R：根據其他行值重命名列表

Question

我已經從matlab導入數據，並有一個大的列表（超過1000個列表元素），我創建了以下示例數據集data只有兩個列表元素。

data <- structure(list(TEST.DATA.1.1 = structure(list(ID = c(2, 2, 2), YEAR = c(1990, 1991, 1992), DATA.1 = c(10, 20, 30), DATA.NAME = structure(c(1L, 1L, 1L), class = "factor", .Label = "Test"), Remarks = c(1990, 1991, 1992)), .Names = c("ID", "YEAR", "DATA.1", "DATA.NAME", "Remarks"), row.names = c(NA, -3L), class = "data.frame"), TEST.DATA.2.1 = structure(list(ID = c(4, 4), YEAR = c(2000, 2001), DATA.1 = c(55, 60), DATA.2 = c(0, 2), DATA.3 = c(4, 6), DATA.NAME.structure..n1....Dim...c.1L..1L.. = structure(c(1L,1L), class = "factor", .Label = "n1"), DATA.NAME.structure..n2....Dim...c.1L..1L.. = structure(c(1L, 1L), class = "factor", .Label = "n2"), DATA.NAME.structure..n3....Dim...c.1L..1L.. = structure(c(1L,1L), class = "factor", .Label = "n3"), Remarks = c(2000,2001)), .Names = c("ID", "YEAR", "DATA.1", "DATA.2", "DATA.3", "DATA.NAME.structure..n1....Dim...c.1L..1L..", "DATA.NAME.structure..n2....Dim...c.1L..1L..", "DATA.NAME.structure..n3....Dim...c.1L..1L..", "Remarks"), row.names = c(NA, -2L), class = "data.frame")), .Names = c("TEST.DATA.1.1", "TEST.DATA.2.1")) 

data 
$TEST.DATA.1.1 
    ID YEAR DATA.1 DATA.NAME Remarks 
1 2 1990  10  Test 1990 
2 2 1991  20  Test 1991 
3 2 1992  30  Test 1992 

$TEST.DATA.2.1 
    ID YEAR DATA.1 DATA.2 DATA.3 DATA.NAME.structure..n1....Dim...c.1L..1L.. DATA.NAME.structure..n2....Dim...c.1L..1L.. DATA.NAME.structure..n3....Dim...c.1L..1L.. Remarks 
1 4 2000  55  0  4           n1           n2           n3 2000 
2 4 2001  60  2  6           n1           n2           n3 2001 

我正在尋找一種方式，我如何能與來自塔（S）DATA.NAME名稱重命名數據列。有時在第二個列表元素中有多個數據列和各自的名稱，有時候只有一個，比如在第一個元素中。我正在尋找一種方法來爲大列表（> 1000個列表元素）進行重命名，然後刪除DATA.NAME列，如data_new。

data_new 
    $TEST.DATA.1.1 
     ID YEAR Test Remarks 
    1 2 1990 10 1990 
    2 2 1991 20 1991 
    3 2 1992 30 1992 

    $TEST.DATA.2.1 
     ID YEAR n1 n2 n3 Remarks 
    1 4 2000 55 0 4 2000 
    2 4 2001 60 2 6 2001 

Answer 1

這裏有一個基礎R方法：

for (i in seq_along(data)) { 
    namecis <- grep('^DATA\\.NAME',names(data[[i]])); 
    datacis <- grep('^DATA\\.\\d+',names(data[[i]])); 
    names(data[[i]])[datacis] <- as.character(unlist(data[[i]][1,namecis])); 
    data[[i]][namecis] <- list(NULL); 
}; 
data; 
## $TEST.DATA.1.1 
## ID YEAR Test Remarks 
## 1 2 1990 10 1990 
## 2 2 1991 20 1991 
## 3 2 1992 30 1992 
## 
## $TEST.DATA.2.1 
## ID YEAR n1 n2 n3 Remarks 
## 1 4 2000 55 0 4 2000 
## 2 4 2001 60 2 6 2001 

Answer 2

解決方案使用data.table包。

require(data.table) 

data <- structure(list(TEST.DATA.1.1 = structure(list(ID = c(2, 2, 2), YEAR = c(1990, 1991, 1992), DATA.1 = c(10, 20, 30), DATA.NAME = structure(c(1L, 1L, 1L), class = "factor", .Label = "Test"), Remarks = c(1990, 1991, 1992)), .Names = c("ID", "YEAR", "DATA.1", "DATA.NAME", "Remarks"), row.names = c(NA, -3L), class = "data.frame"), TEST.DATA.2.1 = structure(list(ID = c(4, 4), YEAR = c(2000, 2001), DATA.1 = c(55, 60), DATA.2 = c(0, 2), DATA.3 = c(4, 6), DATA.NAME.structure..n1....Dim...c.1L..1L.. = structure(c(1L,1L), class = "factor", .Label = "n1"), DATA.NAME.structure..n2....Dim...c.1L..1L.. = structure(c(1L, 1L), class = "factor", .Label = "n2"), DATA.NAME.structure..n3....Dim...c.1L..1L.. = structure(c(1L,1L), class = "factor", .Label = "n3"), Remarks = c(2000,2001)), .Names = c("ID", "YEAR", "DATA.1", "DATA.2", "DATA.3", "DATA.NAME.structure..n1....Dim...c.1L..1L..", "DATA.NAME.structure..n2....Dim...c.1L..1L..", "DATA.NAME.structure..n3....Dim...c.1L..1L..", "Remarks"), row.names = c(NA, -2L), class = "data.frame")), .Names = c("TEST.DATA.1.1", "TEST.DATA.2.1")) 

fun <- function(x) { 
    x <- data.table(x) 
    var1 <- grep("DATA.[0-9]", names(x), value = T) 
    var2 <- as.character(unlist(x[1, grep("DATA.NAME", names(x)), with = F])) 
    setnames(x, var1, var2) 
    x[, grep("DATA.NAME", names(x)) := NULL, with = F] 
    return(x) 
} 

data_new <- lapply(data, fun) 

Answer 3

這應該工作...

library(dplyr) 

for (i in 1:length(data)) 
{ 

    d <- data[[i]] 

    # Find the new names 
    new_names <- select(d, starts_with('DATA.NAME')) 
    new_names <- unlist(new_names[1,]) 
    names(new_names) <- NULL 
    new_names <- as.character(new_names) 

    # Remove the columns containing the names 
    d <- select(d, -starts_with('DATA.NAME')) 

    # Pick which columns we want to replace 
    old_names <- names(d) 
    to_replace <- grep('DATA.[0-9]+', old_names) 

    # Replace those names 
    names(d)[to_replace] <- new_names 

    #Replace the list element 
    data[[i]] <- d 

}