在dplyr中使用filter（）查找grepl值的第一个匹配项，并返回该值和所有后续行

我正在尝试使用dplyr按组过滤数据帧，其中捕获行中第一次出现的字符串“ReadingOnset”，并将其和所有后续行传递到新的数据帧中

Text_Stimuli <- structure(list(Name = c("Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", 
"Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1", "Sub1"
), StimulusName = c("GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", "GenLie20", 
"GenLie20"), StimuliBlock = c("Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4", "Block_4", "Block_4", "Block_4", "Block_4", 
"Block_4", "Block_4"), Reading_Onset = c("", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "ReadingOnset", "", "", "", "", 
"", "", "")), row.names = c(NA, -101L), vars = c("Name", "StimulusName", 
"StimuliBlock"), drop = TRUE, indices = list(0:100), group_sizes = 101L, biggest_group_size = 101L, labels = structure(list(
    Name = "Innocent Subject 15", StimulusName = "GenLie20", 
    StimuliBlock = "Block_4"), row.names = c(NA, -1L), class = "data.frame", vars = c("Name", 
"StimulusName", "StimuliBlock"), drop = TRUE), class = c("grouped_df", 
"tbl_df", "tbl", "data.frame"))

---

Text\u刺激您可以使用您的数据集尝试以下方法：

library(dplyr)
library(stringr)
library(zoo)
df %>% filter(ifelse(str_detect(Reading_Onset,"ReadingOnset"),TRUE,NA) %>%
              na.locf(na.rm=FALSE))

## A tibble: 8 x 4
## Groups:   Name, StimulusName, StimuliBlock [1]
#  Name                StimulusName StimuliBlock Reading_Onset
#  <chr>               <chr>        <chr>        <chr>        
#1 Innocent Subject 15 GenLie20     Block_4      ReadingOnset 
#2 Innocent Subject 15 GenLie20     Block_4      ""           
#3 Innocent Subject 15 GenLie20     Block_4      ""           
#4 Innocent Subject 15 GenLie20     Block_4      ""           
#5 Innocent Subject 15 GenLie20     Block_4      ""           
#6 Innocent Subject 15 GenLie20     Block_4      ""           
#7 Innocent Subject 15 GenLie20     Block_4      ""           
#8 Innocent Subject 15 GenLie20     Block_4      ""

库（dplyr）
图书馆（stringr）
图书馆（动物园）
df%>%过滤器（如果其他（str\u检测（读取开始，“读取插入”），真，NA）%>%
na.locf（na.rm=FALSE））
##一个tibble:8x4
##组：名称、刺激名称、刺激块[1]
#名称刺激名称刺激块阅读开始
#                                         
#1无辜受试者15 GenLie20 Block_4读数输入
#2无辜受试者15 GenLie20 Block_4“
#3无辜受试者15 GenLie20 Block_4“
#4无辜受试者15 GenLie20 Block_4“
#5无辜受试者15 GenLie20 Block_4“
#6无辜受试者15 GenLie20 Block_4“
#7无辜受试者15 GenLie20 Block_4“
#8无辜受试者15 GenLie20 Block_4“
您可以使用数据集尝试以下操作：

library(dplyr)
library(stringr)
library(zoo)
df %>% filter(ifelse(str_detect(Reading_Onset,"ReadingOnset"),TRUE,NA) %>%
              na.locf(na.rm=FALSE))

## A tibble: 8 x 4
## Groups:   Name, StimulusName, StimuliBlock [1]
#  Name                StimulusName StimuliBlock Reading_Onset
#  <chr>               <chr>        <chr>        <chr>        
#1 Innocent Subject 15 GenLie20     Block_4      ReadingOnset 
#2 Innocent Subject 15 GenLie20     Block_4      ""           
#3 Innocent Subject 15 GenLie20     Block_4      ""           
#4 Innocent Subject 15 GenLie20     Block_4      ""           
#5 Innocent Subject 15 GenLie20     Block_4      ""           
#6 Innocent Subject 15 GenLie20     Block_4      ""           
#7 Innocent Subject 15 GenLie20     Block_4      ""           
#8 Innocent Subject 15 GenLie20     Block_4      ""

库（dplyr）
图书馆（stringr）
图书馆（动物园）
df%>%过滤器（如果其他（str\u检测（读取开始，“读取插入”），真，NA）%>%
na.locf（na.rm=FALSE））
##一个tibble:8x4
##组：名称、刺激名称、刺激块[1]
#名称刺激名称刺激块阅读开始
#                                         
#1无辜受试者15 GenLie20 Block_4读数输入
#2无辜受试者15 GenLie20 Block_4“
#3无辜受试者15 GenLie20 Block_4“
#4无辜受试者15 GenLie20 Block_4“
#5无辜受试者15 GenLie20 Block_4“
#6无辜受试者15 GenLie20 Block_4“
#7无辜受试者15 GenLie20 Block_4“
#8无辜受试者15 GenLie20 Block_4“
我无法判断您是否需要在ReadingOnset之前和包括ReadingOnset在内的所有内容，或者是否需要在ReadingOnset之后和包括ReadingOnset在内的所有内容，因此我将两者都显示出来

之前的一切，包括：

library(dplyr)

Text_Stimuli %>% 
  filter(row_number() <= which(grepl("ReadingOnset", Reading_Onset)))

Text_Stimuli %>% 
  filter(row_number() >= which(grepl("ReadingOnset", Reading_Onset)))

我们所做的只是根据“ReadingOnset”所在的行号进行过滤。
我无法判断您是否需要在ReadingOnset之前和之后的所有内容，包括ReadingOnset，所以我将两者都显示出来

之前的一切，包括：

library(dplyr)

Text_Stimuli %>% 
  filter(row_number() <= which(grepl("ReadingOnset", Reading_Onset)))

Text_Stimuli %>% 
  filter(row_number() >= which(grepl("ReadingOnset", Reading_Onset)))

我们所做的只是根据“ReadingOnset”所在的行号进行过滤。
您能阅读并发布您的数据的最小子集以制作一个可运行的示例吗？谢谢Oliver。我马上就去！请您阅读并发布您的数据的最小子集以制作一个可运行的示例，好吗？谢谢Oliver。我马上就去！