ping vars。问题主要是关于粘贴（“data$”，var.out[i]，sep=”“）部分，用于访问循环中感兴趣的列。如何粘贴或以某种方式组合列名？感谢大家的关注和帮助，我想知道为什么要在循环中这样做？朱巴的答案告诉你如何一步到位。为什么要把它弄得更

---

ping vars。问题主要是关于

粘贴（“data$”，var.out[i]，sep=”“）

部分，用于访问循环中感兴趣的列。如何粘贴或以某种方式组合列名？感谢大家的关注和帮助，我想知道为什么要在循环中这样做？朱巴的答案告诉你如何一步到位。为什么要把它弄得更复杂呢？当然，我在代码中使用了

subset

函数的

select

参数。我只是想看看如何在循环中访问任意列，以防除了删除列之外还要做其他事情。原始数据集大约有1200个变量，我只想使用其中的4个变量，而不知道它们的确切位置。或者您可以使用

DT[，var.out:=NULL]

删除您希望删除的列。子集（x，select=…）方法同时适用于

data.frame

和

data.table

classes我喜欢使用

NULL

的第二个选项，但是为什么当您输入两个以上的名称时，需要使用

list（NULL）

来分配它呢？我只是想知道它是如何工作的，因为我只尝试了一个名字，我不需要

list（）

@DarwinPC Yes。如果您直接访问一个向量元素（使用

$

或

[[

），使用

是否改变了此行为？我使用
NULL
和
list（NULL）
X[，-grep（“B”，colnames（X））]获得相同的结果在没有列名称包含“代码> B <代码>的情况下，将不返回任何列，而不是按需要返回所有列。考虑使用<代码> x使用<代码> dPLYR::SELECT（DF2，-ONION（c（x′，y）））< /C> >仍然有效（带有警告）即使某些命名列不存在，这正是我搜索@divibisan的解决方案，谢谢！
data <- read.dta("file.dta")

var.out <- names(data)[!names(data) %in% c("iden", "name", "x_serv", "m_serv")]

for(i in 1:length(var.out)) {
   paste("data$", var.out[i], sep="") <- NULL
}

R> df <- data.frame(x=1:5, y=2:6, z=3:7, u=4:8)
R> df
  x y z u
1 1 2 3 4
2 2 3 4 5
3 3 4 5 6
4 4 5 6 7
5 5 6 7 8

R> df[ , -which(names(df) %in% c("z","u"))]
  x y
1 1 2
2 2 3
3 3 4
4 4 5
5 5 6

R> subset(df, select=-c(z,u))
  x y
1 1 2
2 2 3
3 3 4
4 4 5
5 5 6

R> df[ , c("x","y")]
  x y
1 1 2
2 2 3
3 3 4
4 4 5
5 5 6

R> subset(df, select=c(x,y))
  x y
1 1 2
2 2 3
3 3 4
4 4 5
5 5 6

dat <- data.frame(x=1:5, y=2:6, z=3:7, u=4:8)
dat[ , -which(names(dat) %in% c("z","u"))] ## works as expected
dat[ , -which(names(dat) %in% c("foo","bar"))] ## deletes all columns! Probably not what you wanted...

dat[ , !names(dat) %in% c("z","u")] ## works as expected
dat[ , !names(dat) %in% c("foo","bar")] ## returns the un-altered data.frame. Probably what you want

# read data
dat<-read.dta("file.dta")

# vars to delete
var.in<-c("iden", "name", "x_serv", "m_serv")

# what I'm keeping
var.out<-setdiff(names(dat),var.in)

# keep only the ones I want       
dat <- dat[var.out]

DF = read.table(text = "
     fruit state grade y1980 y1990 y2000
     apples Ohio   aa    500   100   55
     apples Ohio   bb      0     0   44
     apples Ohio   cc    700     0   33
     apples Ohio   dd    300    50   66
", sep = "", header = TRUE, stringsAsFactors = FALSE)

DF[ , !names(DF) %in% c("grade")]   # all columns other than 'grade'
   fruit state y1980 y1990 y2000
1 apples  Ohio   500   100    55
2 apples  Ohio     0     0    44
3 apples  Ohio   700     0    33
4 apples  Ohio   300    50    66

library('data.table')
DT = as.data.table(DF)

DT[ , !names(dat4) %in% c("grade")]    # not expected !! not the same as DF !!
[1]  TRUE  TRUE FALSE  TRUE  TRUE  TRUE

DT[ , !names(DT) %in% c("grade"), with=FALSE]    # that's better
    fruit state y1980 y1990 y2000
1: apples  Ohio   500   100    55
2: apples  Ohio     0     0    44
3: apples  Ohio   700     0    33
4: apples  Ohio   300    50    66

df = read.table(text = "

state county city  region  mmatrix  X1 X2 X3    A1     A2     A3      B1     B2     B3      C1      C2      C3

  1      1     1      1     111010   1  0  0     2     20    200       4      8     12      NA      NA      NA
  1      2     1      1     111010   1  0  0     4     NA    400       5      9     NA      NA      NA      NA
  1      1     2      1     111010   1  0  0     6     60     NA      NA     10     14      NA      NA      NA
  1      2     2      1     111010   1  0  0    NA     80    800       7     11     15      NA      NA      NA

  1      1     3      2     111010   0  1  0     1      2      1       2      2      2      10      20      30
  1      2     3      2     111010   0  1  0     2     NA      1       2      2     NA      40      50      NA
  1      1     4      2     111010   0  1  0     1      1     NA      NA      2      2      70      80      90
  1      2     4      2     111010   0  1  0    NA      2      1       2      2     10     100     110     120

  1      1     1      3     010010   0  0  1    10     20     10     200    200    200       1       2       3
  1      2     1      3     001000   0  0  1    20     NA     10     200    200    200       4       5       9
  1      1     2      3     101000   0  0  1    10     10     NA     200    200    200       7       8      NA
  1      2     2      3     011010   0  0  1    NA     20     10     200    200    200      10      11      12

", sep = "", header = TRUE, stringsAsFactors = FALSE)
df

df2 <- df[df$region == 2, names(df) %in% c(paste("C", seq_along(1:3), sep=''))]
df2

#    C1  C2  C3
# 5  10  20  30
# 6  40  50  NA
# 7  70  80  90
# 8 100 110 120

var.out.bool <- !names(data) %in% c("iden", "name", "x_serv", "m_serv")

data <- data[,var.out.bool] # or...
data <- data[,var.out.bool, drop = FALSE] # You will need this option to avoid the conversion to an atomic vector if there is only one column left

data[c("iden", "name", "x_serv", "m_serv")] <- list(NULL) # You need list() to respect the target structure.

subset( data, select = -c("iden", "name", "x_serv", "m_serv") ) # WILL NOT WORK
subset( data, select = -c(iden, name, x_serv, m_serv) ) # WILL

                                        re_assign(dtest, drop_vec)  46.719  52.5655  54.6460  59.0400  1347.331
                                      null_assign(dtest, drop_vec)  74.593  83.0585  86.2025  94.0035  1476.150
               subset(dtest, select = !names(dtest) %in% drop_vec) 106.280 115.4810 120.3435 131.4665 65133.780
 subset(dtest, select = names(dtest)[!names(dtest) %in% drop_vec]) 108.611 119.4830 124.0865 135.4270  1599.577
                                  subset(dtest, select = -c(x, y)) 102.026 111.2680 115.7035 126.2320  1484.174

dtest <- data.frame(x=1:5, y=2:6, z = 3:7)
drop_vec <- c("x", "y")

null_assign <- function(df, names) {
  df[names] <- list(NULL)
  df
}

re_assign <- function(df, drop) {
  df <- df [, ! names(df) %in% drop, drop = FALSE]
  df
}

res <- microbenchmark(
  re_assign(dtest,drop_vec),
  null_assign(dtest,drop_vec),
  subset(dtest, select = ! names(dtest) %in% drop_vec),
  subset(dtest, select = names(dtest)[! names(dtest) %in% drop_vec]),
  subset(dtest, select = -c(x, y) ),
times=5000)

plt <- ggplot2::qplot(y=time, data=res[res$time < 1000000,], colour=expr)
plt <- plt + ggplot2::scale_y_log10() + 
  ggplot2::labs(colour = "expression") + 
  ggplot2::scale_color_discrete(labels = c("re_assign", "null_assign", "subset_bool", "subset_names", "subset_drop")) +
  ggplot2::theme_bw(base_size=16)
print(plt)

for(i in 1:length(var.out)) {
   paste("data$", var.out[i], sep="") <- NULL
}

for(i in 1:length(var.out)) {

  text_to_source <- paste0 ("data$", var.out[i], "<- NULL") # Write a line of your
                                                  # code like a character string
  eval (parse (text=text_to_source)) # Source a text that contains a code
}

for(i in 1:length(var.out)) {
  data[var.out[i]] <- NULL
}

R> df <- data.frame(x=1:5, y=2:6, z=3:7, u=4:8)
R> df
  x y z u
1 1 2 3 4
2 2 3 4 5
3 3 4 5 6
4 4 5 6 7
5 5 6 7 8
R> library(dplyr)
R> dplyr::select(df2, -c(x, y))  # remove columns x and y
  z u
1 3 4
2 4 5
3 5 6
4 6 7
5 7 8

df2 <- df[!names(df) %in% c("c1", "c2")]

> X<-data.frame(A=c(1,2),B=c(3,4),C=c(5,6))
> X
  A B C
1 1 3 5
2 2 4 6

> X<-X[,-grep("B",colnames(X))]

> X
  A C
1 1 5
2 2 6

> X<-data.frame(A=c(1,2),B=c(3,4),C=c(5,6),D=c(7,8),E=c(9,10))
> X
  A B C D  E
1 1 3 5 7  9
2 2 4 6 8 10

> X<-X[,-grep("B|D",colnames(X))]
> X
  A C  E
1 1 5  9
2 2 6 10

> X<-data.frame(A=c(1,2),B=c(3,4),C=c(5,6),D=c(7,8),E=c(9,10))
> X
  A B C D  E
1 1 3 5 7  9
2 2 4 6 8 10
> X<-X[,!grepl("B|D",colnames(X))]
> X
  A C  E
1 1 5  9
2 2 6 10

> X<-X[,!grepl("G",colnames(X))]
> X
  A C  E
1 1 5  9
2 2 6 10

df = mtcars