R 基于变量运行和其他变量的附加条件定义序列

在上面的数据中，我需要定义一个列，该列将包含

group

列的运行长度类型id（如

data.table:：rleid

生成，但忽略

NA

）。正如您所看到的，我们还有列

seq_break

，它应该结束一个序列。通常是这样的，比如当

group=NA

然后

seq\u break=TRUE

。但有时

seq_break=TRUE

且组为

A

或

B

——则应结束序列并启动新序列，即使下一行指的是同一组。因此，例如，对于行

25:26

，我们应该有两个不同的序列id，即使这两个事件都指向组

B

。通常，预期输出如下所示：

structure(list(group = c(NA, "A", "B", NA, "B", "B", "B", "B", 
"B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", 
"B", NA, NA, "B", "B", "A", "A", NA, NA, "B", "B", "B", NA, "A", 
"A", "A", "A", "A", "A", "A", "A", "A", "A", NA, NA, "B", "B", 
NA, "A"), seq_break = c(TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, 
TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, FALSE, TRUE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, FALSE)), .Names = c("group", 
"seq_break"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-50L))

---

如何使用

tidyverse

？使用

tidyverse

和

data.table

的解决方案。假设

dt1

是示例数据帧，

dt3

是最终输出。请注意，我认为在预期的输出中，第47到48行应该是9，第50行应该是10。我不知道为什么在您的预期输出中，第47到48行是11，第50行是12

structure(list(group = c(NA, "A", "B", NA, "B", "B", "B", "B", 
"B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", 
"B", NA, NA, "B", "B", "A", "A", NA, NA, "B", "B", "B", NA, "A", 
"A", "A", "A", "A", "A", "A", "A", "A", "A", NA, NA, "B", "B", 
NA, "A"), seq_break = c(TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, 
TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, FALSE, TRUE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, FALSE), expected_output = c(NA, 
1, 2, NA, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 
3, NA, NA, 4, 5, 6, 6, NA, NA, 7, 7, 7, NA, 8, 8, 8, 8, 8, 8, 
8, 8, 8, 8, NA, NA, 11, 11, NA, 12)), .Names = c("group", "seq_break", 
"expected_output"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-50L))

库（tidyverse）
库（数据表）
dt2%rowid_到_列（）
dt3%
突变（ID=rleid（组，序列中断））%>%
分组依据（分组，顺序中断，ID）%>%
过滤器（！（is.na（组）&序列中断和行编号（）>1））%>%
解组（）%>%
突变（ID2=cumsum（seq_break））%>%
下降(组别)%>%
突变（预期的_输出=rleid（组，ID2））%>%
选择（rowid，预期的_输出）%>%
左联合（dt2，by=“rowid”）%>%
选择（-rowid）
dt3
##tibble:50 x 3
#组顺序\u中断预期\u输出
#                    
#1不适用真不适用
#2 A错误1
#3 B错误2
#4不适用真不适用
#5 B错误3
#6 B错误3
#7 B错误3
#8 B错误3
#9 B错误3
#10 B错误3
# # ... 还有40行

library(tidyverse)
library(data.table)

dt2 <- dt1 %>% rowid_to_column() 

dt3 <- dt2 %>%
  mutate(ID = rleid(group, seq_break)) %>%
  group_by(group, seq_break, ID) %>%
  filter(!(is.na(group) & seq_break & row_number() > 1)) %>%
  ungroup() %>%
  mutate(ID2 = cumsum(seq_break)) %>%
  drop_na(group) %>%
  mutate(expected_output = rleid(group, ID2)) %>%
  select(rowid, expected_output) %>%
  left_join(dt2, ., by = "rowid") %>%
  select(-rowid)

dt3
# # A tibble: 50 x 3
#    group seq_break expected_output
#    <chr> <lgl>               <int>
#  1 NA    TRUE                   NA
#  2 A     FALSE                   1
#  3 B     FALSE                   2
#  4 NA    TRUE                   NA
#  5 B     FALSE                   3
#  6 B     FALSE                   3
#  7 B     FALSE                   3
#  8 B     FALSE                   3
#  9 B     FALSE                   3
# 10 B     FALSE                   3
# # ... with 40 more rows