Erstellen Sie eine gültige Schleife auf R

Question

Ich habe this file, die drei .csv-Dateien enthält, EURAUD_201501, EURAUD_201502, EURAUD_201503. Die Dateien enthalten von Januar bis März 2015 Forex-Tick-Daten. Der erste Schritt meiner Übung besteht darin, den Datensatz in eine funktionale Form zu bringen. Der (Arbeits-) Code ist:

#Entering and editing data by hand# 

data1<-read.csv("EURAUD_201501.csv", header = FALSE, col.names = c("TIMESTAMP", "BID", "OFR", "VOL"), stringsAsFactors = FALSE) 
data1$VOL<- NULL #drops the VOL column 
data1$TIMESTAMP = sub('(?<=.{11})', ':', data1$TIMESTAMP, perl=TRUE) #manipulate the strings to create clear timestamps 
data1$TIMESTAMP = sub('(?<=.{14})', ':', data1$TIMESTAMP, perl=TRUE) 
data1$TIMESTAMP = sub('(?<=.{17})', '.', data1$TIMESTAMP, perl=TRUE) 
xts_data1 = xts(data1[,c(2,3)], order.by = as.POSIXct(data1$TIMESTAMP, tz = "EST", format = "%Y%m%d %H:%M:%OS")) #Convert file to an xts object 
rm(data1) #remove data1 object in order to save space 

data2<-read.csv("EURAUD_201502.csv", header = FALSE, col.names = c("TIMESTAMP", "BID", "OFR", "VOL"), stringsAsFactors = FALSE) 
data2$VOL<- NULL #drops the VOL column 
data2$TIMESTAMP = sub('(?<=.{11})', ':', data2$TIMESTAMP, perl=TRUE) #manipulate the strings to create clear timestamps 
data2$TIMESTAMP = sub('(?<=.{14})', ':', data2$TIMESTAMP, perl=TRUE) 
data2$TIMESTAMP = sub('(?<=.{17})', '.', data2$TIMESTAMP, perl=TRUE) 
xts_data2 = xts(data2[,c(2,3)], order.by = as.POSIXct(data2$TIMESTAMP, tz = "EST", format = "%Y%m%d %H:%M:%OS")) #Convert file to an xts object 
rm(data2) #remove data2 object in order to save space 

data3<-read.csv("EURAUD_201503.csv", header = FALSE, col.names = c("TIMESTAMP", "BID", "OFR", "VOL"), stringsAsFactors = FALSE) 
data3$VOL<- NULL #drops the VOL column 
data3$TIMESTAMP = sub('(?<=.{11})', ':', data3$TIMESTAMP, perl=TRUE) #manipulate the strings to create clear timestamps 
data3$TIMESTAMP = sub('(?<=.{14})', ':', data3$TIMESTAMP, perl=TRUE) 
data3$TIMESTAMP = sub('(?<=.{17})', '.', data3$TIMESTAMP, perl=TRUE) 
xts_data3 = xts(data3[,c(2,3)], order.by = as.POSIXct(data3$TIMESTAMP, tz = "EST", format = "%Y%m%d %H:%M:%OS")) #Convert file to an xts object 
rm(data3) #remove data3 object in order to save space 

#Create 5-minute intervals 
final_xts = rbind.xts(xts_data1, xts_data2, xts_data3) 
rm(data1_xts, data2_xts, data3_xts) 
final_fivemin = aggregatets(final_xts, FUN = "previoustick", on = "minutes", k = 5) 

Wie kann ich eine funktionelle Schleife erstellen, ohne die gleiche Prozedur für jede Datensatz zu wiederholen?

Answer 1

Scheint so, als ob Sie vielleicht versuchen möchten lapply. Sie könnten die for Schleife mit

xts_data <- lapply(real_data, function(x){ 
    data <- read.csv(x, header = FALSE, col.names = c("TIMESTAMP", "BID", "OFR", "VOL"), 
     stringsAsFactors = FALSE) 
    data$VOL<- NULL #drops the VOL column 
    data$TIMESTAMP = sub('(?<=.{11})', ':', data[i]$TIMESTAMP, perl=TRUE) #manipulate the strings to create clear timestamps 
    data$TIMESTAMP = sub('(?<=.{14})', ':', data[i]$TIMESTAMP, perl=TRUE) 
    data$TIMESTAMP = sub('(?<=.{17})', '.', data[i]$TIMESTAMP, perl=TRUE) 
    return(xts(data[,c(2,3)], 
     order.by = as.POSIXct(data$TIMESTAMP, tz = "EST", format = "%Y%m%d %H:%M:%OS"))) 
     #Convert file to an xts object 
}) 

ersetzen Und dann beenden:

#Create 5-minute intervals 
final_xts = do.call(rbind, xts_data) 
final_fivemin = aggregatets(final_xts, FUN = "previoustick", on = "minutes", k = 5)