我相信这就是您正在寻找的。它为您提供所需的输出。请注意,当您在 df 中定义 time 列时,您的原始问题中有一个错字,其中您有 32 而不是 42。我说这是一个错字,因为它与您在df 定义下方的输出不匹配。我在下面的代码中将 32 更改为 42。
library(dplyr)
df <- data.frame(id = c(rep(1,7),rep(2,5)), event = c("a","b","b","b","a","b","a","a","a","b","a","a"), time = c(1,3,6,12,24,30,42,1,2,6,17,24))
seq <- c("a", "b", "a")
time_LB <- c(0, 2, 12)
time_UB <- c(Inf, 8, 18)
df %>%
full_join(df,by='id',suffix=c('1','2')) %>%
full_join(df,by='id') %>%
rename(event3 = event, time3 = time) %>%
filter(event1 == seq[1] & event2 == seq[2] & event3 == seq[3]) %>%
filter(time1 %>% between(time_LB[1],time_UB[1])) %>%
filter((time2-time1) %>% between(time_LB[2],time_UB[2])) %>%
filter((time3-time2) %>% between(time_LB[3],time_UB[3])) %>%
group_by(id,time1) %>%
slice(1) %>% # slice 1 row for each unique id and time1 (so no duplicate time1s)
group_by(id) %>%
count()
这是输出:
# A tibble: 2 x 2
id n
<dbl> <int>
1 1 2
2 2 2
此外,如果您省略 dplyr 管道的最后 2 部分进行计数(以查看它匹配的序列),您将获得以下序列:
Source: local data frame [4 x 7]
Groups: id, time1 [4]
id event1 time1 event2 time2 event3 time3
<dbl> <fctr> <dbl> <fctr> <dbl> <fctr> <dbl>
1 1 a 1 b 6 a 24
2 1 a 24 b 30 a 42
3 2 a 1 b 6 a 24
4 2 a 2 b 6 a 24
编辑以回应关于泛化此的评论: 是的,可以将其泛化为任意长度的序列,但需要一些 R 巫术。最值得注意的是,请注意Reduce 的使用,它允许您在对象列表以及foreach 上应用通用函数,我从foreach 包中借用它来执行一些任意循环。代码如下:
library(dplyr)
library(foreach)
df <- data.frame(id = c(rep(1,7),rep(2,5)), event = c("a","b","b","b","a","b","a","a","a","b","a","a"), time = c(1,3,6,12,24,30,42,1,2,6,17,24))
seq <- c("a", "b", "a")
time_LB <- c(0, 2, 12)
time_UB <- c(Inf, 8, 18)
multi_full_join = function(df1,df2) {full_join(df1,df2,by='id')}
df_list = foreach(i=1:length(seq)) %do% {df}
df2 = Reduce(multi_full_join,df_list)
names(df2)[grep('event',names(df2))] = paste0('event',seq_along(seq))
names(df2)[grep('time',names(df2))] = paste0('time',seq_along(seq))
df2 = df2 %>% mutate_if(is.factor,as.character)
df2 = df2 %>%
mutate(seq_string = Reduce(paste0,df2 %>% select(grep('event',names(df2))) %>% as.list)) %>%
filter(seq_string == paste0(seq,collapse=''))
time_diff = df2 %>% select(grep('time',names(df2))) %>%
t %>%
as.data.frame() %>%
lapply(diff) %>%
unlist %>% matrix(ncol=2,byrow=TRUE) %>%
as.data.frame
foreach(i=seq_along(time_diff),.combine=data.frame) %do%
{
time_diff[[i]] %>% between(time_LB[i+1],time_UB[i+1])
} %>%
Reduce(`&`,.) %>%
which %>%
slice(df2,.) %>%
filter(time1 %>% between(time_LB[1],time_UB[1])) %>% # deal with time1 bounds, which we skipped over earlier
group_by(id,time1) %>%
slice(1) # slice 1 row for each unique id and time1 (so no duplicate time1s)
这会输出以下内容:
Source: local data frame [4 x 8]
Groups: id, time1 [4]
id event1 time1 event2 time2 event3 time3 seq_string
<dbl> <chr> <dbl> <chr> <dbl> <chr> <dbl> <chr>
1 1 a 1 b 6 a 24 aba
2 1 a 24 b 30 a 42 aba
3 2 a 1 b 6 a 24 aba
4 2 a 2 b 6 a 24 aba
如果你只想要计数,你可以group_by(id) 然后count() 就像在原始代码 sn-p 中一样。