Question

我有以下数据框：

structure(list(vnum1 = c(-1.38, 1.22, -0.17, -0.47, -0.08, -1.11, 
-1.56, -0.14, 0.55, -0.43, 0.25, 0.8, 0.77, -0.1, -0.21, -0.62, 
-0.6, -0.19, -0.41, 0.11, -0.46, -3.08, -2.09, 1.27, -1.5, 0.57, 
-1.69, 0.86, -0.12, -0.22, -0.85, 0.66, 0.11, -1.15, 0.32, -0.36, 
-0.42, -1.17, -0.71, 0.45, -0.41, 0.43, 2.18, 0.39, 0.1, -0.12, 
1.64, -1.24, -1.14, 1.22), vint1 = c(7L, 7L, 9L, 6L, 6L, 2L, 
8L, 10L, 8L, 8L, 10L, 5L, 7L, 4L, 7L, 4L, 2L, 9L, 3L, 7L, 4L, 
9L, 3L, 4L, 10L, 10L, 1L, 6L, 4L, 2L, 1L, 6L, 10L, 9L, 3L, 9L, 
3L, 8L, 7L, 7L, 3L, 4L, 5L, 6L, 5L, 9L, 3L, 10L, 10L, 4L), vfac1 = structure(c(2L, 
4L, 2L, 1L, 1L, 2L, 3L, 3L, 3L, 2L, 4L, 2L, 2L, 3L, 2L, 3L, 3L, 
3L, 1L, 2L, 1L, 2L, 3L, 3L, 3L, 1L, 2L, 2L, 3L, 2L, 1L, 3L, 3L, 
2L, 4L, 2L, 4L, 3L, 1L, 1L, 2L, 4L, 3L, 4L, 1L, 1L, 2L, 1L, 1L, 
4L), .Label = c("1", "2", "3", "4"), class = "factor")), .Names = c("vnum1", 
"vint1", "vfac1"), row.names = c(NA, -50L), class = "data.frame")


> head(ddf)
  vnum1 vint1 vfac1
1 -1.38     7     2
2  1.22     7     4
3 -0.17     9     2
4 -0.47     6     1
5 -0.08     6     1
6 -1.11     2     2
>

我想创建一个矩阵，其中vint1的唯一值为行，vfac1的唯一值为列。对于相应的vint1和vfac1，矩阵需要用vnum1的平均值填充。我尝试了以下功能：

df2mat = function(gdf){
        for(i in sort(unique(vint1))) cat("\t",i)
        cat("\n")
        for(j in sort(levels(vfac1))) {
                cat("j:",j)
                sum =0
                for(j in 1:10){
                        cat(with(gdf[vint1==i & vfac1==j,], mean(vnum1, na.rm=T)),"\t")
                        #cat("\t")
                        }
                cat("\n")
        }
        cat("\n")
}   

> df2mat(ddf)
         1       2       3       4       5       6       7       8       9       10
j: 1-0.6033333  NaN     -0.51   0.25    NaN     NaN     NaN     NaN     NaN     NaN 
j: 2-0.6033333  NaN     -0.51   0.25    NaN     NaN     NaN     NaN     NaN     NaN 
j: 3-0.6033333  NaN     -0.51   0.25    NaN     NaN     NaN     NaN     NaN     NaN 
j: 4-0.6033333  NaN     -0.51   0.25    NaN     NaN     NaN     NaN     NaN     NaN

由于重复第一行的值，因此产生的输出不正确。此外，缺失值会产生NaN错误。另外，我怎样才能将它变成一个合适的矩阵对象？我该如何纠正这些问题。谢谢你的帮助。

Answer 1

这可以很好地利用标准tapply和两个因素。你可以做到

with(ddf, tapply(vnum1, list(vint1,vfac1), mean))

#            1       2          3      4
#1  -0.8500000 -1.6900         NA     NA
#2          NA -0.6650 -0.6000000     NA
#3  -0.4100000  0.6150 -2.0900000 -0.050
#4  -0.4600000      NA  0.1075000  0.825
#5   0.1000000  0.8000  2.1800000     NA
#6  -0.2750000  0.8600  0.6600000  0.390
#7  -0.1300000 -0.1775         NA  1.220
#8          NA -0.4300 -0.7266667     NA
#9  -0.1200000 -1.1900 -0.1900000     NA
#10 -0.6033333      NA -0.5100000  0.250

Answer 2

您可以使用acast包中的reshape2功能，它可以满足您的需求：

library(reshape2)
acast(ddf, vint1 ~ vfac1, fun.aggregate = mean, value.var = 'vnum1')

             1       2          3      4
1  -0.8500000 -1.6900        NaN    NaN
2         NaN -0.6650 -0.6000000    NaN
3  -0.4100000  0.6150 -2.0900000 -0.050
4  -0.4600000     NaN  0.1075000  0.825
5   0.1000000  0.8000  2.1800000    NaN
6  -0.2750000  0.8600  0.6600000  0.390
7  -0.1300000 -0.1775        NaN  1.220
8         NaN -0.4300 -0.7266667    NaN
9  -0.1200000 -1.1900 -0.1900000    NaN
10 -0.6033333     NaN -0.5100000  0.250

如何根据2因子和数据将数据帧转换为矩阵1个数字列

2 个答案: