每次遇到关键字时插入一个空行

Question

我有这个数据集：

structure(list(Event = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 2L, 
1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L), .Label = c("Insert", 
"Ok"), class = "factor")), .Names = "Event", class = "data.frame", row.names = c(NA, 
-18L))

每当有＆＃34;插入＆＃34;

时，我想在下面插入一个空行

我如何在R？

中执行此操作

Answer 1

这是基于整数索引的第二种方法。在这里，我将使用一个字符向量，因为这对于提供的数据更有意义。

# get integer index with repeats for observations with "Insert"
myRows <- sort(c(seq_along(temp), which(temp == "Insert")))
# set second row index to missing
is.na(myRows) <- duplicated(myRows)

现在，将其提供给索引字符向量。

temp[myRows]
 [1] "Ok"     "Ok"     "Insert" NA       "Ok"     "Ok"     "Ok"     "Ok"     "Insert" NA       "Insert" NA       "Ok"    
[14] "Ok"     "Ok"     "Ok"     "Insert" NA       "Ok"     "Ok"     "Ok"     "Insert" NA  

数据

temp <-
structure(list(Event = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 2L, 
1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L), .Label = c("Insert", 
"Ok"), class = "factor")), .Names = "Event", class = "data.frame", row.names = c(NA, 
-18L))

temp <- as.character(temp$Event)

Answer 2

我们可以创建一个逻辑向量

i1 <- df1$Event == "Insert"
Event <- unlist(lapply(split(df1$Event, 
    cumsum(c(TRUE, i1[-length(i1)]))), function(x) c(as.character(x), "")))
df2 <- data.frame(Event, stringsAsFactors=FALSE)

或另一种选择是

library(data.table)
setDT(df1)[, grp := cumsum(shift(Event == "Insert", fill = TRUE))
      ][, .SD[c(seq_len(.N), .N+1)] , grp
        ][is.na(Event), Event := ""
         ][, grp := NULL][]
#     Event
# 1:     Ok
# 2:     Ok
# 3: Insert
# 4:       
# 5:     Ok
# 6:     Ok
# 7:     Ok
# 8:     Ok
# 9: Insert
#10:       
#11: Insert
#12:       
#13:     Ok
#14:     Ok
#15:     Ok
#16:     Ok
#17: Insert
#18:       
#19:     Ok
#20:     Ok
#21:     Ok
#22: Insert
#23:       

Answer 3

这是一个想法：

mydf <- structure(list(Event = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 2L, 
1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L), .Label = c("Insert", 
"Ok"), class = "factor")), .Names = "Event", class = "data.frame", row.names = c(NA, 
-18L))

mydf$rowindex <- 1:nrow(mydf)
mydf$repeats <- 1
mydf$repeats[which(mydf$Event=="Insert")] <- 2
mydf2 <- mydf[rep(mydf$rowindex,mydf$repeats),]
mydf2[which(grepl("\\.",row.names(mydf2))),"Event"] <- NA

如果有帮助，请告诉我。