r - .SD : calculating percentage change concisely 的数据表操作

Question

我正在尝试使用 data.table 简洁地计算一些百分比变化，但是我在完全理解 .SD 操作的工作原理时遇到了一些麻烦。

假设我有下表

dt = structure(list(type = c("A", "A", "A", "B", "B", "B"), Year = c(2000L, 
2005L, 2010L, 2000L, 2005L, 2010L), alpha = c(0.0364325563237498, 
0.0401968159729988, 0.0357395587861466, 0.0317236054181487, 0.0328213742235379, 
0.0294694430578336), beta = c(0.0364325563237498, 0.0401968159729988, 
0.0357395587861466, 0.0317236054181487, 0.0328213742235379, 0.0294694430578336
)), .Names = c("type", "Year", "alpha", "beta"), row.names = c(NA, 
-6L), class = c("data.table", "data.frame"))


> dt
##    type Year      alpha       beta
## 1:    A 2000 0.03643256 0.03643256
## 2:    A 2005 0.04019682 0.04019682
## 3:    A 2010 0.03573956 0.03573956
## 4:    B 2000 0.03172361 0.03172361
## 5:    B 2005 0.03282137 0.03282137
## 6:    B 2010 0.02946944 0.02946944

为了按类别计算 alpha 的百分比变化，我想出了以下代码:

dt[,change:=list(lapply(3:2,function(x)(.SD[x,alpha]/.SD[
(x-1),alpha]))),by=list(type)][][Year==2000,change:=NA]   

但有些事情告诉我，他们可能是一种更简洁的方式。特别是如果想要对两列执行百分比更改，以下将不起作用

dt[,c("changeAlpha","changeBeta"):=list(lapply(3:2,
function(x)(.SD[x]/.SD[(x-1)]))),by=list(type)][Year==2000,change:=NA][]

所以我求助于:

dt[,c("changeAlpha","changeBeta"):=list(
lapply(3:2,function(x)(.SD[x,alpha]/.SD[(x-1),alpha])),
lapply(3:2,function(x)(.SD[x,beta]/.SD[(x-1),beta]))),by=list(type)][
Year==2000,c("changeAlpha","changeBeta"):=list(NA,NA)][]

##        type Year      alpha       beta       changeAlpha        changeBeta
## 1:    A 2000 0.03643256 0.03643256                NA                NA
## 2:    A 2005 0.04019682 0.04019682  1.10332131557826  1.10332131557826
## 3:    A 2010 0.03573956 0.03573956 0.889114172877617 0.889114172877617
## 4:    B 2000 0.03172361 0.03172361                NA                NA
## 5:    B 2005 0.03282137 0.03282137  1.03460416276522  1.03460416276522
## 6:    B 2010 0.02946944 0.02946944 0.897873527693412 0.897873527693412

但是操作似乎是正确的，但收到了很多警告，这导致我来到这里。

我的思维方法是完全错误的还是进行此操作的正确方法？

Answer 1

您可以使用 shift来自 data.table 的函数 v1.9.6+

定义你的功能

myFunc <- function(x) x/shift(x)

选择要计算百分比的列

cols <- c("alpha", "beta")

或者，如果您想在除前两个之外的所有列上运行它

cols <- names(dt)[-(1:2)]

在列上运行函数

dt[, paste0("change", cols) := lapply(.SD, myFunc), by = type, .SDcols = cols][]
#    type Year      alpha       beta changealpha changebeta
# 1:    A 2000 0.03643256 0.03643256          NA         NA
# 2:    A 2005 0.04019682 0.04019682   1.1033213  1.1033213
# 3:    A 2010 0.03573956 0.03573956   0.8891142  0.8891142
# 4:    B 2000 0.03172361 0.03172361          NA         NA
# 5:    B 2005 0.03282137 0.03282137   1.0346042  1.0346042
# 6:    B 2010 0.02946944 0.02946944   0.8978735  0.8978735