r - R 数据框中先前连续出现的事件

Question

我正在尝试编写一个代码，在其中我可以找到相同二进制值的先前连续出现。

我已经设法编写了一个 for 循环来查找以前的值(在我的实际问题中，数据被子集化因此需要一个 for 循环)。

x<-data.frame(successRate=c(1,1,0,1,0,0,0,1,0,1,1,1,0,1,0,0,0,0,1,1,0,1))


xLength<-length(x$successRate)

y<-vector(mode="integer",length<-xLength)

if (xLength>1){

  for (i in 2:xLength){
    y[i]<-x$successRate[i-1]
  }

}

y[1]<-NA

x[,"previous"]<-y

但是我正在寻找如下所需的输出:

# desired output

data.frame(successRate=c(1,1,0,1,0,0,0,1,0,1,1,1,0,1,0,0,0,0,1,1,0,1),previousConsecutiveSuccess=c(NA,1,2,-1,1,-1,-2,-3,1,-1,1,2,3,-1,1,-1,-2,-3,-4,1,2,-1))

Answer 1

x <- data.frame(successRate=c(1,1,0,1,0,0,0,1,0,1,1,1,0,1,0,0,0,0,1,1,0,1))
x$previous <- NA # no need for extra variable

if (nrow(x)>1) {

  # set first consecutive idx manually
  x$previous[2] <- -1+2*x$successRate[1] # -1 if successRate == 0; 1 otherwise

  # loop only if nrow(x) is large enough
  if (nrow(x)>2) {
    for (i in 3:nrow(x)){ # start on row 3, as the last 2 rows are needed
      x$previous[i] <- ifelse(x$successRate[i-1] == x$successRate[i-2], # consecutive?
                              sign(x$previous[i-1])*(abs(x$previous[i-1])+1), # yes: add 1 and keep sign
                              -1+2*x$successRate[i-1])      #  no: 0 -> -1; 1 -> 1
    }
  }
}
print(x$previous)

[1] NA 1 2 -1 1 -1 -2 -3 1 -1 1 2 3 -1 1 -1 -2 -3 -4 1 2 -1