如何按条件删除行

Question

I'm trying to delete rows for which the condition is not satisfying eg.Remove that Subject row which do not have all period's value following is the dataframe

Subject          Period
1                  1
1                  2
1                  3
2                  1
2                  2
2                  3
3                  1
3                  2
4                  1
4                  2
4                  3


Subject          Period
1                  1
1                  2
1                  3
2                  1
2                  2
2                  3
4                  1
4                  2
4                  3

Answer 1

A dplyr solution.

library(dplyr)
dat %>% 
  group_by(Subject) %>%
  filter(all(unique(dat$Period) %in% Period)) %>%
  ungroup()
# # A tibble: 9 x 2
#   Subject Period
#     <int>  <int>
# 1       1      1
# 2       1      2
# 3       1      3
# 4       2      1
# 5       2      2
# 6       2      3
# 7       4      1
# 8       4      2
# 9       4      3

A base R solution.

dat_list <- split(dat, f = dat$Subject) 
keep_vec <- sapply(dat_list, function(x) all(unique(dat$Period) %in% x$Period))
dat_keep <- dat_list[keep_vec]

dat2 <- do.call(rbind, dat_keep)
dat2
#      Subject Period
# 1.1        1      1
# 1.2        1      2
# 1.3        1      3
# 2.4        2      1
# 2.5        2      2
# 2.6        2      3
# 4.9        4      1
# 4.10       4      2
# 4.11       4      3

A solution using purrr and dplyr .

library(purrr)
library(dplyr)

dat2 <- dat %>%
  split(f = .$Subject) %>%
  keep(~all(unique(dat$Period) %in% .x$Period)) %>%
  bind_rows()
dat2
#   Subject Period
# 1       1      1
# 2       1      2
# 3       1      3
# 4       2      1
# 5       2      2
# 6       2      3
# 7       4      1
# 8       4      2
# 9       4      3

DATA

dat <- read.table(text = "Subject          Period
1                  1
                  1                  2
                  1                  3
                  2                  1
                  2                  2
                  2                  3
                  3                  1
                  3                  2
                  4                  1
                  4                  2
                  4                  3",
                  header = TRUE)

Answer 2

考虑ave用于内联聚合然后相应的subset ：

sub_df <- subset(df, ave(Period, Subject, FUN=max) != 3)