R模拟编程效率

Question

我是一个相对较新的R程序员，我写了一个脚本，它获取一些统计结果，并最终将其与目标变量已被随机化的结果向量进行比较。结果向量包含n个模拟的统计结果。随着模拟数量的增加(我希望至少运行10,000个模拟)，运行时间比我希望的要长。我已经尝试过用我知道的修改代码的方法来提高性能，但我希望能得到其他人的帮助来优化它。下面是代码的相关部分。

#CREATE DATA   

require(plyr)

Simulations <- 10001
Variation <- c("Control", "A", "B","C")
Trials <- c(727,724,723,720)
NonResponse <- c(692,669,679,682)
Response <- c(35,55,44,38)
ConfLevel <- .95

#PERFORM INITIAL CALCS  

NonResponse <- Trials-Response
Data <-data.frame(Variation, NonResponse, Response, Trials)
total <- ddply(Data,.(Variation),function(x){data.frame(value = rep(c(0,1),times =   c(x$NonResponse,x$Response)))})
total <- total[sample(1:nrow(total)), ]
colnames(total) <- c("Variation","Response")

#CREATE FUNCTION TO PERFORM SIMULATIONS   

targetshuffle <- function(x) 
{
  shuffle_target <- x[,"Response"] 
  shuffle_target <- data.frame(sample(shuffle_target)) 

  revised <- cbind(x[,"Variation"], shuffle_target) 
  colnames(revised) <- c("Variation","Yes")

  yes_variation <- data.frame(table(revised$Yes,revised$Variation))
  colnames(yes_variation) <- c("Yes","Variation","Shuffled_Response")
  Shuffled_Data <- subset(yes_variation, yes_variation$Yes==1)
  Shuffled_Data <- Shuffled_Data[match(Variation, Shuffled_Data$Variation),]
  yes_variation <- cbind(Data,Shuffled_Data)

  VectorPTest_All <- yes_variation[,c("Variation","NonResponse","Response","Trials","Shuffled_Response")]
  Control_Only <- yes_variation[yes_variation$Variation=="Control",]
  VectorPTest_Chall <- subset(yes_variation,!(Variation=="Control"))
  VectorPTest_Chall <- VectorPTest_Chall[,c("Variation","NonResponse","Response","Trials","Shuffled_Response")] 

  ControlResponse <- Control_Only$Response
  ControlResponseRevised <- Control_Only$Shuffled_Response
  ControlTotal <- Control_Only$Trials
  VariationCount <- length(VectorPTest_Chall$Variation)          

  VP <- data.frame(c(VectorPTest_Chall,rep(ControlResponse),rep(ControlResponseRevised),rep(ControlTotal)))

  names(VP) <- c("Variation","NonResponse","Response", "Trials", "ResponseShuffled", "ControlReponse", 
             "ControlResponseShuffled","ControlTotal")

  VP1 <<- data.frame(VP[,c(5,7,4,8)]) 
  VP2 <<- data.frame(VP[,c(3,6,4,8)]) 

  ptest <- apply(VP1, 1, function(column) prop.test(x=c(column[1], column[2]), 
                                               n=c(column[3], column[4]),  alternative="two.sided", 
                                               conf.level=ConfLevel,  correct=FALSE)$p.value)

  min_p_value <- min(ptest)

  return(min_p_value)
}

#CALL FUNCTION   

sim_result <- do.call(rbind, rlply(Simulations, targetshuffle(total)))

Answer 1

现在，需要考虑的一件事就是创建所有的数据帧。每次这样做的时候，都是在复制组成对象中的所有数据。如果维度是可预测的，您可以考虑在函数开始时创建空矩阵，并在执行过程中填充它们。