向列联表添加行

Question

我正在使用 R。我有以下三个数据集：

set.seed(123)

v1 <- c("2010-2011","2011-2012", "2012-2013", "2013-2014", "2014-2015") 
v2 <- c("A", "B", "C", "D", "E")
v3 <- c("Z", "Y", "X", "W" )

data_1 = data.frame(var_1 = rnorm(871, 10,10), var_2 = rnorm(871, 5,5))

data_1$dates <- as.factor(sample(v1, 871, replace=TRUE, prob=c(0.5, 0.2, 0.1, 0.1, 0.1)))

data_1$types <- as.factor(sample(v2, 871, replace=TRUE, prob=c(0.3, 0.2, 0.1, 0.1, 0.1)))

data_1$types2 <- as.factor(sample(v3, 871, replace=TRUE, prob=c(0.3, 0.5, 0.1, 0.1)))


data_2 = data.frame(var_1 = rnorm(412, 10,10), var_2 = rnorm(412, 5,5))

data_2$dates <- as.factor(sample(v1, 412, replace=TRUE, prob=c(0.5, 0.2, 0.1, 0.1, 0.1)))

data_2$types <- as.factor(sample(v2, 412, replace=TRUE, prob=c(0.3, 0.2, 0.1, 0.1, 0.1)))

data_2$types2 <- as.factor(sample(v3, 412, replace=TRUE, prob=c(0.3, 0.5, 0.1, 0.1)))

data_3 = data.frame(var_1 = rnorm(332, 10,10), var_2 = rnorm(332, 5,5))

data_3$dates <- as.factor(sample(v1, 332, replace=TRUE, prob=c(0.5, 0.2, 0.1, 0.1, 0.1)))

data_3$types <- as.factor(sample(v2, 332, replace=TRUE, prob=c(0.3, 0.2, 0.1, 0.1, 0.1)))

data_3$types2 <- as.factor(sample(v3, 332, replace=TRUE, prob=c(0.3, 0.5, 0.1, 0.1)))

我将这3个数据集结合起来，做了如下列联表：

data_1 <- data.frame(name="data_1", data_1)
data_2 <- data.frame(name="data_2", data_2)
data_3 <- data.frame(name="data_3", data_3)

problem_data <- rbind(data_1, data_2, data_3)


summary <- xtabs(~dates+name+types+types2, problem_data)
t = ftable(summary, row.vars=1, col.vars=2:4)

最后，使用“memisc”库，我能够使用“show_html()”函数“发布”这个表：

library(memisc) 
show_html(t)

在上表中，我想为每个垂直组合添加一行“总计”（例如 A,W , A,X, , A,Y, , A,Z, B,W, . ..)

我知道如何生成所有这些总计：

library(dplyr)


#column of totals

totals = problem_data %>% 
    group_by(name,  types, types2) %>% 
    summarise(totals = n())

`summarise()` has grouped output by 'name', 'types'. You can override using the `.groups` argument.
# A tibble: 60 x 4
# Groups:   name, types [15]
   name   types types2 totals
   <chr>  <fct> <fct>   <int>
 1 data_1 A     W          26
 2 data_1 A     X          29
 3 data_1 A     Y         172
 4 data_1 A     Z         104
 5 data_1 B     W          27
 6 data_1 B     X          20
 7 data_1 B     Y         111
 8 data_1 B     Z          48
 9 data_1 C     W          12
10 data_1 C     X          10
# ... with 50 more rows

这些也可以转置以使其更容易：

library(data.table)
 transpose(totals)
      V1     V2     V3     V4     V5     V6     V7     V8     V9    V10    V11    V12    V13    V14    V15    V16    V17    V18    V19    V20    V21    V22    V23    V24    V25    V26    V27
1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_1 data_2 data_2 data_2 data_2 data_2 data_2 data_2
2      A      A      A      A      B      B      B      B      C      C      C      C      D      D      D      D      E      E      E      E      A      A      A      A      B      B      B
3      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y
4     26     29    172    104     27     20    111     48     12     10     64     32     12     10     43     33     15      9     56     38     13     14     80     54      9     12     56

     V28    V29    V30    V31    V32    V33    V34    V35    V36    V37    V38    V39    V40    V41    V42    V43    V44    V45    V46    V47    V48    V49    V50    V51    V52    V53    V54
1 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_2 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3 data_3
2      B      C      C      C      C      D      D      D      D      E      E      E      E      A      A      A      A      B      B      B      B      C      C      C      C      D      D
3      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X      Y      Z      W      X
4     35      5      4     25     18      3      2     16     14      8      4     27     13      6     11     62     48      7     12     38     24      6      2     20      8 
 6      5
     V55    V56    V57    V58    V59    V60
1 data_3 data_3 data_3 data_3 data_3 data_3
2      D      D      E      E      E      E
3      Y      Z      W      X      Y      Z
4     19     14      7      3     27      7

但是有人可以告诉我如何将这些总数添加到前面列联表“t”的底行吗？有没有办法直接使用“xtabs”和“ftable”命令来做到这一点？

谢谢！

Answer 1

使用group_by 需要弄清楚变量出现的顺序。相反，我更愿意使用addmargins 函数。这会为数据添加边距。唯一的技巧是改变属性：

v <- attributes(t)
result <- addmargins(t, 1) #Adds the totals
v$row.vars[[1]] <- c(v$row.vars[[1]], 'Total')
v$dim <- dim(result)
attributes(result) <- v
memisc::show_html(result)

Answer 2

您可以通过rbind(your_ftable, total = ...) 进行操作。这将在your_ftable 的最后一行之后创建一个名为total 的行。例如，

summary <- xtabs(~dates+name+types+types2, problem_data)
t <- ftable(summary, row.vars=1, col.vars=2:4)
totals <- problem_data %>% group_by(name,  types, types2) %>% summarise(totals = n())
memisc::show_html(rbind(t, totals = totals$totals), varinfront = FALSE)

给予

延伸阅读：https://cran.r-project.org/web/packages/memisc/vignettes/ftable-matrix.html