Question

data=data.frame("student"=c(1,1,1,1,2,2,2,3,3,3,3,4,4,4,4),
"year"=c(2014,2015,2016,2017,2014,2015,2016,2014,2015,2016,2017,2014,2015,2016,2017),
"grade"=c(9,10,11,12,9,10,11,9,10,11,12,9,10,11,12),
"scoreA"=c(0,0,0,0,0,0,2,0,1,1,2,0,0,1,1),
"scoreB"=c(0,0,0,0,0,0,2,0,0,1,2,0,0,0,1),
"WANTgradeA"=c(12,12,12,12,11,11,11,10,10,10,10,11,11,11,11),
"WANTscoreA"=c(0,0,0,0,2,2,2,1,1,1,1,1,1,1,1),
"WANTgradeB"=c(12,12,12,12,11,11,11,11,11,11,11,12,12,12,12),
"WANTscoreB"=c(0,0,0,0,2,2,2,1,1,1,1,1,1,1,1))

这是我的数据。我的预期输出是所有以“ WANT”开头的变量

当scoreA等于0且
如果scoreA从未超过0，则WANTgradeA等于GRADE的最大值 WANTscoreA等于scoreA的最大值。
当scoreB大于0并且
如果scoreB从未超过0，则WANTgradeB等于GRADE的最大值和WANTscoreB等于scoreB的最大值

我的尝试未能添加这4个新变量，而是砍掉了数据

data %>% 
    group_by(student) %>%
    filter(value == max(score > 0))

Answer 1

这是一个dplyr解决方案-

df %>% 
  group_by(student) %>% 
  mutate(
    wgradeA = case_when(
      any(scoreA > 0) ~ grade[scoreA > 0][1],
      TRUE ~ max(grade)
    ),
    wscoreA = scoreA[match(TRUE, scoreA > 0, nomatch = 1)],
    wgradeB = case_when(
      any(scoreB > 0) ~ grade[scoreB > 0][1],
      TRUE ~ max(grade)
    ),
    wscoreB = scoreB[match(TRUE, scoreB > 0, nomatch = 1)]
  ) %>% 
  ungroup()

# A tibble: 15 x 13
   student  year grade scoreA scoreB WANTgradeA WANTscoreA WANTgradeB WANTscoreB wgradeA wscoreA wgradeB wscoreB
     <dbl> <dbl> <dbl>  <dbl>  <dbl>      <dbl>      <dbl>      <dbl>      <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
 1       1  2014     9      0      0         12          0         12          0      12       0      12       0
 2       1  2015    10      0      0         12          0         12          0      12       0      12       0
 3       1  2016    11      0      0         12          0         12          0      12       0      12       0
 4       1  2017    12      0      0         12          0         12          0      12       0      12       0
 5       2  2014     9      0      0         11          2         11          2      11       2      11       2
 6       2  2015    10      0      0         11          2         11          2      11       2      11       2
 7       2  2016    11      2      2         11          2         11          2      11       2      11       2
 8       3  2014     9      0      0         10          1         11          1      10       1      11       1
 9       3  2015    10      1      0         10          1         11          1      10       1      11       1
10       3  2016    11      1      1         10          1         11          1      10       1      11       1
11       3  2017    12      2      2         10          1         11          1      10       1      11       1
12       4  2014     9      0      0         11          1         12          1      11       1      12       1
13       4  2015    10      0      0         11          1         12          1      11       1      12       1
14       4  2016    11      1      0         11          1         12          1      11       1      12       1
15       4  2017    12      1      1         11          1         12          1      11       1      12       1

dplyr slice新变量

1 个答案: