如果缺少观察值，则在数据框中添加行[重复]

Question

我有一个 df1，每 人 (id) 有多个问卷（测量），这些问卷在特定时间点（日期）得到回答.通常，每个人都应每次会话填写三份调查问卷（第一、前、后）。一些参与者未能填写所有三份问卷。他们可能只回答三个中的一两个。因此，可能的模式可能是完整的（参与者 A）、缺少“post”（参与者 B）、缺少“first”（参与者 C）、缺少“pre”（参与者 D），或者只回答了三个中的一个（参与者E、F、G)。

见df1：

df1 <- structure(list(id = structure(c(1L, 1L, 1L, 2L, 2L, 3L, 3L, 4L,  4L, 5L, 6L, 7L), .Label = c("A", "B", "C", "D", "E", "F", "G"), class = "factor"), measure = structure(c(1L, 3L, 2L, 1L, 3L, 3L, 2L, 1L, 2L, 1L, 3L, 2L), .Label = c("first", "post", "pre"), class = "factor"), date = structure(c(17558, 17558, 17558,  17558, 17559, 17559, 17559, 17559, 17558, 17558, 17558, 17558 ), class = "Date"), result = c(1, 5, 4, 7, 8, 7, 2, 1, 3, 5, 7, 7)), class = "data.frame", row.names = c(NA, -12L))

现在，我想在数据集中添加缺失的行，其中包含 id 和 measure 以及缺失日期和结果的“NA”。最终的 df 应该看起来像 df2。

df2 <- structure(list(id = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L), .Label = c("A", "B", "C", "D", "E", "F", "G"), class = "factor"), measure = structure(c(1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L), .Label = c("first", "post", "pre"), class = "factor"), date = structure(c(17558, 17558, 17558, 17558, 17559, NA, NA, 17559, 17559, 17559, NA, 17558, 17558, NA, NA, NA, 17558, NA, NA, NA, 17558), class = "Date"), result = c(1, 5, 4, 7, 8, NA, NA, 7, 2, 1, NA, 3, 5, NA, NA, NA, 7, NA, NA, NA, 7)), class = "data.frame", row.names = c(NA, -21L))

我尝试将可能丢失的组合分组并插入一行。但这并没有带来预期的结果。

require (tidyverse)
final <- df1 %>%
group_by(id, measure == "first" & lag(measure, 1, default=NA) == "post") %>%
do(add_row(., measure = "pre", .after = 0)) %>%
ungroup()

我也试过了

final <- df1 %>% complete(id, nesting(measure, date))

也许更复杂的是，参与者可以参加多个会议。因此，有可能每个 id 都有 x * (first, post, pre)。

Answer 1

只需由complete(df1, id, measure) 完成即可。试试这个：

library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
library(tidyr)

df1 <- structure(list(
  id = structure(c(1L, 1L, 1L, 2L, 2L, 3L, 3L, 4L,  4L, 5L, 6L, 7L), 
                 .Label = c("A", "B", "C", "D", "E", "F", "G"), 
                 class = "factor"), 
  measure = structure(c(1L, 3L, 2L, 1L, 3L, 3L, 2L, 1L, 2L, 1L, 3L, 2L), 
                      .Label = c("first", "post", "pre"), 
                      class = "factor"), 
  date = structure(c(17558, 17558, 17558,  17558, 17559, 17559, 17559, 17559, 17558, 17558, 17558, 17558 ), class = "Date"), 
  result = c(1, 5, 4, 7, 8, 7, 2, 1, 3, 5, 7, 7)), class = "data.frame", row.names = c(NA, -12L))

df2 <- structure(list(id = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L), .Label = c("A", "B", "C", "D", "E", "F", "G"), class = "factor"), measure = structure(c(1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L), .Label = c("first", "post", "pre"), class = "factor"), date = structure(c(17558, 17558, 17558, 17558, 17559, NA, NA, 17559, 17559, 17559, NA, 17558, 17558, NA, NA, NA, 17558, NA, NA, NA, 17558), class = "Date"), result = c(1, 5, 4, 7, 8, NA, NA, 7, 2, 1, NA, 3, 5, NA, NA, NA, 7, NA, NA, NA, 7)), class = "data.frame", row.names = c(NA, -21L))

# Result with complete(df1, id, measure) and setting order of measure
complete(df1, id, measure) %>% 
  mutate(measure = factor(measure, levels = c("first", "pre", "post"))) %>% 
  arrange(id, measure, date) %>% 
  as.data.frame()
#>    id measure       date result
#> 1   A   first 2018-01-27      1
#> 2   A     pre 2018-01-27      5
#> 3   A    post 2018-01-27      4
#> 4   B   first 2018-01-27      7
#> 5   B     pre 2018-01-28      8
#> 6   B    post       <NA>     NA
#> 7   C   first       <NA>     NA
#> 8   C     pre 2018-01-28      7
#> 9   C    post 2018-01-28      2
#> 10  D   first 2018-01-28      1
#> 11  D     pre       <NA>     NA
#> 12  D    post 2018-01-27      3
#> 13  E   first 2018-01-27      5
#> 14  E     pre       <NA>     NA
#> 15  E    post       <NA>     NA
#> 16  F   first       <NA>     NA
#> 17  F     pre 2018-01-27      7
#> 18  F    post       <NA>     NA
#> 19  G   first       <NA>     NA
#> 20  G     pre       <NA>     NA
#> 21  G    post 2018-01-27      7

# Desired output
df2 %>% 
  mutate(measure = factor(measure, levels = c("first", "pre", "post"))) %>% 
  arrange(id, measure, date)
#>    id measure       date result
#> 1   A   first 2018-01-27      1
#> 2   A     pre 2018-01-27      5
#> 3   A    post 2018-01-27      4
#> 4   B   first 2018-01-27      7
#> 5   B     pre 2018-01-28      8
#> 6   B    post       <NA>     NA
#> 7   C   first       <NA>     NA
#> 8   C     pre 2018-01-28      7
#> 9   C    post 2018-01-28      2
#> 10  D   first 2018-01-28      1
#> 11  D     pre       <NA>     NA
#> 12  D    post 2018-01-27      3
#> 13  E   first 2018-01-27      5
#> 14  E     pre       <NA>     NA
#> 15  E    post       <NA>     NA
#> 16  F   first       <NA>     NA
#> 17  F     pre 2018-01-27      7
#> 18  F    post       <NA>     NA
#> 19  G   first       <NA>     NA
#> 20  G     pre       <NA>     NA
#> 21  G    post 2018-01-27      7

^{由reprex package (v0.3.0) 于 2020 年 3 月 9 日创建}