Question

我正在尝试仅使用mutate_at在某些列上应用函数。

这里的数据：

structure(list(LoB = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L), .Label = c("1", "2", "3", "4"), class = "factor"), 
AY = c(1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 
2003, 2004, 2005), R_0 = c(50135, 46530, 38295, 12033, 13332, 
35064, 15695, 41227, 88360, 29500, 30158, 47589), R_1 = c(76631, 
4908, 30427, 4268, 1994, 48426, 4585, 15578, 8112, 30945, 
8141, 11594), R_2 = c(28763, 2634, 374, 0, 216, 0, 555, 0, 
7161, 2192, 0, 772), R_3 = c(0, 1409, 470, 0, 203, 0, 0, 
0, 0, 1556, 0, 675), R_4 = c(16433, 0, 436, 0, 202, 2115, 
0, 0, 0, 1271, 0, 535), R_5 = c(6301, 0, 0, 0, 179, 0, 0, 
0, 183, 1052, 0, 0), R_6 = c(0, 0, 0, 0, 147, 0, 0, 0, 0, 
982, 0, 0), R_7 = c(0, 0, 0, 0, 135, 0, 0, 0, 0, 907, 2356, 
0), R_8 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 902, 0, 0), R_9 = c(0, 
0, 0, 0, 0, 0, 0, 0, 0, 833, 0, 0), R_10 = c(0, 0, 0, 0, 
0, 0, 0, 0, 0, 800, 0, 0), R_11 = c(0, 0, 0, 0, 0, 0, 0, 
0, 0, 684, 0, 0)), row.names = c(NA, -12L), class = c("grouped_df", 
"tbl_df", "tbl", "data.frame"), vars = "LoB", drop = TRUE, indices = list(
0:11), group_sizes = 12L, biggest_group_size = 12L, labels = structure(list(
LoB = structure(1L, .Label = c("1", "2", "3", "4"), class = "factor")), row.names = c(NA, 
-1L), class = "data.frame", vars = "LoB", drop = TRUE))

如下所示：

# A tibble: 12 x 14
# Groups:   LoB [1]
  LoB      AY   R_0   R_1   R_2   R_3   R_4   R_5   R_6   R_7   R_8   R_9  R_10  R_11
  <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1 1      1994 50135 76631 28763     0 16433  6301     0     0     0     0     0     0
 2 1      1995 46530  4908  2634  1409     0     0     0     0     0     0     0     0
 3 1      1996 38295 30427   374   470   436     0     0     0     0     0     0     0
 4 1      1997 12033  4268     0     0     0     0     0     0     0     0     0     0
 5 1      1998 13332  1994   216   203   202   179   147   135     0     0     0     0
 6 1      1999 35064 48426     0     0  2115     0     0     0     0     0     0     0
 7 1      2000 15695  4585   555     0     0     0     0     0     0     0     0     0
 8 1      2001 41227 15578     0     0     0     0     0     0     0     0     0     0
 9 1      2002 88360  8112  7161     0     0   183     0     0     0     0     0     0
10 1      2003 29500 30945  2192  1556  1271  1052   982   907   902   833   800   684
11 1      2004 30158  8141     0     0     0     0     0  2356     0     0     0     0
12 1      2005 47589 11594   772   675   535     0     0     0     0     0     0     0

假设我想创建一个以R_开头的列的累积和。为了做到这一点，我写道：

df %>% mutate_at(vars(contains("R_")), funs(cumsum))

这给了我以下输出：

# A tibble: 12 x 14
# Groups:   LoB [1]
   LoB      AY    R_0    R_1   R_2   R_3   R_4   R_5   R_6   R_7   R_8   R_9  R_10  R_11
   <fct> <dbl>  <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1 1      1994  50135  76631 28763     0 16433  6301     0     0     0     0     0     0
 2 1      1995  96665  81539 31397  1409 16433  6301     0     0     0     0     0     0
 3 1      1996 134960 111966 31771  1879 16869  6301     0     0     0     0     0     0
 4 1      1997 146993 116234 31771  1879 16869  6301     0     0     0     0     0     0
 5 1      1998 160325 118228 31987  2082 17071  6480   147   135     0     0     0     0
 6 1      1999 195389 166654 31987  2082 19186  6480   147   135     0     0     0     0
 7 1      2000 211084 171239 32542  2082 19186  6480   147   135     0     0     0     0
 8 1      2001 252311 186817 32542  2082 19186  6480   147   135     0     0     0     0
 9 1      2002 340671 194929 39703  2082 19186  6663   147   135     0     0     0     0
10 1      2003 370171 225874 41895  3638 20457  7715  1129  1042   902   833   800   684
11 1      2004 400329 234015 41895  3638 20457  7715  1129  3398   902   833   800   684
12 1      2005 447918 245609 42667  4313 20992  7715  1129  3398   902   833   800   684

这里的问题是累积和是垂直（按变量）而不是水平进行的。如何在dplyr中实现？

Answer 1

我不确定没有使用gather和spread的方法。这就是我要做的。首先，我将数据重塑为“长”，然后我们需要使用group_by，以便只计算原始cumsum中每一行的data.frame（如果没有足够的分组，我们可以向数据添加row_number，然后group_by）。之后，我们先mutate，然后再spread，使数据恢复为“宽”。最后，我们按照@Gregor的建议添加select(names(df))，以保留原始列顺序。

df %>%
    gather(variable, value, contains('R_')) %>% # reshape wide to long
    group_by(LoB, AY) %>% # group by for each row in original data
    mutate(value = cumsum(value)) %>% # calculate cumsum
    spread(variable, value) %>% # reshape back from long to wide
    select(names(df)) # added to retain original column order

#   LoB      AY   R_0    R_1    R_2    R_3 ...
#   <fct> <dbl> <dbl>  <dbl>  <dbl>  <dbl> ... 
# 1 1      1994 50135 126766 155529 155529 ...
# 2 1      1995 46530  51438  54072  55481 ...
# 3 1      1996 38295  68722  69096  69566 ... 
# 4 1      1997 12033  16301  16301  16301 ...

Answer 2

与弹力球类似的答案，但它会保持列顺序并使用通用ID，以防万一（LoB，AY）不是主键：

df %>% 
  mutate(id = 1:n()) %>% 
  gather(old_name, value, starts_with("R_")) %>% 
  arrange(id, nchar(old_name), old_name) %>% 
  group_by(id) %>% 
  mutate(value = cumsum(value)) %>% 
  ungroup() %>% 
  select(-id) %>% 
  spread(old_name, value) %>% 
  select(names(df)) %>% 
  select(AY, everything())

Answer 3

按行运算通常在矩阵上效果更好。为了避免fieldName = media的麻烦，我将提取gather/spread列，使用R_（隐式转换为矩阵），然后将结果分配回原始数据：

也就是说，数据似乎不太整洁。您最好将apply设为长格式并保持长格式。

gather

mutate_at水平与垂直

3 个答案: