Question

我对R很新，并提前道歉我的帖子不是通常的格式（我尝试使用dput()但得到一个奇怪的输出，不知道如何上传数据集我很抱歉）。

我有一个包含6个colums的数据集（site，startdate，enddate，photodate，species，indiv）。例如：

site    year    startdate   enddate photodate   species indiv
M1_7    2012    19/07/2012  10/08/2012  20/07/2012  Sylvicapra grimmia  1
M1_7    2012    19/07/2012  10/08/2012  23/07/2012  Crocuta crocuta 1
M1_7    2012    19/07/2012  10/08/2012  23/07/2012  Potamochoerus larvatus  1
M1_7    2012    19/07/2012  10/08/2012  25/07/2012  Hystrix cristata    1
M1_7    2012    19/07/2012  10/08/2012  27/07/2012  Potamochoerus larvatus  1
M1_7    2012    19/07/2012  10/08/2012  27/07/2012  Sylvicapra grimmia  1
M1_7    2012    19/07/2012  10/08/2012  28/07/2012  Hippotragus equinus     1
M1_7    2012    19/07/2012  10/08/2012  30/07/2012  Crocuta crocuta 1
M1_7    2012    19/07/2012  10/08/2012  01/08/2012  Equus q. boehmi 1
M1_7    2012    19/07/2012  10/08/2012  01/08/2012  Crocuta crocuta 1
M1_7    2012    19/07/2012  10/08/2012  05/08/2012  Potamochoerus larvatus  1
M1_7    2012    19/07/2012  10/08/2012  07/08/2012  Hippotragus equinus     1
M1_9    2012    21/07/2012  11/08/2012  24/07/2012  Pedetes capensis    1
M1_9    2012    21/07/2012  11/08/2012  24/07/2012  Crocuta crocuta 2
M1_9    2012    21/07/2012  11/08/2012  24/07/2012  Pedetes capensis    1
M1_9    2012    21/07/2012  11/08/2012  27/07/2012  Pedetes capensis    1
M1_9    2012    21/07/2012  11/08/2012  01/08/2012  Alcelaphus b. lichtensteinii    1
M1_9    2012    21/07/2012  11/08/2012  03/08/2012  Pedetes capensis    1
M1_9    2012    21/07/2012  11/08/2012  04/08/2012  Crocuta crocuta 1
M1_9    2012    21/07/2012  11/08/2012  06/08/2012  Pedetes capensis    1
M1_9    2012    21/07/2012  11/08/2012  07/08/2012  Pedetes capensis    1
M1_9    2012    21/07/2012  11/08/2012  08/08/2012  Pedetes capensis    1
M1_11   2012    21/07/2012  11/08/2012  26/07/2012  Mellivora capensis  1
M1_11   2012    21/07/2012  11/08/2012  03/08/2012  Sylvicapra grimmia  1
M1_11   2012    21/07/2012  11/08/2012  07/08/2012  Hystrix cristata    1
M1_11   2012    21/07/2012  11/08/2012  08/08/2012  Potamochoerus larvatus  1

我一直在尝试编写一个循环，创建一个49列矩阵，其中第1列对应于站点，第2列为站点内“startdate”和“enddate”之间的日期序列，第3:49列到物种名称。在第3:49列的单元格中，我想在特定日期为特定物种总结计数数据（indiv）得出的数据。

到目前为止，我只能创建一个对应于我想要的空矩阵，但无法填写数据。这是我用过的代码：

mlele2012<- read.delim("C:\\multiple regression\\mlele 2012 empty matrix creation.txt")
africa <- read.delim("C:\\species accumulation curves\\COMPLETE species list.txt")
specieslistx<-unique(africa)
specieslistx<-t(specieslistx) 

oldtemp<-NULL 
temp <- rep(0, length(specieslistx ))

strptime(mlele2012$photodate, "%Y-%m-%d")
strptime(mlele2012$startdate, "%d/%m/%Y")
strptime(mlele2012$enddate, "%d/%m/%Y")

#create empty dataframe with dimensions: no. of sites x no. of dates in each

for(i in levels(mlele2012$site))    { ##for each site

    sitetemp <- subset(mlele2012, site == i) ###subset of dataset , for the particular site i##

    sitetemp$startdate<- as.Date(sitetemp$startdate, "%d/%m/%Y")
    sitetemp$enddate<- as.Date(sitetemp$enddate, "%d/%m/%Y")

    sitedatelist<-seq(as.Date(sitetemp$startdate[1]), as.Date(sitetemp$enddate[1]), "days")

    empty<-matrix(0,length(sitedatelist),length(specieslistx))
    sitedatelist1<-as.character(sitedatelist)
    row.names(empty)<-(sitedatelist1)
    colnames(empty)<-specieslistx

    addsitecol<-matrix(0,length(sitedatelist),1)
    extendempty<-cbind(addsitecol,empty)
    extendempty[,1]<-i
    oldtemp<-rbind(oldtemp, extendempty)
}

write.csv(oldtemp, "Mlele 2012 dry empty.csv")

此外，我一直试图提取以相同的格式/维度创建另一个矩阵，但没有多余的日期（即只有“photodate”列中的日期而不是“startdate”和“enddate”之间的序列）。我希望我最终能以某种方式合并两个矩阵以获得我最终需要的东西。不幸的是，这段代码不起作用，尽管似乎没有错误。这是我的代码的第二部分：

for(i in mlele2012$site)    {    
   sitetemp <- subset(mlele2012, site == i) ###subset of dataset "allsites", for the particular site i##
   for(j in sitetemp$photodate){
      datetemp <- subset(sitetemp, photodate == j) ###subset of dataset "africaa", for the particular date i#
      uniquespperdate <- unique(datetemp$species)###unique species within each date (row) i#
      temp <- rep(0, length(specieslistx)) #create a temporary vector of 0s with the same length as the species list###

      for(a in uniquespperdate){
         sptemp <- subset(datetemp , species == a) ###subset of dataset "sitetemp", for the particular sp j##
         countdata<-sum(sptemp$indiv)
         index <- pmatch(a, names(temp)) ###match the unique species per date to the location on the species list###
         #there is a problem here, it works when run as a single line but not within a loop
         temp[index] <- countdata   ###for the locations listed in "index", assign the count data to the temporary vector###
         names(temp)<- specieslistx
      }
   }        
   oldtemp <- rbind(oldtemp, temp) ### bind the new temp file to the old temp file, i.e. update the list as the loop runs###
}

非常感谢任何帮助。如果有任何细节可以让我更清楚，请告诉我。

Answer 1

我可以通过以下方式获得样品的大部分内容：

> ftable(xtabs(indiv~site+year+species, data=dat) )
           species boehmi capensis cristata crocuta equinus grimmia larvatus lichtensteinii
site  year                                                                                 
M1_11 2012              0        1        1       0       0       1        1              0
M1_7  2012              1        0        1       3       2       2        3              0
M1_9  2012              0        7        0       3       0       0        0              1

我确实使用genus / species作为两列输入数据，因为您没有提供请求的dput版本。

Answer 2

有点乱，但没有初始化空矩阵，您可以执行以下操作：

如果df是您的初始数据：

result = do.call("rbind",lapply(levels(df$site),function(x){
    do.call("rbind",lapply(levels(df$startdate),function(y){
        do.call("rbind",lapply(levels(df$enddate),function(z){
            foo <- rep(0,length(levels(df$species)))
            names(foo) <- levels(df$species)
            foo[df$species[df$site==x & df$startdate==y & df$enddate==z]] <- df$indiv[df$site==x & df$startdate==y & df$enddate==z]
            c(x,y,z,foo)
        }))
    }))
}))

result应包含您寻求的矩阵（我希望）。

创建空矩阵并在R中填写日期匹配值

2 个答案: