1

这是对此问题的后续问题。

改写：

在之前的数据集的基础上，name现在对我的汇总统计数据很重要，因为有许多不同名称的动物。相反，我们仍然可以在该key_quality领域进行描述性统计。

您会看到生成的表格包含所有单独的统计数据，但我也希望看到所有幼犬身高的平均值。然后我也想看看所有哺乳动物婴儿的平均身高。我们如何添加这些统计数据？

animals_3 <- data.table(
    family = rep(c(1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2 , 2, 2, 2, 2,3 ,3 ,3), 2),
    animal = rep(c(1, 1, 1, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3, 3, 3, 4, 4, 4), 2),
    name = rep(c(1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6),2),
    key_quality = rep(c(rep("bold", 3), rep("smiles", 3), rep("sings", 3), rep("fast", 3), rep("sleepy", 3), rep("ticklish", 3)), 2),
    age = rep(c(1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3), 2),
    field = c(rep(1, 18), rep(2, 18)),
    value = c(
      c(25, 45, 75, 40, 65, 80, 10, 25, 50, 10, 15, 25, 18, 24, 40, 5, 15, 20),
      c(5, 15, 30, 7, 19, 40, 3, 9, 13, 2, 5, 9, 4, 7, 14, 1, 2, 3.5))
  )

animals_3 <- expss::apply_labels(
  animals_3,
  family = "|",
  family = c("mammal" = 1, "reptilia" = 2, "amphibia" = 3),
  animal = "|",
  animal = c("dog" = 1, "cat" = 2, "turtle" = 3, "frog" = 4),
  name = "|",
  name = c("fred" = 1, "billiy" = 2, "tod" = 3, "timmy" = 4, "ricardo" = 5, "jonno" = 6),
  key_quality = "|",
  age = "|",
  age = c("baby" = 1, "young" = 2, "mature" = 3),
  field = "|",
  field = c("height" = 1, "weight" = 2),
  value = "|"
)

expss::expss_output_viewer()

animals_3 %>% 
  expss::tab_rows(family %nest% animal %nest% name) %>% 
  # here we create separate column for name
  expss::tab_cols(total(label = "quality")) %>%
  expss::tab_cells(key_quality) %>%
  expss::tab_stat_fun(unique) %>%
  # end of creation
  expss::tab_cells(value) %>% 
  expss::tab_cols(age %nest%field) %>% 
  expss::tab_stat_sum(label = "") %>% 
  expss::tab_pivot(stat_position = "outside_column") %>% 
  expss::drop_empty_rows()

非常感谢！

4

1 回答 1

1

对于相同的嵌套变量，您需要不同的统计信息。对于这种情况，计算每个组的所有统计数据然后删除不必要的行和标签会更简单。这很容易，因为结果表只是一个普通的 data.frame。

library(expss)
animals_3 <- data.table(
    family = rep(c(1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2 , 2, 2, 2, 2,3 ,3 ,3), 2),
    animal = rep(c(1, 1, 1, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3, 3, 3, 4, 4, 4), 2),
    name = rep(c(1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6),2),
    key_quality = rep(c(rep("bold", 3), rep("smiles", 3), rep("sings", 3), rep("fast", 3), rep("sleepy", 3), rep("ticklish", 3)), 2),
    age = rep(c(1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3), 2),
    field = c(rep(1, 18), rep(2, 18)),
    value = c(
        c(25, 45, 75, 40, 65, 80, 10, 25, 50, 10, 15, 25, 18, 24, 40, 5, 15, 20),
        c(5, 15, 30, 7, 19, 40, 3, 9, 13, 2, 5, 9, 4, 7, 14, 1, 2, 3.5))
)

animals_3 <- expss::apply_labels(
    animals_3,
    family = "|",
    family = c("mammal" = 1, "reptilia" = 2, "amphibia" = 3),
    animal = "|",
    animal = c("dog" = 1, "cat" = 2, "turtle" = 3, "frog" = 4),
    name = "|",
    name = c("fred" = 1, "billiy" = 2, "tod" = 3, "timmy" = 4, "ricardo" = 5, "jonno" = 6),
    key_quality = "|",
    age = "|",
    age = c("baby" = 1, "young" = 2, "mature" = 3),
    field = "|",
    field = c("height" = 1, "weight" = 2),
    value = "|"
)

expss::expss_output_viewer()

animals_3 %>% 
    expss::tab_rows(family %nest% animal %nest% name) %>% 
    # here we create separate column for name
    expss::tab_cols(total(label = "quality")) %>%
    expss::tab_cells(key_quality) %>%
    # we name 'unique' as 'sum' to merge different statistics in one row
    expss::tab_stat_fun(sum = unique) %>%
    # end of creation
    expss::tab_rows(family %nest% list(total(), animal %nest% list(total(label = "|"), name))) %>% 
    expss::tab_cells(value) %>% 
    expss::tab_cols(age %nest%field) %>% 
    expss::tab_stat_fun(mean, sum) %>% 
    expss::tab_pivot(stat_position = "outside_column") %>% 
    expss::drop_empty_rows() %>% 
    where(

        (grepl("Total", row_labels) & grepl("mean", row_labels))  # to keep total and mean
        | (!grepl("Total", row_labels) & grepl("sum", row_labels)) # to drop mean with all other rows

    ) %>% 
    compute(row_labels = gsub("\\|(mean|sum|#Total)", "", row_labels)) %>% # remove labels 'sum', 'mean', '#Total'
    make_subheadings(1) # optional part

# |          |         |  quality |   baby |        |  young |        | mature |        |
# |          |         |          | height | weight | height | weight | height | weight |
# | -------- | ------- | -------- | ------ | ------ | ------ | ------ | ------ | ------ |
# |   mammal |         |          |     25 |      5 |   45.0 |   14.3 |   68.3 |   27.7 |
# |      dog |         |          |     65 |     12 |  110.0 |   34.0 |  155.0 |   70.0 |
# |          |    fred |     bold |     25 |      5 |   45.0 |   15.0 |   75.0 |   30.0 |
# |          |  billiy |   smiles |     40 |      7 |   65.0 |   19.0 |   80.0 |   40.0 |
# |      cat |         |          |     10 |      3 |   25.0 |    9.0 |   50.0 |   13.0 |
# |          |     tod |    sings |     10 |      3 |   25.0 |    9.0 |   50.0 |   13.0 |
# | reptilia |         |          |     14 |      3 |   19.5 |    6.0 |   32.5 |   11.5 |
# |   turtle |         |          |     28 |      6 |   39.0 |   12.0 |   65.0 |   23.0 |
# |          |   timmy |     fast |     10 |      2 |   15.0 |    5.0 |   25.0 |    9.0 |
# |          | ricardo |   sleepy |     18 |      4 |   24.0 |    7.0 |   40.0 |   14.0 |
# | amphibia |         |          |      5 |      1 |   15.0 |    2.0 |   20.0 |    3.5 |
# |     frog |         |          |      5 |      1 |   15.0 |    2.0 |   20.0 |    3.5 |
# |          |   jonno | ticklish |      5 |      1 |   15.0 |    2.0 |   20.0 |    3.5 |
于 2019-11-19T09:00:49.203 回答