在 R 中测试多个相同的列
Testing for multiple identical columns in R
是否有一种简短的方法来测试 多个 列的身份?
例如,在此输入
data=data.table(one=c(1,2,3,4), two=c(7,8,9,10), three=c(1,2,3,4), four=c(1,2,3,4) )
有没有什么东西可以 return 所有与 data$one 相同的列?像
allcolumnsidentity(data$one, data) # compares all columns with respect to data$one
应该return(真、假、真、真),因为数据 $3 和数据 $4 与数据 $1 相同。
我看到了 identical() 和 comapre() 命令,但它们处理两列之间的比较。有通用的方法吗?
祝福
好的,这比预期的要容易:)
简单的应用如下:
apply(data, 2, identical, data$one)
# returned:
# one two three four
# TRUE FALSE TRUE TRUE
这里有 3 个可能的解决方案和一个更大数据集的基准
n <- 1e6
data=data.table(one=rep(1:4, n),
two=rep(7:10, n),
three=rep(1:4, n),
four=rep(1:4, n))
library(microbenchmark)
microbenchmark(
apply(data, 2, identical, data$one) ,
colSums(data == data$one) == nrow(data),
colSums(as.matrix(data) == data$one) == nrow(data),
data[, lapply(.SD, function(x) sum(x == data$one) == .N)],
data[, lapply(.SD, function(x) identical(x, data$one))]
)
# Unit: milliseconds
# expr min lq mean median uq max neval
# apply(data, 2, identical, data$one) 352.58769 414.846535 457.767582 437.041789 521.895046 643.77981 100
# colSums(data == data$one) == nrow(data) 1264.95548 1315.882084 1335.827386 1326.250976 1346.501505 1466.64232 100
# colSums(as.matrix(data) == data$one) == nrow(data) 110.05474 114.618818 125.116033 121.631323 126.912647 185.69939 100
# data[, lapply(.SD, function(x) sum(x == data$one) == .N)] 75.36791 77.960613 85.599088 79.327108 89.369938 156.03422 100
# data[, lapply(.SD, function(x) identical(x, data$one))] 7.00261 7.448851 8.687903 8.776724 9.491253 15.72188 100
这里有一些比较,以防你有很多列
n <- 1e7
set.seed(123)
data <- data.table(matrix(sample(n, replace = TRUE), ncol = 400))
microbenchmark(
apply(data, 2, identical, data$V1) ,
colSums(data == data$V1) == nrow(data),
colSums(as.matrix(data) == data$V1) == nrow(data),
data[, lapply(.SD, function(x) sum(x == data$V1) == .N)],
data[, lapply(.SD, function(x) identical(x,data$V1))]
)
# Unit: milliseconds
# expr min lq mean median uq max neval
# apply(data, 2, identical, data$V1) 176.65997 185.23895 235.44088 234.60227 253.88658 331.18788 100
# colSums(data == data$V1) == nrow(data) 680.48398 759.82115 786.64634 774.86919 804.91661 987.26456 100
# colSums(as.matrix(data) == data$V1) == nrow(data) 60.62470 62.86181 70.41601 63.75478 65.16708 120.30393 100
# data[, lapply(.SD, function(x) sum(x == data$V1) == .N)] 83.95790 86.72680 90.45487 88.46165 90.04441 142.08614 100
# data[, lapply(.SD, function(x) identical(x, data$V1))] 40.86718 42.65486 45.06100 44.29602 45.49430 91.57465 100
是否有一种简短的方法来测试 多个 列的身份? 例如,在此输入
data=data.table(one=c(1,2,3,4), two=c(7,8,9,10), three=c(1,2,3,4), four=c(1,2,3,4) )
有没有什么东西可以 return 所有与 data$one 相同的列?像
allcolumnsidentity(data$one, data) # compares all columns with respect to data$one
应该return(真、假、真、真),因为数据 $3 和数据 $4 与数据 $1 相同。
我看到了 identical() 和 comapre() 命令,但它们处理两列之间的比较。有通用的方法吗?
祝福
好的,这比预期的要容易:)
简单的应用如下:
apply(data, 2, identical, data$one)
# returned:
# one two three four
# TRUE FALSE TRUE TRUE
这里有 3 个可能的解决方案和一个更大数据集的基准
n <- 1e6
data=data.table(one=rep(1:4, n),
two=rep(7:10, n),
three=rep(1:4, n),
four=rep(1:4, n))
library(microbenchmark)
microbenchmark(
apply(data, 2, identical, data$one) ,
colSums(data == data$one) == nrow(data),
colSums(as.matrix(data) == data$one) == nrow(data),
data[, lapply(.SD, function(x) sum(x == data$one) == .N)],
data[, lapply(.SD, function(x) identical(x, data$one))]
)
# Unit: milliseconds
# expr min lq mean median uq max neval
# apply(data, 2, identical, data$one) 352.58769 414.846535 457.767582 437.041789 521.895046 643.77981 100
# colSums(data == data$one) == nrow(data) 1264.95548 1315.882084 1335.827386 1326.250976 1346.501505 1466.64232 100
# colSums(as.matrix(data) == data$one) == nrow(data) 110.05474 114.618818 125.116033 121.631323 126.912647 185.69939 100
# data[, lapply(.SD, function(x) sum(x == data$one) == .N)] 75.36791 77.960613 85.599088 79.327108 89.369938 156.03422 100
# data[, lapply(.SD, function(x) identical(x, data$one))] 7.00261 7.448851 8.687903 8.776724 9.491253 15.72188 100
这里有一些比较,以防你有很多列
n <- 1e7
set.seed(123)
data <- data.table(matrix(sample(n, replace = TRUE), ncol = 400))
microbenchmark(
apply(data, 2, identical, data$V1) ,
colSums(data == data$V1) == nrow(data),
colSums(as.matrix(data) == data$V1) == nrow(data),
data[, lapply(.SD, function(x) sum(x == data$V1) == .N)],
data[, lapply(.SD, function(x) identical(x,data$V1))]
)
# Unit: milliseconds
# expr min lq mean median uq max neval
# apply(data, 2, identical, data$V1) 176.65997 185.23895 235.44088 234.60227 253.88658 331.18788 100
# colSums(data == data$V1) == nrow(data) 680.48398 759.82115 786.64634 774.86919 804.91661 987.26456 100
# colSums(as.matrix(data) == data$V1) == nrow(data) 60.62470 62.86181 70.41601 63.75478 65.16708 120.30393 100
# data[, lapply(.SD, function(x) sum(x == data$V1) == .N)] 83.95790 86.72680 90.45487 88.46165 90.04441 142.08614 100
# data[, lapply(.SD, function(x) identical(x, data$V1))] 40.86718 42.65486 45.06100 44.29602 45.49430 91.57465 100