Блог

Мне нужно создать новую переменную ( obs.new ), которая сохраняет исходное значение, за obs исключением случаев, когда date отсутствует минимум. В этих случаях obs.new значение должно быть mean.obs значением. Другие экземпляры, где obs есть na , должны остаться na .

Это воспроизводимый пример того, что я сделал:

 library(dplyr)

data.1 <-read.csv(text = "
site ,treat,date,obs,mean.obs,
1,a,33,0.585581765,0.4,
1,a,34,0.871886986,0.4,
1,a,35,,0.4,
1,a,36,,0.4,
1,a,37,,0.4,
1,a,38,,0.4,
1,a,39,0.628236902,0.4,
1,a,40,0.041956742,0.4,
1,b,36,,0.52,
1,b,37,0.327067686,0.52,
1,b,38,,0.52,
1,b,39,,0.52,
1,b,40,,0.52,
1,b,41,0.982637394,0.52,
1,b,42,0.80141212,0.52,
1,b,43,0.739522519,0.52,
2,a,56,,0.48,
2,a,57,0.724849037,0.48,
2,a,58,0.050617254,0.48,
2,a,59,,0.48,
2,a,60,,0.48,
2,a,61,,0.48,
2,a,62,,0.48,
2,a,63,0.269993451,0.48,
2,b,23,0.216291392,0.49,
2,b,24,,0.49,
2,b,25,,0.49,
2,b,26,,0.49,
2,b,27,,0.49,
2,b,28,,0.49,
2,b,29,0.951644067,0.49,
2,b,30,0.745131113,0.49")


data.1.1 <- data.1 %>%
  group(site, treat) %>%
  mutate(obs.new = if_else(is.na(slice(which.min(date))),
                           mean.obs, obs))
 

Это ошибка, которую я получил:

 Error: Problem with `mutate()` input `obs.new`.
x no applicable method for 'slice' applied to an object of class "c('integer', 'numeric')"
i Input `obs.new` is `if_else(is.na(slice(which.min(date))), mean.obs, obs)`.
i The error occurred in group 1: site = 1, treat = "a".
Run `rlang::last_error()` to see where the error occurred.
 

Ожидаемый результат таков:

Спасибо за любую подсказку.

Вы могли бы заменить obs значение, если obs NA оно равно и date является минимальной датой в группе.

 library(dplyr)

data.1 %>%
  group_by(site, treat) %>%
  mutate(mean.obs.new = ifelse(is.na(obs) amp; date == min(date), mean.obs, obs))

#    site treat  date     obs mean.obs mean.obs.new
#   <int> <chr> <int>   <dbl>    <dbl>        <dbl>
# 1     1 a        33  0.586      0.4        0.586 
# 2     1 a        34  0.872      0.4        0.872 
# 3     1 a        35 NA          0.4       NA     
# 4     1 a        36 NA          0.4       NA     
# 5     1 a        37 NA          0.4       NA     
# 6     1 a        38 NA          0.4       NA     
# 7     1 a        39  0.628      0.4        0.628 
# 8     1 a        40  0.0420     0.4        0.0420
# 9     1 b        36 NA          0.52       0.52  
#10     1 b        37  0.327      0.52       0.327 
# … with 22 more rows

 

 data.1 %>%
  group_by(site, treat) %>%
  mutate(obs.new = if_else(!is.na(obs), 
                           obs,
                           if_else(date == min(date), 
                                   mean.obs,
                                   0)
                           )
         )
 

 data.1 %>%
    group_by(site, treat) %>%
    mutate(obs.new = coalesce(obs, 
        if_else(row_number() == 1, mean.obs, NA_real_))) %>%
    ungroup()

# A tibble: 32 x 7
    site treat  date     obs mean.obs X     obs.new
   <int> <chr> <int>   <dbl>    <dbl> <lgl>   <dbl>
 1     1 a        33  0.586      0.4  NA     0.586 
 2     1 a        34  0.872      0.4  NA     0.872 
 3     1 a        35 NA          0.4  NA    NA     
 4     1 a        36 NA          0.4  NA    NA     
 5     1 a        37 NA          0.4  NA    NA     
 6     1 a        38 NA          0.4  NA    NA     
 7     1 a        39  0.628      0.4  NA     0.628 
 8     1 a        40  0.0420     0.4  NA     0.0420
 9     1 b        36 NA          0.52 NA     0.52  
10     1 b        37  0.327      0.52 NA     0.327 
# … with 22 more rows
 

измените group на group_by, затем вы можете использовать case_when()

 library(dplyr)
data.1 %>%
  group_by(site, treat) %>%
  mutate(obs.new = case_when(!is.na(obs) ~ obs,
                             date==min(date) ~ mean.obs,
                             TRUE ~ 0))
 

Используя data.table

 library(data.table)
setDT(data.1)[, mean.obs.new := fifelse(is.na(obs) amp; date == min(date), mean.obs, obs), .(site, treat)]