Question

我一直在努力在两个特定数据帧之间合并列，并且还合并数据帧中的行并将它们的值相加。我想首先将表1中的“X”和“Y”列添加到表2的末尾。在表2中，重复了一些“城镇”如“城镇A”。我想合并这些行，同时在行中添加数据。

表1

       |        X|         Y |     
  |Town|
  |A   |       21|         23|           
  |A   |       21|         23|               
  |B   |       21|         23|               
  |C   |       21|         23|                
  |D   |       21|         23|                
  |D   |       21|         23|                
  |E   |       21|         23|                 
  |E   |       21|         23|               
  |F   |       21|         23|                
  |F   |       21|         23|

表2

       |Species A| Species B | Species C| Species D| Species E | Species F |    
  |Town|
  |A   |       21|         23|        15|        0 |         3 |          7| 
  |A   |       21|         23|        15|        0 |         3 |          7| 
  |B   |       21|         23|        15|        0 |         3 |          7| 
  |C   |       21|         23|        15|        0 |         3 |          7| 
  |D   |       21|         23|        15|        0 |         3 |          7| 
  |D   |       21|         23|        15|        0 |         3 |          7| 
  |E   |       21|         23|        15|        0 |         3 |          7| 
  |E   |       21|         23|        15|        0 |         3 |          7| 
  |F   |       21|         23|        15|        0 |         3 |          7| 
  |F   |       21|         23|        15|        0 |         3 |          7|

我尝试使用的一些代码是c.bind和merge函数，我也尝试使用run.seq，如下所示：

run.seq <- function(x) as.numeric(ave(paste(x), x, FUN = seq_along))
L <- list(df1, df2) 
L2 <- lapply(L, function(x) cbind(x, run.seq = run.seq("Town"))) 
out <- Reduce(function(...) merge(..., all = TRUE), L2)[-2]

哪个不太奏效。

哪种代码最适合此类合并/组合？

如果有帮助，我会附上下表的结构：

表1

structure(list(Town = c("A", "A", "B", "C", "D", "D", "E", "E", "F", "F"), Captured = c(168L, 16L, 243L, 12L, 17L, 15L, 7L, 233L, 14L, 12L), Proportion = c(0.23, 0.02, 0.33, 0.02, 0.02, 0.02, 0.01, 0.32, 0.02, 0.02)), class = "data.frame", .Names = c("Town", "Captured", "Proportion"), row.names = c(NA,-10L))

表2

structure(c(106L, 7L, 5L, 4L, 4L, 4L, 4L, 18L, 5L, 3L, 38L, 6L, 234L, 6L, 8L, 5L, 3L, 203L, 4L, 7L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 1L, 0L, 0L, 1L, 0L, 2L, 0L, 0L, 20L, 2L, 3L, 2L, 5L, 5L, 0L, 7L, 5L, 2L), .Dim = c(10L, 6L), .Dimnames = structure(list(Town = c("A", "A", "B", "C", "D", "D", "E", "E", "F", "F"), Species = c("funestus", "gambiae", "indeterminada", "outro", "pharoenois", "tenebrosus")), .Names = c("Town", "Species")), class = "table")

Answer 1

最好先汇总然后合并/加入两个数据集。使用 table 2 的表格格式，您还可以将 reshape2 的melt和dcast函数与sum一起用作聚合函数（生成数据框）然后与聚合的t1数据框合并：

library(reshape2)
# aggragate 't1'
t1sum <- aggregate(.~Town, t1, sum)
# reshape and aggregate 't2'
t2sum <- dcast(melt(t2), Town ~ Species, fun.aggregate = sum)
# or with 'as.data.frame(t2)' instead of 'melt(t2)'
t2sum <- dcast(as.data.frame(t2), Town ~ Species, fun.aggregate = sum)

merge(t1sum, t2sum, by = 'Town')

给出：

  Town Captured Proportion funestus gambiae indeterminada outro pharoenois tenebrosus
1    A      184       0.25      113      44             1     2          2         22
2    B      243       0.33        5     234             0     0          1          3
3    C       12       0.02        4       6             0     0          0          2
4    D       32       0.04        8      13             0     0          1         10
5    E      240       0.33       22     206             0     0          2          7
6    F       26       0.04        8      11             0     0          0          7

使用 data.table 包，您可以执行类似的操作：

library(data.table)
t1dt <- setDT(t1)[, lapply(.SD, sum), by = Town]
t2dt <- dcast(setDT(melt(t2)), Town ~ Species, fun.aggregate = sum)

t1dt[t2dt, on='Town']

使用过的数据：

t1 <- structure(list(Town = c("A", "A", "B", "C", "D", "D", "E", "E", "F", "F"), Captured = c(168L, 16L, 243L, 12L, 17L, 15L, 7L, 233L, 14L, 12L), Proportion = c(0.23, 0.02, 0.33, 0.02, 0.02, 0.02, 0.01, 0.32, 0.02, 0.02)), class = "data.frame", .Names = c("Town", "Captured", "Proportion"), row.names = c(NA,-10L))
t2 <- structure(c(106L, 7L, 5L, 4L, 4L, 4L, 4L, 18L, 5L, 3L, 38L, 6L, 234L, 6L, 8L, 5L, 3L, 203L, 4L, 7L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 1L, 0L, 0L, 1L, 0L, 2L, 0L, 0L, 20L, 2L, 3L, 2L, 5L, 5L, 0L, 7L, 5L, 2L), .Dim = c(10L, 6L), .Dimnames = structure(list(Town = c("A", "A", "B", "C", "D", "D", "E", "E", "F", "F"), Species = c("funestus", "gambiae", "indeterminada", "outro", "pharoenois", "tenebrosus")), .Names = c("Town", "Species")), class = "table")

合并数据框中的行并在数据框之间合并列

1 个答案: