使用 foreach

R 并行编程

Nabeel Imam

Data Scientist

一种新循环

R 的原生 for 循环

numbers <- 1:1e6

sqroots <- rep(0, length(numbers))

for (i in 1:length(numbers)) {
  sqroots[i] <- sqrt(numbers[i])
}

foreach 循环

numbers <- 1:1e6

library(foreach)


sqroots <- foreach(i = numbers) %do% {
  sqrt(i)
}

并行循环

numbers <- 1:1e6

sqroots <- foreach(i = numbers) %do% {
  sqrt(i)
}

cl <- makeCluster(4)


library(doParallel)
registerDoParallel(cl)


sqroots <- foreach(i = numbers
                   # 并行运算符
                  ) %dopar% {
  sqrt(i)
}


stopCluster(cl)

顶尖工程类大学

print(uni_list)

 [1] "./uni_data/Argentina.csv"
 [2] "./uni_data/Australia.csv"
 [3] "./uni_data/Austria.csv"
 [4] "./uni_data/Azerbaijan.csv"
 [5] "./uni_data/Bahrain.csv"
 [6] "./uni_data/Bangladesh.csv"
 [7] "./uni_data/Belarus.csv"
 [8] "./uni_data/Belgium.csv"
 [9] "./uni_data/Bolivia.csv"
[10] "./uni_data/Bosnia and Herzegovina.csv"
...

cl <- makeCluster(4)

registerDoParallel(cl)


ls_df <- foreach(csv = uni_list) %dopar% {
  read.csv(csv)
}

stopCluster(cl)

用 foreach 汇总结果

cl <- makeCluster(4)
registerDoParallel(cl)
ls_df <- foreach(csv = uni_list) %dopar% {
  read.csv(csv)
}
stopCluster(cl)

[[1]]
 location                  institution score
Argentina  Universidad de Buenos Aires  68.9
...
[[2]]
 location                     institution score
Australia  Australian National University  82.1
...

cl <- makeCluster(4)
registerDoParallel(cl)

df_uni <- foreach(csv = uni_list,
                 .combine = "rbind") %dopar% {
  read.csv(csv)
}
stopCluster(cl)

   location                     institution score
1 Argentina     Universidad de Buenos Aires  68.9
2 Argentina  Universidad Católica Argentina  33.3
3 Argentina     Universidad de Palermo (UP)  29.1
...

读取、筛选并合并

library(dplyr)

n_unis <- 3


# 空列表
ls_df <- list()


for (i in 1:length(uni_list)) {
  # 读取、筛选、收集到空列表
  ls_df[[i]] <- read.csv(uni_list[[i]]) %>%
    top_n(n_unis, total_score)

}

# 合并为一个数据框
combined_df <- Reduce("rbind", ls_df)

foreach 大显身手

n_unis <- 3


cl <- makeCluster(4)
registerDoParallel(cl)


df_top3 <- foreach(csv = uni_list,

                   .packages = "dplyr",

                   .export = "n_unis",

                   .combine = "rbind") %dopar% {

  read.csv(csv) %>% 
    top_n(n_unis, score)
}

stopCluster(cl)

 location                     institution score
Argentina     Universidad de Buenos Aires  68.9
Argentina  Universidad Católica Argentina  33.3
Argentina     Universidad de Palermo (UP)  29.1
Australia  Australian National University  82.1
Australia     The University of Melbourne  81.6
Australia        The University of Sydney  79.6
  Austria            University of Vienna  50.6
  Austria     Technische Universität Wien  45.7
...

Vamos praticar!

R 并行编程