问题描述
我有一个矩阵(# This is another comment.
)代表一个人口普查区mat_cdf
在给定日期移至人口普查区i
的累积概率。给定一个决定不“待在家”的特工向量,下面我有一个函数j
,可以从该矩阵中随机抽样以确定他们将在哪个普查区花费时间。
GetCTMove
与一百万个代理一起工作,每个样本大约需要10秒钟才能运行,乘以许多时间步长会导致每次模拟花费数小时,而此功能到目前为止是模型的速率限制因素。我想知道是否有人对更快实施这种随机抽样有意见。我已经使用# Random generation
cts <- 500
i <- rgamma(cts,50,1)
prop <- 1:cts
# Matrix where rows correspond to probability mass of column integer
mat <- do.call(rbind,lapply(i,function(i){dpois(prop,i)}))
# Convert to cumulative probability mass
mat_cdf <- matrix(NA,cts,cts)
for(i in 1:cts){
# Create cdf for row i
mat_cdf[i,] <- sapply(1:cts,function(j) sum(mat[i,1:j]))
}
GetCTMove <- function(agent_cts,ct_mat_cdf){
# Expand such that every agent has its own row corresponding to CDF of movement from their home ct i to j
mat_expand <- ct_mat_cdf[agent_cts,]
# Probabilistically sample column index for every row by generating random number and then determining corresponding closest column
s <- runif(length(agent_cts))
fin_col <- max.col(s < mat_expand,"first")
return(fin_col)
}
# Sample of 500,000 agents' residence ct
agents <- sample(1:cts,size = 500000,replace = T)
# Run function
system.time(GetCTMove(agents,mat_cdf))
user system elapsed
3.09 1.19 4.30
包来加快随机数的生成,但是与矩阵扩展(dqrng
)和mat_expand
调用(它们需要花费最长的运行时间)相比,这是相对较小的。>
解决方法
您可以优化的第一件事是以下代码:
max.col(s < mat_expand,"first")
由于s < mat_expand
返回逻辑矩阵,因此应用max.col
函数与获取每一行的第一个TRUE
相同。在这种情况下,使用which
会更有效率。另外,如下所示,您将所有CDF存储在一个矩阵中。
mat <- do.call(rbind,lapply(i,function(i){dpois(prop,i)}))
mat_cdf <- matrix(NA,cts,cts)
for(i in 1:cts){
mat_cdf[i,] <- sapply(1:cts,function(j) sum(mat[i,1:j]))
}
此结构可能不是最佳的。 list
结构更适用于应用which
之类的功能。由于您不必经过do.call(rbind,...)
,因此运行起来也更快。
# using a list structure to speed up the creation of cdfs
ls_cdf <- lapply(i,function(x) cumsum(dpois(prop,x)))
下面是您的实现:
# Implementation 1
GetCTMove <- function(agent_cts,ct_mat_cdf){
mat_expand <- ct_mat_cdf[agent_cts,]
s <- runif(length(agent_cts))
fin_col <- max.col(s < mat_expand,"first")
return(fin_col)
}
在我的桌面上,大约需要运行2.68秒。
> system.time(GetCTMove(agents,mat_cdf))
user system elapsed
2.25 0.41 2.68
使用list
结构和which
函数,运行时间可以减少大约1s。
# Implementation 2
GetCTMove2 <- function(agent_cts,ls_cdf){
n <- length(agent_cts)
s <- runif(n)
out <- integer(n)
i <- 1L
while (i <= n) {
out[[i]] <- which(s[[i]] < ls_cdf[[agent_cts[[i]]]])[[1L]]
i <- i + 1L
}
out
}
> system.time(GetCTMove2(agents,ls_cdf))
user system elapsed
1.59 0.02 1.64
据我所知,只有R,没有其他方法可以进一步加快代码的速度。但是,您确实可以通过在C ++中重写键函数GetCTMove
来提高性能。使用Rcpp
软件包,您可以执行以下操作:
# Implementation 3
Rcpp::cppFunction('NumericVector fast_GetCTMove(NumericVector agents,NumericVector s,List cdfs) {
int n = agents.size();
NumericVector out(n);
for (int i = 0; i < n; ++i) {
NumericVector cdf = as<NumericVector>(cdfs[agents[i] - 1]);
int m = cdf.size();
for (int j = 0; j < m; ++j) {
if (s[i] < cdf[j]) {
out[i] = j + 1;
break;
}
}
}
return out;
}')
GetCTMove3 <- function(agent_cts,ls_cdf){
s <- runif(length(agent_cts))
fast_GetCTMove(agent_cts,s,ls_cdf)
}
此实现快如闪电,应该可以满足您的所有需求。
> system.time(GetCTMove3(agents,ls_cdf))
user system elapsed
0.07 0.00 0.06
完整脚本如下:
# Random generation
cts <- 500
i <- rgamma(cts,50,1)
prop <- 1:cts
agents <- sample(1:cts,size = 500000,replace = T)
# using a list structure to speed up the creation of cdfs
ls_cdf <- lapply(i,x)))
# below is your code
mat <- do.call(rbind,1:j]))
}
# Implementation 1
GetCTMove <- function(agent_cts,"first")
return(fin_col)
}
# Implementation 2
GetCTMove2 <- function(agent_cts,ls_cdf){
n <- length(agent_cts)
s <- runif(n)
out <- integer(n)
i <- 1L
while (i <= n) {
out[[i]] <- which(s[[i]] < ls_cdf[[agent_cts[[i]]]])[[1L]]
i <- i + 1L
}
out
}
# Implementation 3
Rcpp::cppFunction('NumericVector fast_GetCTMove(NumericVector agents,ls_cdf)
}
system.time(GetCTMove(agents,mat_cdf))
system.time(GetCTMove2(agents,ls_cdf))
system.time(GetCTMove3(agents,ls_cdf))