0

我有一个数据集，我想使用 tq_mutate 和 rollapply 处理不同的参数值。

目前我正在使用 for 循环遍历所有参数值，但我确信这不是完成此任务的最有效或最快的方法（尤其是当我要查看大量参数值时）。如何改进或删除 for 循环？我怀疑这意味着使用 purrr::map 或其他方式（多线程/多核等），但我无法在网上找到有用的示例。

下面是一些示例代码。请忽略数据集和比例函数输出的简单性，仅用于说明目的。我想要做的是迭代许多不同的 V0 值。 

library(dplyr)
library(tidyverse)
library(broom)
library(tidyquant)

my_bogus_function <- function(df, V0=1925) { 
  # WILL HAVE SOMETHING MORE SOPHISTICATED IN HERE BUT KEEPING IT SIMPLE
  # FOR THE PURPOSES OF THE QUESTION
  c(V0, V0*2)
}

window_size <- 7 * 24
cnames = c("foo", "bar")
df <- c("FB") %>%
    tq_get(get = "stock.prices", from = "2016-01-01", to = "2017-01-01") %>% 
    dplyr::select("date", "open")

# CAN THIS LOOP BE DONE IN A MORE EFFICIENT MANNER? 
for (i in (1825:1830)){
  df <- df %>% 
        tq_mutate(mutate_fun = rollapply,
                  width      = window_size,
                  by.column  = FALSE,
                  FUN        = my_bogus_function,
                  col_rename = gsub("$", sprintf(".%d", i), cnames), 
                  V0 = i
    )
}
# END OF THE FOR LOOP I WANT FASTER
4

1 回答 1

0

鉴于 R 使用一个核心，我通过使用并行包、doSNOW 和 foreach 发现了改进，这些包允许使用多个核心（请注意，我在 Windows 机器上，因此其他一些包不可用）。

我确信对于多线程/并行/向量化代码还有其他答案。

这是任何有兴趣的人的代码。

library(dplyr)
library(tidyverse)
library(tidyquant)
library(parallel)
library(doSNOW)  
library(foreach)

window_size <- 7 * 24
cnames = c("foo", "bar")
df <- c("FB") %>%
  tq_get(get = "stock.prices", from = "2016-01-01", to = "2017-01-01") %>% 
  dplyr::select("date", "open")

my_bogus_function <- function(df, V0=1925) { 
  # WILL HAVE SOMETHING MORE SOPHISTICATED IN HERE BUT KEEPING IT SIMPLE
  # FOR THE PURPOSES OF THE QUESTION
  c(V0, V0*2)
}

# CAN THIS LOOP BE DONE IN A MORE EFFICIENT/FASTER MANNER? YES 
numCores <- detectCores() # get the number of cores available
cl <- makeCluster(numCores, type = "SOCK")
registerDoSNOW(cl) 

# Function to combine the outputs 
mycombinefunc <-  function(a,b){merge(a, b, by = c("date","open"))}

# Run the loop over multiple cores
meh <- foreach(i = 1825:1830, .combine = "mycombinefunc") %dopar% {
  message(i)
  df %>% 
    # Adjust everything
    tq_mutate(mutate_fun = rollapply,
              width      = window_size,
              by.column  = FALSE,
              FUN        = my_bogus_function,
              col_rename = gsub("$", sprintf(".%d", i), cnames), 
              V0 = i
    )
}
stopCluster(cl)
# END OF THE FOR LOOP I WANTED FASTER
于 2018-11-26T23:04:55.930 回答