R 选择范围可变的子集集

我必须在这个数据集（dat）上做出一组根据日期而变化的选择，该数据集由物种（sp）、日（日，在POSIXct中）和面积（ar）组成：

我需要对物种“A”出现的位置进行子集划分。但是，根据该矩阵（dat.ar），拟选择的区域将因日期而异：

更具体地说，对于物种“A”出现的区域，在00年1月1日，我只需要区域1和6。对于2000年1月2日、1区和12区，依此类推。 作为示例，本示例中该选择的期望输出如下所示：

sp  day        ar
A   2-Jan-00    1
A   4-Jan-00    3

我还没有成功地获得for循环，因为我仍在努力学习R中的语义。总之，对于必须做什么，我有一个大致的想法，但仍在努力学习该语言。下面是我认为应该做的事情的草图：

dat1 = with(dat,sapply(day[sp=="A" & dat.ar$day.s[i] ], 
function(x) ar == (ar[sp=="A" & day == x]==dat.ar$ar.select[j]) 
final=dat[rowSums(dat1) > 0, ]

我相信我必须适应一个for循环，它将通过dat.ar，指定要在dat中选择的区域。但是，尽管我努力尝试进入for循环，我还是没有接近。我甚至不确定将sappy和for循环结合起来是否是正确的方法。 如果有人希望重现问题：

sp=c("A","B","C","A","D","E","F","A","G","B")
day=c("1-Jan-00", "1-Jan-00", "2-Jan-00", "2-Jan-00", "2-Jan-00", 
"2-Jan-00", "3-Jan-00", "4-Jan-00", "4-Jan-00", "4-Jan-00")
day=as.POSIXct(day, format="%d-%b-%y")
ar=c(2,6,2,1,4,12,8,3,2,1)
dat= as.data.frame(cbind(sp, day, ar)) 

day.s=c("1-Jan-00", "2-Jan-00", "3-Jan-00", "4-jan-00")
day.s=as.POSIXct(day.s, format="%d-%b-%y")
a.s=c(1,1,4,3)
a.e=c(6,12,8,12)
ar.select=paste(a.s, a.e, sep=",")
dat.ar=cbind(day.s, ar.select)

---

非常感谢您的帮助。

您可以将条件表合并到原始数据集中，并有条件地进行筛选。考虑A1和A2，像你的SP和日值，OBS就像你的AR值。< /P>

library(data.table)
dataset <- data.table(
a1 = c("A","B","C","B","A","A","A","A"),
a2 = c("P","Q","Q","Q","R","R","P","Q"),
obs = c(3,2,3,4,2,4,8,0)
)

constraints <- data.table(
a1 = c("A","B","C","A","B","C","A","B","C"),
a2 = c("P","P","P","Q","Q","Q","R","R","R"),
lower = c(1,2,3,4,3,2,3,2,5),
upper = c(6,4,5,7,5,6,5,3,7)
)


checkingdataset <- merge(dataset,constraints, by = c("a1","a2"), all.x = TRUE)

checkingdataset[obs <= upper & obs >= lower, obs.keep := TRUE]


#   a1 a2 obs lower upper obs.keep
#1:  A  P   3     1     6    TRUE
#2:  A  P   8     1     6      NA
#3:  A  Q   0     4     7      NA
#4:  A  R   2     3     5      NA
#5:  A  R   4     3     5    TRUE
#6:  B  Q   2     3     5      NA
#7:  B  Q   4     3     5    TRUE
#8:  C  Q   3     2     6    TRUE

库（data.table）
dataset您可以将条件表合并到原始数据集，并有条件地对其进行筛选。考虑A1和A2，像你的SP和日值，OBS就像你的AR值。< /P>
library(data.table)
dataset <- data.table(
a1 = c("A","B","C","B","A","A","A","A"),
a2 = c("P","Q","Q","Q","R","R","P","Q"),
obs = c(3,2,3,4,2,4,8,0)
)

constraints <- data.table(
a1 = c("A","B","C","A","B","C","A","B","C"),
a2 = c("P","P","P","Q","Q","Q","R","R","R"),
lower = c(1,2,3,4,3,2,3,2,5),
upper = c(6,4,5,7,5,6,5,3,7)
)


checkingdataset <- merge(dataset,constraints, by = c("a1","a2"), all.x = TRUE)

checkingdataset[obs <= upper & obs >= lower, obs.keep := TRUE]


#   a1 a2 obs lower upper obs.keep
#1:  A  P   3     1     6    TRUE
#2:  A  P   8     1     6      NA
#3:  A  Q   0     4     7      NA
#4:  A  R   2     3     5      NA
#5:  A  R   4     3     5    TRUE
#6:  B  Q   2     3     5      NA
#7:  B  Q   4     3     5    TRUE
#8:  C  Q   3     2     6    TRUE

库（data.table）
dataset首先，我不会使用
as.data.frame（cbind（…）
来创建您的
data.frame
s。第二，我将创建
dat.ar
，其结构与您创建的
dat
基本相同。第三，我只需要使用
merge
就可以得到您想要的结果

dat <- data.frame(sp=c("A","B","C","A","D","E","F","A","G","B"),
                  day=c("1-Jan-00", "1-Jan-00", "2-Jan-00", "2-Jan-00", 
                        "2-Jan-00", "2-Jan-00", "3-Jan-00", "4-Jan-00", 
                        "4-Jan-00", "4-Jan-00"),
                  ar=c(2,6,2,1,4,12,8,3,2,1))
dat$day <- as.POSIXct(dat$day, format="%d-%b-%y")

day.s <- c("1-Jan-00", "2-Jan-00", "3-Jan-00", "4-jan-00")
day.s <- as.POSIXct(day.s, format="%d-%b-%y")
a.s <- c(1,1,4,3)
a.e <- c(6,12,8,12)
ar.select <- paste(a.s, a.e, sep=",")
dat.ar <- data.frame(sp = "A", day = day.s, ar = ar.select)

dat.ar <- cbind(dat.ar[-3], 
                read.csv(text = as.character(dat.ar$ar), header = FALSE))
library(reshape2)
dat.ar <- melt(dat.ar, id.vars=1:2, value.name="ar")
dat.ar
#   sp        day variable ar
# 1  A 2000-01-01       V1  1
# 2  A 2000-01-02       V1  1
# 3  A 2000-01-03       V1  4
# 4  A 2000-01-04       V1  3
# 5  A 2000-01-01       V2  6
# 6  A 2000-01-02       V2 12
# 7  A 2000-01-03       V2  8
# 8  A 2000-01-04       V2 12

merge(dat, dat.ar)
#   sp        day ar variable
# 1  A 2000-01-02  1       V1
# 2  A 2000-01-04  3       V1

首先，我不会使用
as.data.frame（cbind（…）
来创建
data.frame
s。第二，我将创建
dat.ar
，其结构与您创建的
dat
基本相同。第三，我只需要使用
merge
就可以得到您想要的结果

dat <- data.frame(sp=c("A","B","C","A","D","E","F","A","G","B"),
                  day=c("1-Jan-00", "1-Jan-00", "2-Jan-00", "2-Jan-00", 
                        "2-Jan-00", "2-Jan-00", "3-Jan-00", "4-Jan-00", 
                        "4-Jan-00", "4-Jan-00"),
                  ar=c(2,6,2,1,4,12,8,3,2,1))
dat$day <- as.POSIXct(dat$day, format="%d-%b-%y")

day.s <- c("1-Jan-00", "2-Jan-00", "3-Jan-00", "4-jan-00")
day.s <- as.POSIXct(day.s, format="%d-%b-%y")
a.s <- c(1,1,4,3)
a.e <- c(6,12,8,12)
ar.select <- paste(a.s, a.e, sep=",")
dat.ar <- data.frame(sp = "A", day = day.s, ar = ar.select)

dat.ar <- cbind(dat.ar[-3], 
                read.csv(text = as.character(dat.ar$ar), header = FALSE))
library(reshape2)
dat.ar <- melt(dat.ar, id.vars=1:2, value.name="ar")
dat.ar
#   sp        day variable ar
# 1  A 2000-01-01       V1  1
# 2  A 2000-01-02       V1  1
# 3  A 2000-01-03       V1  4
# 4  A 2000-01-04       V1  3
# 5  A 2000-01-01       V2  6
# 6  A 2000-01-02       V2 12
# 7  A 2000-01-03       V2  8
# 8  A 2000-01-04       V2 12

merge(dat, dat.ar)
#   sp        day ar variable
# 1  A 2000-01-02  1       V1
# 2  A 2000-01-04  3       V1

dat.ar <- data.frame(sp = "A", 
                     day = c("1-Jan-00", "2-Jan-00", "3-Jan-00", "4-jan-00"),
                     a.s = c(1,1,4,3), a.e = c(6,12,8,12))
dat.ar$day <- as.POSIXct(dat.ar$day, format="%d-%b-%y")

library(reshape2)
dat.ar <- melt(dat.ar, id.vars=1:2, value.name="ar")