除了在前面的回答中演示的select(-one_of(drop_col_names))之外，还有其他一些dplyr选项可以使用select()删除列，这些选项不涉及定义所有特定的列名(使用dplyr starwars示例数据来获取列名中的某些种类):

library(dplyr)
starwars %>% 
  select(-(name:mass)) %>%        # the range of columns from 'name' to 'mass'
  select(-contains('color')) %>%  # any column name that contains 'color'
  select(-starts_with('bi')) %>%  # any column name that starts with 'bi'
  select(-ends_with('er')) %>%    # any column name that ends with 'er'
  select(-matches('^f.+s$')) %>%  # any column name matching the regex pattern
  select_if(~!is.list(.)) %>%     # not by column name but by data type
  head(2)

# A tibble: 2 x 2
homeworld species
  <chr>     <chr>  
1 Tatooine  Human  
2 Tatooine  Droid 

如果您需要删除数据帧中可能存在也可能不存在的列，这里使用select_if()略有变化，与使用one_of()不同，它不会抛出Unknown列:如果列名不存在，则会发出警告。在这个例子中，'bad_column'不是数据帧中的列:

starwars %>% 
  select_if(!names(.) %in% c('height', 'mass', 'bad_column'))

within(df, rm(x))

可能是最简单的，或者对于多个变量:

within(df, rm(x, y))

或者如果你在处理数据。如何在data.table中按名称删除列?

dt[, x := NULL]   # Deletes column x by reference instantly.

dt[, !"x"]   # Selects all but x into a new data.table.

或者对于多个变量

dt[, c("x","y") := NULL]

dt[, !c("x", "y")]

list(NULL)也可以:

dat <- mtcars
colnames(dat)
# [1] "mpg"  "cyl"  "disp" "hp"   "drat" "wt"   "qsec" "vs"   "am"   "gear"
# [11] "carb"
dat[,c("mpg","cyl","wt")] <- list(NULL)
colnames(dat)
# [1] "disp" "hp"   "drat" "qsec" "vs"   "am"   "gear" "carb"

如果你有一个大的data.frame和低内存使用[. . . .或rm和within删除data.frame的列，因为子集目前(R 3.6.2)使用更多的内存-除了手册提示交互式使用子集。

getData <- function() {
  n <- 1e7
  set.seed(7)
  data.frame(a = runif(n), b = runif(n), c = runif(n), d = runif(n))
}

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF <- DF[setdiff(names(DF), c("a", "c"))] ##
#DF <- DF[!(names(DF) %in% c("a", "c"))] #Alternative
#DF <- DF[-match(c("a","c"),names(DF))]  #Alternative
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#0.1 MB are used

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF <- subset(DF, select = -c(a, c)) ##
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#357 MB are used

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF <- within(DF, rm(a, c)) ##
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#0.1 MB are used

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF[c("a", "c")]  <- NULL ##
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#0.1 MB are used

如果您希望通过引用删除列并避免与data.frames相关的内部复制，则可以使用数据。表包和函数:=

您可以将字符向量名称传递到:=运算符的左侧，并将NULL作为RHS。

library(data.table)

df <- data.frame(a=1:10, b=1:10, c=1:10, d=1:10)
DT <- data.table(df)
# or more simply  DT <- data.table(a=1:10, b=1:10, c=1:10, d=1:10) #

DT[, c('a','b') := NULL]

如果希望将名称预定义为[调用之外的字符向量，请将对象名称包装在()或{}中，以强制LHS在调用范围内计算，而不是作为DT范围内的名称。

del <- c('a','b')
DT <- data.table(a=1:10, b=1:10, c=1:10, d=1:10)
DT[, (del) := NULL]
DT <-  <- data.table(a=1:10, b=1:10, c=1:10, d=1:10)
DT[, {del} := NULL]
# force or `c` would also work.   

您也可以使用set，这避免了[.data]的开销。表，也适用于data.frames!

df <- data.frame(a=1:10, b=1:10, c=1:10, d=1:10)
DT <- data.table(df)

# drop `a` from df (no copying involved)

set(df, j = 'a', value = NULL)
# drop `b` from DT (no copying involved)
set(DT, j = 'b', value = NULL)

你可以像这样在%中使用%:

df[, !(colnames(df) %in% c("x","bar","foo"))]