它们单独放在一个列表中。顺便说一句，还有第三个问题（“如何使用 sqldf 循环数据帧？”）OP 寻求有关 data.frames 列表的帮助。

要将 data.frames 合并到一个大的 data.table 中，rbindlist()使用函数。注意添加的 id 列df标识每行的原始 data.frame。

library(data.table)
rbindlist(my.list, idcol = "df")

   df col_one col_two
1:  1       1       4
2:  1       2       5
3:  1       3       6
4:  2       1       6
5:  2       1       5
6:  2       1       4
7:  3       7       8
8:  3       1       5
9:  3       1       4

现在我们可以轻松计算聚合：

rbindlist(my.list, idcol = "df")[, count_col_one := .N, by = .(df, col_one)][]

   df col_one col_two count_col_one
1:  1       1       4             1
2:  1       2       5             1
3:  1       3       6             1
4:  2       1       6             3
5:  2       1       5             3
6:  2       1       4             3
7:  3       7       8             1
8:  3       1       5             2
9:  3       1       4             2

This data.table语句计算每个单独值的出现次数col_one对于每个df通过使用特殊符号.N并通过分组df and col_one.

在这个问题中，OP 仅要求计算 1、2 或 3 的出现次数col_one。如果确实如此，则需要删除 7 的值。这可以通过过滤结果来完成：

rbindlist(my.list, idcol = "df")[, count_col_one := .N, by = .(df, col_one)][
  col_one %in% 1:3]