使用循环根据列拆分数据集

Question

我一直在尝试获得一个循环，该循环根据列值将数据集拆分为多个数据集。但是，数据集是我以前从未处理过的格式（即包含列表和 data.tables 的列表）。数据集可通过以下方式重现：

table1 <- data.table::data.table(Scenario = 
                            c(rep(
                              c("A", "B", "C", "D"), 
                              4)),
                          A = c(
                            rep("x", 4), rep("b", 4), rep("s", 4),
                            rep("u", 4)),
                          Correlation = c(1, 0.125, 0.1, 0, 
                                          0.125, 1, 0.2, 0, 
                                          0.1, 0.2,   1, 0, 
                                          0,     0,   0, 1),
                          Matrix = "IM",
                          stringsAsFactors = FALSE,
                          check.names = FALSE)
table2 <- data.table::data.table(Scenario = 
                         c(rep(
                           c("A", "B", "C", "D"), 
                           4)),
                       A = c(
                         rep("x", 4), rep("b", 4), rep("s", 4),
                         rep("u", 4)),
                       Correlation = c(1, 0.125, 0.1, 0, 
                                       0.125, 1, 0.2, 0, 
                                       0.1, 0.2,   1, 0, 
                                       0,     0,   0, 1),
                       Matrix = "IM",
                       stringsAsFactors = FALSE,
                       check.names = FALSE)

table3 <- data.table::data.table(Scenario = 
                         c(rep(
                           c("A", "B", "C", "D"), 
                           4)),
                       A = c(
                         rep("x", 4), rep("b", 4), rep("s", 4),
                         rep("u", 4)),
                       Correlation = c(1, 0.125, 0.1, 0, 
                                       0.125, 1, 0.2, 0, 
                                       0.1, 0.2,   1, 0, 
                                       0,     0,   0, 1),
                       Matrix = "IM",
                       stringsAsFactors = FALSE,
                       check.names = FALSE)

list1 <- list("a" = "2019", "b" = "2020", "c" = "2021")
list2 <- list("a" = "test", "b" = "test", "c" = "test")

input_data <- list("table1" = table1, "table2" = table2, "table3" = table3, 
"list1"=list1, "list2" = list2)

我需要一个循环来根据场景列中的所有唯一实例拆分此数据集。第一个数据集（对于场景值“A”）可通过以下方式重现：

table1 <- data.table::data.table(Scenario = 
                               c(rep(
                                 c("A"), 
                                 4)),
                             A = c(
                               rep("x", 1), rep("b", 1), rep("s", 1),
                               rep("u", 1)),
                             Correlation = c(1, 0.125, 0.1, 0 ),
                             Matrix = "IM",
                             stringsAsFactors = FALSE,
                             check.names = FALSE)
table2 <- data.table::data.table(Scenario = 
                               c(rep(
                                 c( "A"), 
                                 4)),
                             A = c(
                               rep("x", 1), rep("b", 1), rep("s", 1),
                               rep("u", 1)),
                             Correlation = c(1, 0.125, 0.1, 0),
                             Matrix = "IM",
                             stringsAsFactors = FALSE,
                             check.names = FALSE)

table3 <- data.table::data.table(Scenario = 
                               c(rep(
                                 c("A"), 
                                 4)),
                             A = c(
                               rep("x", 1), rep("b", 1), rep("s", 1),
                               rep("u", 1)),
                             Correlation = c(1, 0.125, 0.1, 0),
                             Matrix = "IM",
                             stringsAsFactors = FALSE,
                             check.names = FALSE)

list1 <- list("a" = "2019", "b" = "2020", "c" = "2021")
list2 <- list("a" = "test", "b" = "test", "c" = "test")

input_data <- list("table1" = table1, "table2" = table2, "table3" = table3, 
               "list1"=list1, "list2" = list2)

如果需要更多信息，请告诉我。

Answer 1

您可以编写一个包装lapply 的函数，利用inherits 检查列表中每个对象的类型。如果该对象继承自 data.frame 并包含一个名为 Scenario 的列，那么您可以简单地对其进行子集化。不是数据框或数据表的项目，或者没有称为Scenario 的列的项目保持不变：

get_scenario <- function(S) {
  lapply(input_data, function(x) {
    if(!inherits(x, "data.frame")) 
      return(x) 
    else if(!"Scenario" %in% names(x))
      return(x)
    
    return(x[x$Scenario == S,])
    })
}

这允许：

get_scenario("A")
#> $table1
#>    Scenario A Correlation Matrix
#> 1:        A x       1.000     IM
#> 2:        A b       0.125     IM
#> 3:        A s       0.100     IM
#> 4:        A u       0.000     IM
#> 
#> $table2
#>    Scenario A Correlation Matrix
#> 1:        A x       1.000     IM
#> 2:        A b       0.125     IM
#> 3:        A s       0.100     IM
#> 4:        A u       0.000     IM
#> 
#> $table3
#>    Scenario A Correlation Matrix
#> 1:        A x       1.000     IM
#> 2:        A b       0.125     IM
#> 3:        A s       0.100     IM
#> 4:        A u       0.000     IM
#> 
#> $list1
#> $list1$a
#> [1] "2019"
#> 
#> $list1$b
#> [1] "2020"
#> 
#> $list1$c
#> [1] "2021"
#> 
#> 
#> $list2
#> $list2$a
#> [1] "test"
#> 
#> $list2$b
#> [1] "test"
#> 
#> $list2$c
#> [1] "test"

如果您希望所有子组都成为一个超级列表，您可以这样做：

lapply(c("A", "B", "C"), get_scenario)