1. R语言运行效率分析_小结（2）

小结（2）

以上用到了9个方法实现一个问题，在实现的过程中试验数据量为n=10。得到不同方法所用的平均耗时间大小。每种方法在计算平均耗时的重复次数为N =100。当然上述的每个方法测试的数据量尽管相同，但由于（1）数据内容不尽相同，（2）由于测试耗时的时候后台打开的程序多少不同（CPU和内存任务量不同），（3）每种方法所处理的内容不尽相同。这些都对所测试的结果产生影响。为此，为了减小这些影响，本节主要通过增加数据量大小（n）（也可以增加重复次数（N ），本例没加以讨论）来估测每种方法的优劣。另外，为了具有可比性，以下统计结果均为处理单个数据所消耗的时间。时间单位为微秒（microsecond）

自定义函数（1）

计算这9个函数处理n个数据分别所用的平均时间（N为重复次数）

#n为随机化月份数据向量的长度，N为计算每个函数平均重复的次数
methods_time<-function(n,N){
  month<-month_digital(n)
  Month_for_if         <-microbenchmark(Month_name_for_if         (month),times=N,unit="us")#milliseconds
  Month_for_if_else    <-microbenchmark(Month_name_for_if_else    (month),times=N,unit="us")
  Month_for_ifelse     <-microbenchmark(Month_name_for_ifelse     (month),times=N,unit="us")
  Month_for_switch     <-microbenchmark(Month_name_for_switch     (month),times=N,unit="us")
  Month_which          <-microbenchmark(Month_name_which          (month),times=N,unit="us")
  Month_join           <-microbenchmark(Month_name_join           (month),times=N,unit="us")
  Month_ddply          <-microbenchmark(Month_name_ddply          (month),times=N,unit="us")
  Month_str_replace_all<-microbenchmark(Month_name_str_replace_all(month),times=N,unit="us")
  
  Season_for_if         <-microbenchmark(Season_name_for_if         (month),times=N,unit="us")
  Season_for_if_else    <-microbenchmark(Season_name_for_if_else    (month),times=N,unit="us")
  Season_for_ifelse     <-microbenchmark(Season_name_for_ifelse     (month),times=N,unit="us")
  Season_for_switch     <-microbenchmark(Season_name_for_switch     (month),times=N,unit="us")
  Season_which          <-microbenchmark(Season_name_which          (month),times=N,unit="us")
  Season_join           <-microbenchmark(Season_name_join           (month),times=N,unit="us")
  Season_ddply          <-microbenchmark(Season_name_ddply          (month),times=N,unit="us")
  Season_str_replace_all<-microbenchmark(Season_name_str_replace_all(month),times=N,unit="us")
  
  result_for_if         <-microbenchmark(result_for_if         (month),times=N,unit="us")
  result_for_if_else    <-microbenchmark(result_for_if_else    (month),times=N,unit="us")
  result_for_ifelse     <-microbenchmark(result_for_ifelse     (month),times=N,unit="us")
  result_for_switch     <-microbenchmark(result_for_switch     (month),times=N,unit="us")
  result_which          <-microbenchmark(result_which          (month),times=N,unit="us")
  result_join           <-microbenchmark(result_join           (month),times=N,unit="us")
  result_ddply          <-microbenchmark(result_ddply          (month),times=N,unit="us")
  result_str_replace_all<-microbenchmark(result_str_replace_all(month),times=N,unit="us")
  
  Month<-c(summary(Month_for_if)$mean,
           summary(Month_for_if_else)$mean,
           summary(Month_for_ifelse)$mean,
           summary(Month_for_switch)$mean,
           summary(Month_which)$mean,
           summary(Month_join)$mean,
           summary(Month_ddply)$mean,
           summary(Month_str_replace_all)$mean)
  Season<-c(summary(Season_for_if)$mean,
            summary(Season_for_if_else)$mean,
            summary(Season_for_ifelse)$mean,
            summary(Season_for_switch)$mean,
            summary(Season_which)$mean,
            summary(Season_join)$mean,
            summary(Season_ddply)$mean,
            summary(Season_str_replace_all)$mean)
  All<-c(summary(result_for_if)$mean,
         summary(result_for_if_else)$mean,
         summary(result_for_ifelse)$mean,
         summary(result_for_switch)$mean,
         summary(result_which)$mean,
         summary(result_join)$mean,
         summary(result_ddply)$mean,
         summary(result_str_replace_all)$mean)
  df<-data.frame(Month/n,Season/n,All/n)
  colnames(df)<-c("Month","Season","All")
  df$Type<-c("for_if","for_if_else","for_ifelse","for_switch","which","join","ddply","result_str_replace")
  df$n<-n
  df$N<-N
  return(select(df,Type,n,N,everything()))
}

自定义函数（2）

调用上述函数，处理月份数据为100，200，300，……，1000时，所需要的平均时间

result<-data.frame(Type=as.character(),n=as.integer(),N=as.integer(),
                    Month=as.integer(),Season=as.integer(),All=as.integer())
foreach (i= seq(100,1000,100)) %dopar% {
  tmp<-methods_time(i,100)
  result<-rbind(result,tmp)
  cat(paste0(i,"\n"))
}
write.csv(tmp,"/home/xh/300G/tmp/result.csv")

(未完！待续……)