根据 r 中列的值添加缺失值

add missed value based on the value of the column in r

这是我的示例数据集:

   vector1 <-
      data.frame(
        "name" = "a",
        "age" = 10,
        "fruit" = c("orange", "cherry", "apple"),
        "count" = c(1, 1, 1),
        "tag" = c(1, 1, 2)
      )
    vector2 <-
      data.frame(
        "name" = "b",
        "age" = 33,
        "fruit" = c("apple", "mango"),
        "count" = c(1, 1),
        "tag" = c(2, 2)
      )
    vector3 <-
      data.frame(
        "name" = "c",
        "age" = 58,
        "fruit" = c("cherry", "apple"),
        "count" = c(1, 1),
        "tag" = c(1, 1)
      )

    list <- list(vector1, vector2, vector3)
    print(list)

这是我的测试:

default <- c("cherry",
       "orange",
       "apple",
       "mango")

for (num in 1:length(list)) {
  #print(list[[num]])

  list[[num]] <- rbind(
    list[[num]],
    data.frame(
      "name" = list[[num]]$name,
      "age" = list[[num]]$age,
      "fruit" = setdiff(default, list[[num]]$fruit),#add missed value
      "count" = 0,
      "tag" = 1 #not found solutions
    )
  )

  print(paste0("--------------", num, "--------"))
  print(list)
}
#print(list)

我试图在数据框中找到哪个水果未命中,并且水果基于 tag.For 示例的值,在第一个数据框中,有标签 1 和 2.If 标签1的值没有苹果香蕉等默认水果,漏掉的默认水果会补0到数据中frame.The 期望格式如下:

[[1]]
  name age  fruit count tag
1    a  10 orange     1   1
2    a  10 cherry     1   1
3    a  10  apple     1   2
4    a  10  mango     0   1
5    a  10  apple     0   1
6    a  10  mango     0   2
7    a  10  orange    0   2
8    a  10  cherry    0   2

查看循环的过程,我也发现第一个循环加了3次芒果,没找到为什么一次加不了漏值的原因time.The总输出赞以下:

[[1]]
  name age  fruit count tag
1    a  10 orange     1   1
2    a  10 cherry     1   1
3    a  10  apple     1   2
4    a  10  mango     0   1
5    a  10  mango     0   1
6    a  10  mango     0   1

[[2]]
  name age  fruit count tag
1    b  33  apple     1   2
2    b  33  mango     1   2
3    b  33 cherry     0   1
4    b  33 orange     0   1

[[3]]
  name age  fruit count tag
1    c  58 cherry     1   1
2    c  58  apple     1   1
3    c  58 orange     0   1
4    c  58  mango     0   1

有没有人帮我,提供简单的方法或者其他方法?我应该使用sqldf函数添加0值吗?这是解决我问题的简单方法吗?

使用 and 的解决方案。我们可以使用 complete 来扩展数据框并指定填充值为 0 到 count.

请注意,我将您的列表名称从 list 更改为 fruit_list,因为在 R 中使用保留字来命名对象是一种不好的做法。另请注意,当我创建示例数据框时,我设置了 stringsAsFactors = FALSE 因为我不想创建因子列。最后,我使用 lapply 而不是 for-loop 来循环遍历列表元素。

library(dplyr)
library(tidyr)

fruit_list2 <- lapply(fruit_list, function(x){
  x2 <- x %>%
    complete(name, age, fruit = default, tag = c(1, 2), fill = list(count = 0)) %>%
    select(name, age, fruit, count, tag) %>%
    arrange(tag, fruit) %>%
    as.data.frame()
  return(x2)
})

fruit_list2
# [[1]]
#   name age  fruit count tag
# 1    a  10  apple     0   1
# 2    a  10 cherry     1   1
# 3    a  10  mango     0   1
# 4    a  10 orange     1   1
# 5    a  10  apple     1   2
# 6    a  10 cherry     0   2
# 7    a  10  mango     0   2
# 8    a  10 orange     0   2
# 
# [[2]]
#   name age  fruit count tag
# 1    b  33  apple     0   1
# 2    b  33 cherry     0   1
# 3    b  33  mango     0   1
# 4    b  33 orange     0   1
# 5    b  33  apple     1   2
# 6    b  33 cherry     0   2
# 7    b  33  mango     1   2
# 8    b  33 orange     0   2
# 
# [[3]]
#   name age  fruit count tag
# 1    c  58  apple     1   1
# 2    c  58 cherry     1   1
# 3    c  58  mango     0   1
# 4    c  58 orange     0   1
# 5    c  58  apple     0   2
# 6    c  58 cherry     0   2
# 7    c  58  mango     0   2
# 8    c  58 orange     0   2

数据

vector1 <-
  data.frame(
    "name" = "a",
    "age" = 10,
    "fruit" = c("orange", "cherry", "apple"),
    "count" = c(1, 1, 1),
    "tag" = c(1, 1, 2),
    stringsAsFactors = FALSE
  )
vector2 <-
  data.frame(
    "name" = "b",
    "age" = 33,
    "fruit" = c("apple", "mango"),
    "count" = c(1, 1),
    "tag" = c(2, 2),
    stringsAsFactors = FALSE
  )
vector3 <-
  data.frame(
    "name" = "c",
    "age" = 58,
    "fruit" = c("cherry", "apple"),
    "count" = c(1, 1),
    "tag" = c(1, 1),
    stringsAsFactors = FALSE
  )

fruit_list <- list(vector1, vector2, vector3)

default <- c("cherry", "orange", "apple", "mango")

考虑基础 R 方法——lapplyexpand.gridtransformrbindaggregate——它附加所有可能的 fruittag 选项到每个数据帧并保持最大计数。

new_list <- lapply(list, function(df) {
  fruit_tag_df <- transform(expand.grid(fruit=c("apple", "cherry", "mango", "orange"),
                                        tag=c(1,2)),
                            name = df$name[1],
                            age = df$age[1],
                            count = 0)

  aggregate(.~name + age + fruit + tag, rbind(df, fruit_tag_df), FUN=max)
})

输出

new_list

# [[1]]
#   name age  fruit tag count
# 1    a  10  apple   1     0
# 2    a  10 cherry   1     1
# 3    a  10 orange   1     1
# 4    a  10  mango   1     0
# 5    a  10  apple   2     1
# 6    a  10 cherry   2     0
# 7    a  10 orange   2     0
# 8    a  10  mango   2     0

# [[2]]
#   name age  fruit tag count
# 1    b  33  apple   1     0
# 2    b  33  mango   1     0
# 3    b  33 cherry   1     0
# 4    b  33 orange   1     0
# 5    b  33  apple   2     1
# 6    b  33  mango   2     1
# 7    b  33 cherry   2     0
# 8    b  33 orange   2     0

# [[3]]
#   name age  fruit tag count
# 1    c  58  apple   1     1
# 2    c  58 cherry   1     1
# 3    c  58  mango   1     0
# 4    c  58 orange   1     0
# 5    c  58  apple   2     0
# 6    c  58 cherry   2     0
# 7    c  58  mango   2     0
# 8    c  58 orange   2     0

OP 已要求完成 list 中的每个 data.frame,以便 default 水果和标签 1:2 的所有组合将出现在结果中 [=19] =] 应设置为 0 用于其他行。最后,每个 data.frame 应该至少包含 4 x 2 = 8 行。

我想提出两种不同的方法:

  1. 使用 lapply()CJ()cross join)函数从 data.table 到 return 列表。
  2. 使用 rbindlist()list 中的单独 data.frame 合并为 一个 大 data.table 并应用所需的转换整个data.table.

使用 lapply()CJ()

library(data.table)
lapply(lst, function(x) setDT(x)[
  CJ(name = name, age = age, fruit = default, tag = 1:2, unique = TRUE), 
  on = .(name, age, fruit, tag)][
    is.na(count), count := 0][order(-count, tag)]
)
[[1]]
   name age  fruit count tag
1:    a  10 cherry     1   1
2:    a  10 orange     1   1
3:    a  10  apple     1   2
4:    a  10  apple     0   1
5:    a  10  mango     0   1
6:    a  10 cherry     0   2
7:    a  10  mango     0   2
8:    a  10 orange     0   2

[[2]]
   name age  fruit count tag
1:    b  33  apple     1   2
2:    b  33  mango     1   2
3:    b  33  apple     0   1
4:    b  33 cherry     0   1
5:    b  33  mango     0   1
6:    b  33 orange     0   1
7:    b  33 cherry     0   2
8:    b  33 orange     0   2

[[3]]
   name age  fruit count tag
1:    c  58  apple     1   1
2:    c  58 cherry     1   1
3:    c  58  mango     0   1
4:    c  58 orange     0   1
5:    c  58  apple     0   2
6:    c  58 cherry     0   2
7:    c  58  mango     0   2
8:    c  58 orange     0   2

不需要按 counttag 排序,但有助于将结果与 OP 的预期输出进行比较。

在大 data.table

上创作

我们可以使用一个大的data.table,而不是具有相同结构的data.frame列表,其中每一行的来源可以通过id 列。

确实,OP 提出了其他问题(“使用 lapply 函数并在 r 中列出” where he asked for help in handling a list of data.frames. 已经建议将 rbind 行放在一起。

rbindlist() 函数具有 idcol 参数,用于标识每一行的来源:

library(data.table)
rbindlist(list, idcol = "df")
   df name age  fruit count tag
1:  1    a  10 orange     1   1
2:  1    a  10 cherry     1   1
3:  1    a  10  apple     1   2
4:  2    b  33  apple     1   2
5:  2    b  33  mango     1   2
6:  3    c  58 cherry     1   1
7:  3    c  58  apple     1   1

请注意,df 包含 list 中源 data.frame 的编号(如果命名了 list,则包含列表元素的名称)。

现在,我们可以通过对 df:

进行分组来应用上述解决方案
rbindlist(list, idcol = "df")[, .SD[
  CJ(name = name, age = age, fruit = default, tag = 1:2, unique = TRUE), 
  on = .(name, age, fruit, tag)], by = df][
    is.na(count), count := 0][order(df, -count, tag)]
    df name age  fruit count tag
 1:  1    a  10 cherry     1   1
 2:  1    a  10 orange     1   1
 3:  1    a  10  apple     1   2
 4:  1    a  10  apple     0   1
 5:  1    a  10  mango     0   1
 6:  1    a  10 cherry     0   2
 7:  1    a  10  mango     0   2
 8:  1    a  10 orange     0   2
 9:  2    b  33  apple     1   2
10:  2    b  33  mango     1   2
11:  2    b  33  apple     0   1
12:  2    b  33 cherry     0   1
13:  2    b  33  mango     0   1
14:  2    b  33 orange     0   1
15:  2    b  33 cherry     0   2
16:  2    b  33 orange     0   2
17:  3    c  58  apple     1   1
18:  3    c  58 cherry     1   1
19:  3    c  58  mango     0   1
20:  3    c  58 orange     0   1
21:  3    c  58  apple     0   2
22:  3    c  58 cherry     0   2
23:  3    c  58  mango     0   2
24:  3    c  58 orange     0   2
    df name age  fruit count tag