减少重塑的计算时间

我有以下数据集，我想将其从宽格式重塑为长格式：

Name     Code  CURRENCY   01/01/1980   02/01/1980   03/01/1980   04/01/1980
Abengoa  4256  USD        1.53         1.54         1.51         1.52      
Adidas   6783  USD        0.23         0.54         0.61         0.62      

该数据包含从 1980 年到 2013 年每天不同公司的股票价格。因此，我的宽数据中有 8,612 列（大约 3,000 行）。现在，我使用以下命令将数据重塑为长格式：

library(reshape)
data <- read.csv("data.csv")
data1 <- melt(data,id=c("Name","Code", "CURRENCY"),variable_name="Date")

但是，对于大约 50MB 大的 .csv 文件，已经需要大约两个小时。计算时间不应该由弱硬件驱动，因为我在具有 16GB RAM 的 2.7 GHz Intel Core i7 上运行它。还有其他更有效的方法来做到这一点吗？

非常感谢！

基准摘要：

Using Stack（正如@AnandaMahto所建议的）绝对是
较小数据集 (N 随着数据集变大，data.table开始跑赢大盘stack

这是使用 data.table 的选项

dtt <- data.table(data)

# non value columns, ie, the columns to keep post reshape
nvc <- c("Name","Code", "CURRENCY")

# name of columns being transformed 
dateCols <- setdiff(names(data), nvc)

# use rbind list to combine subsets
dtt2 <- rbindlist(lapply(dateCols, function(d) {
    dtt[, Date := d]
    cols <- c(nvc, "Date", d)
    setnames(dtt[, cols, with=FALSE], cols, c(nvc, "Date", "value"))
}))

## Results: 

dtt2
#       Name Code CURRENCY         Date value
# 1: Abengoa 4256      USD X_01_01_1980  1.53
# 2:  Adidas 6783      USD X_01_01_1980  0.23
# 3: Abengoa 4256      USD X_02_01_1980  1.54
# 4:  Adidas 6783      USD X_02_01_1980  0.54
# 5: ... <cropped>

使用更大的样本数据更新了基准

根据 @AnandaMahto 的建议，以下是使用大量（更大）样本数据的基准。请随意改进下面使用的任何方法和/或添加新方法。

基准测试

 Resh <- quote(reshape::melt(data,id=c("Name","Code", "CURRENCY"),variable_name="Date"))
 Resh2 <- quote(reshape2::melt(data,id=c("Name","Code", "CURRENCY"),variable_name="Date"))
 DT <- quote({    nvc <- c("Name","Code", "CURRENCY"); dateCols <- setdiff(names(data), nvc); rbindlist(lapply(dateCols, function(d) { dtt[, Date := d]; cols <- c(nvc, "Date", d); setnames(dtt[, cols, with=FALSE], cols, c(nvc, "Date", "value"))}))})
 Stack <- quote(data.frame(data[1:3], stack(data[-c(1, 2, 3)])))


 # SAMPLE SIZE: ROWS = 900; COLS = 380 + 3; 
 dtt <- data.table(data);  
 benchmark(Resh=eval(Resh),Resh2=eval(Resh2),DT=eval(DT), Stack=eval(Stack), replications=5, columns=c("relative", "test", "elapsed", "user.self", "sys.self", "replications"), order="relative")
 # relative  test elapsed user.self sys.self replications
 #    1.000 Stack   0.813     0.623    0.192            5
 #    2.530    DT   2.057     2.035    0.026            5
 #   40.470  Resh  32.902    18.410   14.602            5
 #   40.578 Resh2  32.990    18.419   14.728            5

 # SAMPLE SIZE: ROWS = 3,500; COLS = 380 + 3; 
 dtt <- data.table(data);  
 benchmark(DT=eval(DT), Stack=eval(Stack), replications=5, columns=c("relative", "test", "elapsed", "user.self", "sys.self", "replications"), order="relative")
 #  relative  test elapsed user.self sys.self replications
 #      1.00    DT   2.407     2.336    0.076            5
 #      1.08 Stack   2.600     1.626    0.983            5

 # SAMPLE SIZE: ROWS = 27,000; COLS = 380 + 3; 
 dtt <- data.table(data);  
 benchmark(DT=eval(DT), Stack=eval(Stack), replications=5, columns=c("relative", "test", "elapsed", "user.self", "sys.self", "replications"), order="relative")
 # relative  test elapsed user.self sys.self replications
 #    1.000    DT  10.450     7.418    3.058            5
 #    2.232 Stack  23.329    14.180    9.266            5

样本数据创建

  # rm(list=ls(all=TRUE))
  set.seed(1)
  LLLL <- apply(expand.grid(LETTERS, LETTERS[10:15], LETTERS[1:20], LETTERS[1:5], stringsAsFactors=FALSE), 1, paste0, collapse="")

  size <- 900
  dateSamples <- 380
  startDate <- as.Date("1980-01-01")

  Name <- apply(matrix(LLLL[1:(2*size)], ncol=2), 1, paste0, collapse="")
  Code <- sample(1e3:max(1e4-1, size+1e3), length(Name))
  CURRENCY <- sample(c("USD", "EUR", "YEN"), length(Name), TRUE)

  Dates <- seq(startDate, length.out=dateSamples, by="mon")
  Values <- sample(c(1:1e2, 1:5e2), size=size*dateSamples, TRUE) / 1e2

  # Calling the sample dataframe `data` to keep consistency, but I dont like this practice
  data <- data.frame(Name, Code, CURRENCY,       
                     matrix(Values, ncol=length(Dates), dimnames=list(c(), as.character(Dates)))
                    ) 

  data[1:6, 1:8]
  #        Name Code CURRENCY X1980.01.01 X1980.02.01 X1980.03.01 X1980.04.01 X1980.05.01
  # 1  AJAAQNFA 3389      YEN        0.37        0.33        3.58        4.33        1.06
  # 2  BJAARNFA 4348      YEN        1.14        2.69        2.57        0.27        3.02
  # 3  CJAASNFA 6154      USD        2.47        3.72        3.32        0.36        4.85
  # 4  DJAATNFA 9171      USD        2.22        2.48        0.71        0.79        2.85
  # 5  EJAAUNFA 2814      USD        2.63        2.17        1.66        0.55        3.12
  # 6  FJAAVNFA 9081      USD        1.92        1.47        3.51        3.23        3.68