Last active
December 15, 2015 12:39
-
-
Save tomaskrehlik/5262087 to your computer and use it in GitHub Desktop.
Data.table: apply window function by index variable
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Lag-function lags the given variable by the date_variable | |
lag_variable <- function(data, variable, lags, date_variable = c("Date")) { | |
if (lags == 0) { | |
return(data) | |
} | |
if (lags>0) { | |
name <- "lag" | |
} else { | |
name <- "forward" | |
} | |
require(data.table) | |
setkeyv(data, date_variable) | |
if (lags>0) { | |
data[,index:=seq(1:.N)] | |
} else { | |
data[,index:=rev(seq(1:.N))] | |
} | |
setkeyv(data, "index") | |
lags <- abs(lags) | |
position <- which(names(data)==variable) | |
for ( j in 1:lags ) { | |
lagname <- paste(variable,"_",name,j,sep="") | |
lag <- paste("data[, ",lagname,":=data[list(index-",j,"), ",variable,", roll=TRUE][[",position,"L]]]", sep = "") | |
eval(parse( text = lag )) | |
} | |
setkeyv(data, date_variable) | |
data[,index:=NULL] | |
} | |
# window_func applies the function to the lagged or forwarded variables created by lag_variable | |
window_func <- function(data, func.name, variable, direction = "window", steps, date_variable = c("Date"), clean = TRUE) { | |
require(data.table) | |
require(stringr) | |
transform <- match.fun(func.name) | |
l <- length(names(data)) | |
if (direction == "forward") { | |
lag_variable(data, variable, -steps, date_variable) | |
cols <- which((!(is.na(str_match(names(a), paste(variable,"_forward(",paste(1:steps,collapse="|"),")",sep=""))[,1])))*1==1) | |
} else { | |
if (direction == "backward") { | |
lag_variable(data, variable, steps, date_variable) | |
cols <- which((!(is.na(str_match(names(a), paste(variable,"_lag(",paste(1:steps,collapse="|"),")",sep=""))[,1])))*1==1) | |
} else { | |
if (direction == "window") { | |
lag_variable(data, variable, -steps, date_variable) | |
lag_variable(data, variable, steps, date_variable) | |
cols <- which((!(is.na(str_match(names(a), paste(variable,"_lag(",paste(1:steps,collapse="|"),")",sep=""))[,1])))*1==1) | |
cols <- c(cols,which((!(is.na(str_match(names(a), paste(variable,"_forward(",paste(1:steps,collapse="|"),")",sep=""))[,1])))*1==1)) | |
} else { | |
stop("The direction must be either backward, forward or window.") | |
} | |
} | |
} | |
data[,transf := apply(data[,cols, with=FALSE], 1, transform)] | |
if (clean) { | |
data[,cols:=NULL,with=FALSE] | |
} | |
return(data) | |
} | |
# Typical use: | |
# I have a data.table DT with variables Date, value1, value2 | |
# I want to get cumulative sum of next five days | |
# window_func(DT, "sum", "value1", direction = "forward", steps = 5) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment