假设我有以下数据
  df
R1 R2
0  0 
1  1
1  1
0  1
1  1 
0  0
0  1
1  0           
0  0
1  0
1  0
1  1        我希望创建一个计数器--在每一列中--逐个计算'1's的出现,每次遇到0时重置,并在新列中输出计数。也就是说,在第1行,它将在第一步重置,然后计数到1,然后计数到2,然后重置,然后计数1,然后重置,复位,重置等,第1列的期望输出是:
  df
R1(Counted) 
N/A   
N/A  
2  
N/A  
1   
N/A  
N/A  
1             
N/A  
N/A  
N/A  
3          我想我需要这样的东西:
Counter = 0  
for i = 1:nrow(df){
  if (???==1){
    counter=counter+1
  } else {
    counter=0
  }
}  但是我真的对计数器没有经验,也不知道如何在重新设置计数器或类似的东西之前,不断地将它的计数打印到一个新的列中。
任何帮助都非常感谢。
发布于 2020-02-28 01:00:38
我们可以创建一个函数,在data.table::rleid的帮助下,根据价值的每一个变化创建组。将所有值转换为NA,但值为1且是组中最后一个元素的值除外。
get_counter <- function(ct) {
   ave(ct, data.table::rleid(ct), FUN = function(x) 
           replace(seq_along(x), x != 1 | seq_along(x) != length(x), NA))
}这个函数可以使用lapply应用于多个列。
df[paste0("ct_", names(df))] <- lapply(df, get_counter)
df
#   R1 R2 ct_R1 ct_R2
#1   0  0    NA    NA
#2   1  1    NA    NA
#3   1  1     2    NA
#4   0  1    NA    NA
#5   1  1     1     4
#6   0  0    NA    NA
#7   0  1    NA     1
#8   1  0     1    NA
#9   0  0    NA    NA
#10  1  0    NA    NA
#11  1  0    NA    NA
#12  1  1     3     1数据
df <- structure(list(R1 = c(0L, 1L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 1L, 
1L, 1L), R2 = c(0L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 1L
)), class = "data.frame", row.names = c(NA, -12L))发布于 2020-02-28 00:41:58
我会这样做:
a <- c(0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1)
b <- sequence(rle(as.character(a))$lengths)
b[a == 0] <- NA                 
b[!is.na(dplyr::lead(b))] <- NA # this finds any where the next value isn't NA
b
# NA NA  2 NA  1 NA NA  1 NA NA NA  3您可以将它变成一个函数,并在您的data.frame上使用data.frame来一次完成每一列,如果您有更多的要做的话,如下所示:
counter <- function(x){
  count <- sequence(rle(as.character(x))$lengths)
  count[x == 0] <- NA
  count[!is.na(dplyr::lead(count))] <- NA
  return(count)
}
df <- data.frame(
  R1 = sample(c(0, 1), 20, T, c(0.2, 0.8)),
  R2 = sample(c(0, 1), 20, T, c(0.7, 0.3))
)
df[paste0(names(df), '_ct')] <- lapply(df, counter)发布于 2020-02-28 01:35:22
下面是一个(相当复杂的)解决方案,它只使用一个基本R,每个循环使用一个while循环( R1和R2)!
df <- data.frame(R1 = c(0,1,1,0,1,0,0,1,0,1,1,1), R2 = c(0,1,1,1,1,0,1,0,0,0,0,1))
#For R1
mycount <- 0
i <- 1
df$R1_counted <- NA
while(i <= nrow(df)){
  mycount <- mycount + df$R1[i]
  if(df$R1[i] == 0 & i == 1){
    df$R1_counted[i] <- NA
  } else if(df$R1[i] != 0 & i == 1){
    df$R1_counted[i] <- df$R1[i]
  }
  if(df$R1[i] == 0 & i > 1){
    df$R1_counted[i] <- NA
    if(df$R1[i-1] != 0){df$R1_counted[i-1] <- mycount}
    mycount <- 0
  } else if(df$R1[i] != 0 & i > 1){
    df$R1_counted[i] <- NA
  }
  if(i == nrow(df) & df$R1[i] != 0){
    df$R1_counted[i] <- mycount
  }
  i <- i + 1
}
#For R2
mycount <- 0
i <- 1
df$R2_counted <- NA
while(i <= nrow(df)){
  mycount <- mycount + df$R2[i]
  if(df$R2[i] == 0 & i == 1){
    df$R2_counted[i] <- NA
  } else if(df$R2[i] != 0 & i == 1){
    df$R2_counted[i] <- df$R2[i]
  }
  if(df$R2[i] == 0 & i > 1){
    df$R2_counted[i] <- NA
    if(df$R2[i-1] != 0){df$R2_counted[i-1] <- mycount}
    mycount <- 0
  } else if(df$R2[i] != 0 & i > 1){
    df$R2_counted[i] <- NA
  }
  if(i == nrow(df) & df$R2[i] != 0){
    df$R2_counted[i] <- mycount
  }
  i <- i + 1
}
df
#   R1 R2 R1_counted R2_counted
#1   0  0         NA         NA
#2   1  1         NA         NA
#3   1  1          2         NA
#4   0  1         NA         NA
#5   1  1          1          4
#6   0  0         NA         NA
#7   0  1         NA          1
#8   1  0          1         NA
#9   0  0         NA         NA
#10  1  0         NA         NA
#11  1  0         NA         NA
#12  1  1          3          1https://stackoverflow.com/questions/60443584
复制相似问题