我想创建一个包含 10 个分类变量和 10 个连续随机变量的数据框。我可以使用以下循环来做到这一点。
p_val=rbeta(10,1,1) #10 probabilities
n=20
library(truncnorm)
mu_val=rtruncnorm(length(p_val),0,Inf, mean = 100, sd=5)#rnorm(length(p))
d_mat_cat=matrix(NA, nrow = n, ncol = length(p))
d_mat_cont= matrix(NA, nrow = n, ncol = length(p))
for ( j in 1:length(p)){
d_mat_cat[,j]=rbinom(n,1,p[j]) #Binary RV
d_mat_cont[,j]=rnorm(n,mu_val[j]) #Cont. RV
}
d_mat=cbind(d_mat_cat, d_mat_cont)
欢迎任何替代选择。
rbinom
在prob
上矢量化,rnorm
在mean
上矢量化,所以你可以使用它:
cbind(
matrix(rbinom(n * length(p_val), size = 1, prob = p_val),
ncol = length(p_val), byrow = TRUE),
matrix(rnorm(n * length(mu_val), mean = mu_val),
ncol = length(mu_val), byrow = TRUE)
)
我们可以聪明一点rep
使通话更干净:
p_val = c(0, 0.5, 1)
mu_val = c(1, 10, 100)
n = 4
##
matrix(
c(
rbinom(n * length(p_val), size = 1, prob = rep(c(0, .5, 1), each = n)),
rnorm(n * length(mu_val), mean = rep(c(1, 10, 100), each = n))
),
nrow = n,
)
# [,1] [,2] [,3] [,4] [,5] [,6]
# [1,] 0 1 1 1.1962718 9.373595 100.1739
# [2,] 0 0 1 -0.1854631 9.574706 100.0725
# [3,] 0 1 1 3.4873697 9.447363 100.1345
# [4,] 0 1 1 2.8467450 9.700975 101.3178
您可以尝试使用sapply
来运行rbinom
,rnorm
和cbind
数据。
cbind(sapply(p_val, rbinom, n = n, size = 1), sapply(mu_val, rnorm, n = n))