没有聚合的 reshape2 dcast - seq 问题

Question

我尝试从中 reshape 数据集(mydata - 片段)

    sample          species         cell_nr biovol
1   41442bay_1      Mytilus sp.     6.22    1243.04
2   41502elba_1     Mytilus sp.     1.35    260.64
3   41502bay_3      Mytilus sp.     2.74    548.21
4   41443bay_2      M. edulis       599.14  114028.15
5   41411elba_2     M. edulis       5107.51 1021502.16

对此(结果)

  sample     variable Mytilus sp.    M. edulis
1 41442bay_1 cell_nr  6.22           0
2 41442bay_1 biovol   1243.04        0
3 41443bay_2 cell_nr  0              599.14
4 41443bay_2 biovol   0              114028.15

到目前为止，我在 R 中使用了 reshape2

mymelt <- melt(mydata, id=c("species", "sample"))
result <- dcast(mymelt, sample+variable~species)

但它聚合了我的变量

Aggregation function missing: defaulting to length

我需要我的一对变量的唯一 ID，以便在不聚合的情况下 reshape - 正如我通过阅读这两个线程所理解的那样:how-to-use-cast-in-reshape-without-aggregation & reshaping-data-frame-with-duplicates

然而，我卡在了这一点上。欢迎任何帮助，并在此先感谢您。

//已编辑

//编辑2

这是“mydata”的一个子集——起始表——两个采样点和两个变量 & 和分类单元

structure(list(sample = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("41411bay_1", 
"41411elba_1"), class = "factor"), genspec = structure(c(1L, 
2L, 5L, 6L, 8L, 9L, 10L, 11L, 13L, 18L, 14L, 15L, 16L, 17L, 19L, 
20L, 21L, 22L, 23L, 12L, 24L, 25L, 26L, 27L, 3L, 4L, 5L, 6L, 
7L, 7L, 8L, 9L, 10L, 11L, 14L), .Label = c("Achnanthes_taeniata", 
"Asterionella_formosa", "Chaetoceros_ceratosporus", "Chaetoceros_compressus", 
"Chaetoceros_simplex", "Chaetoceros_socialis", "Chaetoceros_sp.", 
"Chaetoceros_wighamii", "Chroococcus_minimus", "Chrysophyte_", 
"Cryptophyte_", "decaying_dino", "decaying_dino_", "Gymnodinium_sp.", 
"Melosira_nummuloides", "Monoraphidium_contortum", "Mougeotia_sp.", 
"Mytilus_sp.", "Navicula_sp.", "Protoperidinium_pellucidum", 
"Protoperidinium_sp.", "Quadrigula_sp.", "Rhabdoderma_lineare", 
"Skeletonema_costatum", "Surirella_sp.", "Thalassionema_nitzschioides", 
"Thalassiosira_sp."), class = "factor"), total_cell_nr = c(570.14, 
142.54, 30.54, 95.02, 213.8, 6246.1, 1924.23, 71.27, 47.51, 23.76, 
71.27, 23.76, 35.63, 11.88, 35.63, 59.39, 47.51, 35.63, 95.02, 
59.39, 6235.91, 11.88, 35.63, 11.88, 487.34, 314.42, 15.72, 110.05, 
408.74, 31.44, 267.25, 35471.82, 13119.72, 534.51, 15.72), total_biovol = c(114028.15, 
74830.97, 25900.68, 23850.89, 500084.7, 51217.98, 769690, 15465.07, 
342702.1, 11877.93, 5485537.87, 102340.26, 1460.99, 64200.22, 
74830.97, 1640342.42, 656754.62, 7483.1, 2375.59, 428377.62, 
860556.18, 950234.57, 37059.15, 35633.8, 207121.44, 107530.22, 
13331.23, 27621.43, 163904.98, 12608.08, 625105.87, 290868.96, 
5247886.36, 115988.01, 1210045.12)), .Names = c("sample", "genspec", 
"total_cell_nr", "total_biovol"), class = "data.frame", row.names = c(NA, 
-35L))

我正在做这个

mymelt <- melt(mydata, id.vars=c("genspec", "sample"))
mymelt$indx <- with(mymelt, ave(seq_along(genspec), genspec, sample, FUN=seq_along))
result <- dcast(mymelt, sample+variable+indx~genspec, value.var='value', fill=0)

我希望结果是 4 个 obs。 (两个站点和两个变量)，但我得到了 7 个观测值。 bay_1 有重复的样本，但 elba_1 没有——这发生在原始数据集中的整个结果中。我想这是一个非常基本的问题，答案很简单，但我看不到。

//编辑3

好的，我知道这里发生了什么——我的样本中有重复的 genspec(即物种)。这给 akrun 的整体工作答案带来了困惑。为了明白我的意思，请对上面粘贴的 df 使用以下命令 - 我删除了重复的样本，一切正常:

mydata <- mydata[-30,]
mymelt <- melt(mydata, id.vars=c("genspec", "sample"))
mymelt$indx <- with(mymelt, ave(seq_along(genspec), genspec, sample, FUN=seq_along))
result <- dcast(mymelt, sample+variable+indx~genspec, value.var='value', fill=0)

Answer 1

您可能需要创建一个序列列

mymelt$indx <- with(mymelt, ave(seq_along(species), species, FUN=seq_along))
dcast(mymelt, sample+variable+indx~species, value.var='value', fill=0)
#        sample variable indx  M. edulis Mytilus sp.
#1  41411elba_2  cell_nr    2    5107.51        0.00
#2  41411elba_2   biovol    4 1021502.16        0.00
#3   41442bay_1  cell_nr    1       0.00        6.22
#4   41442bay_1   biovol    4       0.00     1243.04
#5   41443bay_2  cell_nr    1     599.14        0.00
#6   41443bay_2   biovol    3  114028.15        0.00
#7   41502bay_3  cell_nr    3       0.00        2.74
#8   41502bay_3   biovol    6       0.00      548.21
#9  41502elba_1  cell_nr    2       0.00        1.35
#10 41502elba_1   biovol    5       0.00      260.64

编辑

如果数据集仍然有重复项，尝试

 mymelt$indx <- with( mymelt,
                      ave(seq_along(species),
                          species,
                          sample,
                          FUN=seq_along
                      )
                )
 dcast(mymelt, sample+variable+indx~species, value.var='value', fill=0)

数据

 mydata <- structure(
               list(sample  = c("41442bay_1", "41502elba_1", "41502bay_3", "41443bay_2", "41411elba_2"),
                    species = c("Mytilus sp.", "Mytilus sp.", "Mytilus sp.", "M. edulis", "M. edulis"),
                    cell_nr = c(6.22, 1.35, 2.74, 599.14, 5107.51),
                    biovol  = c(1243.04, 260.64, 548.21, 114028.15, 1021502.16)
               ),
               .Names    = c("sample", "species", "cell_nr", "biovol"),
               class     = "data.frame",
               row.names = c("1", "2", "3", "4", "5")
           )