如何在R中使用dplyr进行条件选择?

为了提高效率,我当然更喜欢@andreelrico'的答案,但这里有一个 dplyr 选项。尝试:

df <- data.frame(ID = c(1, 2, 2, 3, 3, 4),
                 type = c("MC", "MC", "MK", "MC", "MK", "MC"),
                 value1 = c(512, 261, 4523, 1004, 1221, 2556),
                 value2 = c(726, 4000, 280, 998, 113, 6789)) 
library(dplyr)
df %>%
  reshape(., idvar = "ID", timevar = "type", direction = "wide") %>%
  group_by(ID) %>%
  mutate(value1 = ifelse(is.na(value1.MK), value1.MC, value1.MK),
         value2 = ifelse(is.na(value2.MC), value2.MK, value2.MC),
         type = "MC") %>%
  select(ID, type, value1, value2)
# output
# A tibble: 4 x 4
# Groups:   ID [4]
     ID  type value1 value2
  <dbl> <chr>  <dbl>  <dbl>
1     1    MC    512    726
2     2    MC   4523   4000
3     3    MC   1221    998
4     4    MC   2556   6789

dplyr

library(dplyr)

df %>%
  group_by(ID) %>%
  mutate(value1 = ifelse(any(type == "MK"), value1[type=="MK"],value1[type=="MC"]), 
         value2 = value2[type == "MC"]) %>%
  filter(type == "MC")

#     ID type  value1 value2
#  <dbl> <fct>  <dbl>  <dbl>
#1     1 MC       512    726
#2     2 MC      4523   4000
#3     3 MC      1221    998
#4     4 MC      2556   6789

value1 我们检查“MK”中的值,如果它存在,或者取相应的“MC”值 value2 默认情况下,我们取“MC”值并只保留带有 type ID )会有一个“MC” 类型 行。

data.table 解决方案

setDT(df1)[,{x=.SD;if(all(c("MC","MK") %in% type)){x$value1[] = last(value1)};first(x)},by=ID]

结果:

#  ID type value1 value2
#1  1   MC    512    726
#2  2   MC   4523   4000
#3  3   MC   1221    998
#4  4   MC   2556   6789

dplyr

df1 %>% group_by(ID) %>% do(.,(function(x){if(all(c("MC","MK") %in% x$type)){x$value1[] = x$value1[x$type=="MK"]};x[1,]})(.))

# A tibble: 4 x 4
# Groups:   ID [4]
#     ID type  value1 value2
#  <dbl> <fct>  <dbl>  <dbl>
#1     1 MC       512    726
#2     2 MC      4523   4000
#3     3 MC      1221    998
#4     4 MC      2556   6789