当列中有NAS时

Question

我有一个纵向数据集，其中有两个人，其中数据行被编号为“情节”，有些情节具有测试“结果”。以下代码的目的是：

1. 创建二进制变量“ sup”以评估“结果”。如果结果== na，则sup == na。此代码有效。
2. 创建SUP_RANK以列举出现SUP == 1的人中的SUP == 1的发生。换句话说，我想知道这是否是第一次，第二次等。 问题：此代码当前不起作用，因为Person 2的第一个sup == 1被排名为'2'（当它被排名为'1'时）。
3. 创建一个事件变量，该变量：

• 等于1，如果sup_rank == 1
• 等于0，如果sup == 0 或 sup_rank不等于1
• 等于na，如果sup（和sup_rank）

当前我试图做＃＃ na等于na 3分在两个步骤中，比赛和事件决赛。 问题：它不起作用，因为'sup_rank'不起作用，但是无论如何，创建“事件”是一个变量（并且不需要'event_final'）是理想的选择。

#Load packages
pacman::p_load(dplyr)

#Create variables for data set 
person <- c(1, 1, 2, 2, 2, 2, 2, 2, 2, 2)
episode <- c(1, 2, 1, 2, 3, 4, 5, 6, 7, 8)
result <- c(NA, NA, NA, 1, NA, 2, NA, 2, NA, 2)

#Populate data frame with variables
d <- cbind(person, episode, result)
d <- as.data.frame(d)

#Manipulate data frame to create 4 new variables
d1 <- d %>%
  #Need to create new variables within each person
  group_by(person) %>%
  #Need to correctly order the rows of data before creating the variables
  arrange(person, episode) %>%
  #Create variable to evaluate 'result'
  mutate(sup = if_else(result == 2, 1, 0, NA_real_)) %>%
  #if sup == 1, rank it
  mutate(sup_rank = ifelse(sup == 1, rank(sup == 1, na.last = 'keep', ties.method = 'first'), NA_real_)) %>%
  #create an event if the rank of the sup == 1 is equal to 1 (we want the initial suppression)
  mutate(event = if_else(sup_rank == 1, 1, 0, NA_real_)) %>%
  #now override the value of event to be equal to 0 if sup==0
  mutate(event_final = if_else(sup == 0, 0, event)) %>%
  arrange(person, episode)

print(d1)
#> # A tibble: 10 x 7
#> # Groups:   person [2]
#>    person episode result   sup sup_rank event event_final
#>     <dbl>   <dbl>  <dbl> <dbl>    <dbl> <dbl>       <dbl>
#>  1      1       1     NA    NA       NA    NA          NA
#>  2      1       2     NA    NA       NA    NA          NA
#>  3      2       1     NA    NA       NA    NA          NA
#>  4      2       2      1     0       NA    NA           0
#>  5      2       3     NA    NA       NA    NA          NA
#>  6      2       4      2     1        2     0           0
#>  7      2       5     NA    NA       NA    NA          NA
#>  8      2       6      2     1        3     0           0
#>  9      2       7     NA    NA       NA    NA          NA
#> 10      2       8      2     1        4     0           0

^由

Answer 1

有一种更有效的方法可以肯定地做到这一点，但是与此同时，这是我创建的解决方案：

#Load packages
pacman::p_load(dplyr)

#Create variables for data set 
person <- c(1, 1, 2, 2, 2, 2, 2, 2, 2, 2)
episode <- c(1, 2, 1, 2, 3, 4, 5, 6, 7, 8)
result <- c(NA, NA, NA, 1, NA, 2, NA, 2, NA, 2)

#Populate data frame with variables
d <- cbind(person, episode, result)
d <- as.data.frame(d)

#Manipulate data frame to create 5 new variables
d1 <- d %>%
  #Need to create new variables within each person
  group_by(person) %>%
  #Need to correctly order the rows of data before creating the variables
  arrange(person, episode) %>%
  #Create variable to evaluate 'result'
  mutate(sup = if_else(result == 2, 1, 0, NA_real_)) %>%
  #Create a flag for each time sup==1
  mutate(sup_flag = if_else(sup == 1, 1, NA_real_, NA_real_)) %>%
  #if sup == 1, rank it
  mutate(sup_rank = ifelse(sup == 1, rank(sup_flag, na.last = 'keep', ties.method = 'first'), NA_real_)) %>%
  #create an event if the rank of the sup == 1 is equal to 1 (we want the initial suppression)
  mutate(event = if_else(sup_rank == 1, 1, 0, NA_real_)) %>%
  #now override the value of event to be equal to 0 if sup==0
  mutate(event_final = if_else(sup == 0, 0, event)) %>%
  arrange(person, episode)

print(d1)
#> # A tibble: 10 x 8
#> # Groups:   person [2]
#>    person episode result   sup sup_flag sup_rank event event_final
#>     <dbl>   <dbl>  <dbl> <dbl>    <dbl>    <dbl> <dbl>       <dbl>
#>  1      1       1     NA    NA       NA       NA    NA          NA
#>  2      1       2     NA    NA       NA       NA    NA          NA
#>  3      2       1     NA    NA       NA       NA    NA          NA
#>  4      2       2      1     0       NA       NA    NA           0
#>  5      2       3     NA    NA       NA       NA    NA          NA
#>  6      2       4      2     1        1        1     1           1
#>  7      2       5     NA    NA       NA       NA    NA          NA
#>  8      2       6      2     1        1        2     0           0
#>  9      2       7     NA    NA       NA       NA    NA          NA
#> 10      2       8      2     1        1        3     0           0

^{由 reprex软件包（v2.0.0）}