让我们假设每个月的时间步长都有大量的全球气候数据集。然后,数据集的形状为以下类型的data.frame
lon,lat,data_month_1_yr_1,...,data_month_12_yr_100
示例:
set.seed(123)
data<- data.frame(cbind(runif(10000,-180,180), runif(10000,-90,90))
, replicate(1200, runif(10000,0,150)))
我想在每个空间点的每月时间序列上执行Mann-Kendall测试(使用trend::mk.test
,并在data.frame
中获得主要统计信息。为了加快这一漫长的过程,我并行执行了代码,并编写了如下内容:
coords<-data[,1:2] #get the coordinates out of the initial dataset
names(coords)<-c("lon","lat")
data_t<- as.data.frame(t(data[,3:1202])) #each column is now the time series associated to a point
data_t$month<-rep(seq(1,12,1),100) # month index as last column of the data frame
# start the parallel processing
library(foreach)
library(doParallel)
cores=detectCores() #count cores
cl <- makeCluster(cores[1]-1) #take all the cores minus 1 not to overload the pc
registerDoParallel(cl)
mk_out<- foreach(m=1:12, .combine = rbind) %:%
foreach (a =1:10000, .combine = rbind) %dopar% {
data_m<-data_t[which(data_t$month==m),]
library(trend) #need to load this all the times otherwise I get an error (don't know why)
test<-mk.test(data_m[,a])
mk_out_temp <- data.frame("lon"=coords[a,1],
"lat"=coords[a,2],
"p.value" = as.numeric(test$p.value),
"z_stat" = as.numeric(test$statistic),
"tau" = as.numeric(test$estimates[3]),
"month"= as.numeric(m))
mk_out_temp
}
stopCluster(cl)
head(mk_out)
lon lat p.value z_stat tau month
1 -76.47209 -34.09350 0.57759040 -0.5569078 -0.03797980 1
2 103.78985 -31.58639 0.64436238 0.4616081 0.03151515 1
3 -32.76831 66.64575 0.11793238 1.5635113 0.10626263 1
4 137.88627 -30.83872 0.79096910 0.2650524 0.01818182 1
5 158.56822 -67.37378 0.09595919 -1.6647673 -0.11313131 1
6 -163.59966 -25.88014 0.82325630 0.2233588 0.01535354 1
这运行得很好,并且给我确切的含义:一个矩阵,报告每个坐标和月份组合的M-K统计信息。尽管该过程是并行的,但是计算仍要花费大量时间。
有没有办法加快这一过程? apply
系列有使用功能的空间吗?
答案 0 :(得分:1)
您注意到您已经解决了问题。可通过以下步骤之一获得:
1:使用.packages
和.export
将必要的对象复制到foreach循环中。这样可以确保每个实例在尝试访问相同的内存时都不会发生冲突。
2:利用高性能库(例如data.table的tidyverse)执行子集和计算。
后者稍微复杂一点,但极大地提高了我纤巧的微型笔记本电脑的性能。 (整个数据集大约需要1.5分钟来执行所有计算。)
以下是我添加的代码。请注意,我用并行包中的单个parLapply函数替换了foreach。
set.seed(123)
data<- data.frame(cbind(runif(10000,-180,180), runif(10000,-90,90))
, replicate(1200, runif(10000,0,150)))
coords<-data[,1:2] #get the coordinates out of the initial dataset
names(coords)<-c("lon","lat")
data_t<- as.data.frame(t(data[,3:1202])) #each column is now the time series associated to a point
data_t$month<-rep(seq(1,12,1),100) # month index as last column of the data frame
# start the parallel processing
library(data.table)
library(parallel)
library(trend)
setDT(data_t)
setDT(coords)
cores=detectCores() #count cores
cl <- makeCluster(cores[1]-1) #take all the cores minus 1 not to overload the pc
#user system elapsed
#17.80 35.12 98.72
system.time({
test <- data_t[,parLapply(cl,
.SD, function(x){
(
unlist(
trend::mk.test(x)[c("p.value","statistic","estimates")]
)
)
}
), by = month] #Perform the calculations across each month
#create a column that indicates what each row is measuring
rows <- rep(c("p.value","statistic.z","estimates.S","estimates.var","estimates.tau"),12)
final_tests <- dcast( #Cast the melted structure to a nice form
melt(cbind(test,rowname = rows), #Melt the data for a better structure
id.vars = c("rowname","month"), #Grouping variables
measure.vars = paste0("V",seq.int(1,10000))), #variable names
month + variable ~ rowname, #LHS groups the data along rows, RHS decides the value columns
value.var = "value", #Which column contain values?
drop = TRUE) #should we drop unused columns? (doesnt matter here)
#rename the columns as desired
names(final_tests) <- c("month","variable","S","tau","var","p.value","z_stat")
#finally add the coordinates
final_tests <- cbind(final_form,coords)
})
答案 1 :(得分:0)