Question

对R来说相对较新，所以要提前道歉，因为无能为力。

多年来，我正在一个国家/地区的多个站点上处理几个（非常大的）观测数据集。我需要计算在第x周中提交观察的站点总数中已记录特定物种的站点的比例（基本上是存在/不存在数据）。我有一个数据集，提供每个人的详细信息物种观察，以及每周观测总数的另一个。因此，我需要一些功能来计算该周记录物种的站点数量，然后将其除以记录同一周内任何物种观测值的站点总数。观察结果记录为一周（1-53）和一年（1995-2011）。

species.data的例子（为了便于粘贴而列为csv）：

SITE_ID, SPECIES, WEEKNO, YEAR
1289, Attenb., 1, 1995
1538, Attenb., 1, 1995
1894, Attenb., 2, 1995
1286, Attenb., 4, 1995
1238, Attenb., 7, 1995
1892, Attenb., 7, 1995

total.obs.data的例子：

YEAR, WEEKNO, TOTALOBS,
1995, 1, 100
1995, 2, 780
1995, 3, 100
1995, 4, 189
1995, 5, 382
1995, 6, 100
1995, 7, 899
1995, 8, 129

（所以我在1995年的第1周我不会那么比例是2/100，能够构建GLM或GAM）

Answer 1

让我试一试，同时注意上述评论中已经陈述的问题的所有限制

#Create the data frame with the total observations
tot.obs<-data.frame(year=rep(1995,10), weekno=1:10, obs=floor(runif(n=10,80,100)))
#Create the variable week-year
tot.obs$week.year<-paste(tot.obs$week,tot.obs$year,sep="-")

#Create the data frame species observations
species.data<-data.frame(site=factor(floor(runif(n=5,2000,3000))), week=c(1,1,2,4,7), year=rep(1995,5),observ=rep(1,5))
species.data$week.year<-paste(species.data$week,species.data$year,sep="-")
species.data$total.obs<-NA

#Match the total observations form the tot.obs data frame to the species data frame. You can probably do it much faster but here is a "quick and dirty way"

for (i in 1:dim(species.data)[1]){
  species.data$total.obs[i]<-tot.obs$obs[tot.obs$week.year==species.data$week.year[i]]  
}

#Calculates the percentage of the total observation that each center contributes
species.data$per.obs<-species.data$observ/ species.data$total.obs 

#For the presentation of the data, reshape is your friend
library(reshape)
species.data.melt<-melt(species.data,id.vars=c("site","week.year"), measure.vars="per.obs")

cast(species.data.melt,site~week.year, fun.aggregate=sum)


site     1-1995     2-1995     4-1995     7-1995
1 2436 0.00000000 0.00000000 0.01010101 0.00000000
2 2501 0.00000000 0.01123596 0.00000000 0.00000000
3 2590 0.00000000 0.00000000 0.00000000 0.01123596
4 2608 0.01030928 0.00000000 0.00000000 0.00000000
5 2942 0.01030928 0.00000000 0.00000000 0.00000000

否则，如果您对每个中心的观察不感兴趣，那么事情会更容易：

species.data.melt2<-melt(species.data,id.vars=c("week.year"), measure.vars="observ")
species.obs.total<-data.frame(cast(species.data.melt2,week.year~value, fun.aggregate=sum))
colnames(species.obs.total)[2]<-"aggregated.total"
species.obs.total$total<-NA

for (i in 1:dim(species.obs.total)[1]){
  species.obs.total$total[i]<-tot.obs$obs[tot.obs$week.year==species.obs.total$week.year[i]]  
}

species.obs.total$perc<-species.obs.total$aggregated.total/ species.obs.total$total
species.obs.total


  week.year aggregated.total total       perc
1    1-1995                2    97 0.02061856
2    2-1995                1    89 0.01123596
3    4-1995                1    99 0.01010101
4    7-1995                1    89 0.01123596

Answer 2

目前数据过于简单，无法支持测试的复杂性。 xtabs函数创建一个矩阵对象，可以除以该周的总数：

> xtblspec <-  xtabs( ~ SPECIES+ SITE_ID +WEEKNO + YEAR  , data=dat)     
> xtblspec
, , WEEKNO = 1, YEAR = 1995

         SITE_ID
SPECIES   1238 1286 1289 1538 1892 1894
  Attenb.    0    0    1    1    0    0

, , WEEKNO = 2, YEAR = 1995

         SITE_ID
SPECIES   1238 1286 1289 1538 1892 1894
  Attenb.    0    0    0    0    0    1

, , WEEKNO = 4, YEAR = 1995

         SITE_ID
SPECIES   1238 1286 1289 1538 1892 1894
  Attenb.    0    1    0    0    0    0

, , WEEKNO = 7, YEAR = 1995

         SITE_ID
SPECIES   1238 1286 1289 1538 1892 1894
  Attenb.    1    0    0    0    1    0
#-------------

weekobs <- totobs[ match( as.numeric(dimnames(xtblspec[ 1, ,  ,])$WEEKNO ) ,totobs$WEEKNO) ,
                  "TOTALOBS"]
#[1] 100 780 189 899

要正确设置特定观察矩阵，以便矩阵分区正常工作，您需要将WEEKNO作为第一维：

xtblspec <-  xtabs( ~ WEEKNO +SPECIES+ SITE_ID  + YEAR  , data=dat)
> xtblspec/weekobs
, , SITE_ID = 1238, YEAR = 1995

      SPECIES
WEEKNO     Attenb.
     1 0.000000000
     2 0.000000000
     4 0.000000000
     7 0.001112347

, , SITE_ID = 1286, YEAR = 1995

      SPECIES
WEEKNO     Attenb.
     1 0.000000000
     2 0.000000000
     4 0.005291005
     7 0.000000000

, , SITE_ID = 1289, YEAR = 1995

      SPECIES
WEEKNO     Attenb.
     1 0.010000000
     2 0.000000000
     4 0.000000000
     7 0.000000000

, , SITE_ID = 1538, YEAR = 1995

      SPECIES
WEEKNO     Attenb.
     1 0.010000000
     2 0.000000000
     4 0.000000000
     7 0.000000000

, , SITE_ID = 1892, YEAR = 1995

      SPECIES
WEEKNO     Attenb.
     1 0.000000000
     2 0.000000000
     4 0.000000000
     7 0.001112347

, , SITE_ID = 1894, YEAR = 1995

      SPECIES
WEEKNO     Attenb.
     1 0.000000000
     2 0.001282051
     4 0.000000000
     7 0.000000000

计算数据帧中变量的重复并计算出它的比例

2 个答案: