r - 展平具有复杂嵌套结构的列表

Question

我有一个包含以下示例结构的列表:

> dput(test)
structure(list(id = 1, var1 = 2, var3 = 4, section1 = structure(list(
    var1 = 1, var2 = 2, var3 = 3), .Names = c("var1", "var2", 
"var3")), section2 = structure(list(row = structure(list(var1 = 1, 
    var2 = 2, var3 = 3), .Names = c("var1", "var2", "var3")), 
    row = structure(list(var1 = 4, var2 = 5, var3 = 6), .Names = c("var1", 
    "var2", "var3")), row = structure(list(var1 = 7, var2 = 8, 
        var3 = 9), .Names = c("var1", "var2", "var3"))), .Names = c("row", 
"row", "row"))), .Names = c("id", "var1", "var3", "section1", 
"section2"))


> str(test)
List of 5
 $ id      : num 1
 $ var1    : num 2
 $ var3    : num 4
 $ section1:List of 3
  ..$ var1: num 1
  ..$ var2: num 2
  ..$ var3: num 3
 $ section2:List of 3
  ..$ row:List of 3
  .. ..$ var1: num 1
  .. ..$ var2: num 2
  .. ..$ var3: num 3
  ..$ row:List of 3
  .. ..$ var1: num 4
  .. ..$ var2: num 5
  .. ..$ var3: num 6
  ..$ row:List of 3
  .. ..$ var1: num 7
  .. ..$ var2: num 8
  .. ..$ var3: num 9

请注意 section2列表包含名为 rows 的元素.这些代表多个记录。我拥有的是一个嵌套列表，其中一些元素位于根级别，而其他元素是同一观察的多个嵌套记录。我希望在 data.frame 中有以下输出格式:

> desired
  id var1 var3 section1.var1 section1.var2 section1.var3 section2.var1 section2.var2 section2.var3
1  1    2    4             1             2               3             1             4             7
2 NA   NA   NA            NA            NA              NA             2             5             8
3 NA   NA   NA            NA            NA              NA             3             6             9

根级元素应填充第一行，而 row元素应该有自己的行。作为增加的复杂性， row 中的变量数量条目可能会有所不同。

Answer 1

这是一个通用的方法。它不会假设您只有三行；无论您有多少行，它都可以使用。如果嵌套结构中缺少某个值(例如，第 2 部分中的某些子列表不存在 var1)，则代码会正确返回该单元格的 NA。

例如。如果我们使用以下数据:

test <- structure(list(id = 1, var1 = 2, var3 = 4, section1 = structure(list(var1 = 1, var2 = 2, var3 = 3), .Names = c("var1", "var2", "var3")), section2 = structure(list(row = structure(list(var1 = 1, var2 = 2), .Names = c("var1", "var2")), row = structure(list(var1 = 4, var2 = 5), .Names = c("var1", "var2")), row = structure(list( var2 = 8, var3 = 9), .Names = c("var2", "var3"))), .Names = c("row", "row", "row"))), .Names = c("id", "var1", "var3", "section1", "section2"))

一般的方法是使用melt来创建一个包含嵌套结构信息的数据框，然后dcast将它塑造成你想要的格式。

library("reshape2")

flat <- unlist(test, recursive=FALSE)
names(flat)[grep("row", names(flat))] <- gsub("row", "var", paste0(names(flat)[grep("row", names(flat))], seq_len(length(names(flat)[grep("row", names(flat))]))))  ## keeps track of rows by adding an ID
ul <- melt(unlist(flat))
split <- strsplit(rownames(ul), split=".", fixed=TRUE) ## splits the names into component parts
max <- max(unlist(lapply(split, FUN=length)))
pad <- function(a) {
  c(a, rep(NA, max-length(a)))
}
levels <- matrix(unlist(lapply(split, FUN=pad)), ncol=max, byrow=TRUE)

## Get the nesting structure
nested <- data.frame(levels, ul)
nested$X3[is.na(nested$X3)] <- levels(as.factor(nested$X3))[[1]]
desired <- dcast(nested, X3~X1 + X2)
names(desired) <- gsub("_", "\\.", gsub("_NA", "", names(desired)))
desired <- desired[,names(flat)]

> desired
  ## id var1 var3 section1.var1 section1.var2 section1.var3 section2.var1 section2.var2 section2.var3
## 1  1    2    4             1             2             3             1             4             7
## 2 NA   NA   NA            NA            NA            NA             2             5             8
## 3 NA   NA   NA            NA            NA            NA             3             6             9