如何在R语言中为序列对应位置补充缺失值？

我有如下格式的DataFrame：

dat <- data.frame(matrix(nrow = 10, ncol = 4))
dat$X1 <- seq(1,10)
dat$X2 <- c(1,1,1,1,2,2,2,2,3,3)
dat$X3 <- c(1)
dat$X4 <- c("c(2,3,4)","c(1,2,4)","c(1,2,3,4)","c(1,2,3)","c(1,2,3,4)",
            "c(1,2,3,4)","c(2,3,4)","c(1,2,3)","c(1,2,3,4)","c(1,2,3,4)")
colnames(dat) <- c("Subject","Session","other","option")

我尝试用tidyr包处理：

library(tidyr)
dat <- separate(dat, option, sep = ",", into = paste0("option.", 1:4))
colnames(dat) <- c("Subject","Session","other","pk1","pk2","pk3","pk4")
dat$pk1 <- gsub("c", "", dat$pk1)
dat$pk1 <- gsub("[()]", "", dat$pk1)
dat$pk3 <- gsub("[()]", "", dat$pk3)

但我需要得到如下格式的结果：

dat <- data.frame(matrix(nrow = 10, ncol = 4))
dat$X1 <- seq(1,10)
dat$X2 <- c(1,1,1,1,2,2,2,2,3,3)
dat$X3 <- c(1)
dat$X4 <- c("c(NA,2,3,4)","c(1,2,NA,4)","c(1,2,3,4)","c(1,2,3,NA)","c(1,2,3,4)",
            "c(1,2,3,4)","c(NA,2,3,4)","c(1,2,3,NA)","c(1,2,3,4)","c(1,2,3,4)")
colnames(dat) <- c("Subject","Session","other","option")
dat <- separate(dat, option, sep = ",", into = paste0("option.", 1:4))
colnames(dat) <- c("Subject","Session","other","pk1","pk2","pk3","pk4")
dat$pk1 <- gsub("c", "", dat$pk1)
dat$pk1 <- gsub("[()]", "", dat$pk1)
dat$pk4 <- gsub("[()]", "", dat$pk4)
dat
#    Subject Session other pk1 pk2 pk3 pk4
# 1        1       1     1  NA   2   3   4
# 2        2       1     1   1   2  NA   4
# 3        3       1     1   1   2   3   4
# 4        4       1     1   1   2   3  NA
# 5        5       2     1   1   2   3   4
# 6        6       2     1   1   2   3   4
# 7        7       2     1  NA   2   3   4
# 8        8       2     1   1   2   3  NA
# 9        9       3     1   1   2   3   4
# 10      10       3     1   1   2   3   4

请问该如何为序列添加对应位置的缺失值？

提供两种可行的处理方式，都能得到目标结果：

方法一：解析向量后补全NA #

先把option列的字符串转换成实际数值向量，再将每个向量补全到4个元素，缺失的位置填充NA，最后拆分到对应列：

library(dplyr)
library(tidyr)

# 原始数据
dat <- data.frame(matrix(nrow = 10, ncol = 4))
dat$X1 <- seq(1,10)
dat$X2 <- c(1,1,1,1,2,2,2,2,3,3)
dat$X3 <- c(1)
dat$X4 <- c("c(2,3,4)","c(1,2,4)","c(1,2,3,4)","c(1,2,3)","c(1,2,3,4)",
            "c(1,2,3,4)","c(2,3,4)","c(1,2,3)","c(1,2,3,4)","c(1,2,3,4)")
colnames(dat) <- c("Subject","Session","other","option")

# 处理流程
dat_processed <- dat %>%
  # 将字符串格式的向量解析为实际R向量
  mutate(option = lapply(option, function(x) eval(parse(text = x)))) %>%
  # 补全每个向量到4个元素，对应位置缺失则填NA
  mutate(option = lapply(option, function(x) {
    full_vec <- rep(NA, 4)
    full_vec[x] <- x
    full_vec
  })) %>%
  # 将向量拆分为单独的列
  unnest_wider(option, names_sep = "") %>%
  # 重命名为目标列名
  rename(pk1 = option1, pk2 = option2, pk3 = option3, pk4 = option4)

# 查看结果
dat_processed

方法二：纯字符串处理补全NA #

如果担心eval解析字符串的风险，可以直接通过字符串操作提取数字，对比完整序列后补全NA：

library(tidyr)
library(stringr)
library(dplyr)

# 原始数据
dat <- data.frame(matrix(nrow = 10, ncol = 4))
dat$X1 <- seq(1,10)
dat$X2 <- c(1,1,1,1,2,2,2,2,3,3)
dat$X3 <- c(1)
dat$X4 <- c("c(2,3,4)","c(1,2,4)","c(1,2,3,4)","c(1,2,3)","c(1,2,3,4)",
            "c(1,2,3,4)","c(2,3,4)","c(1,2,3)","c(1,2,3,4)","c(1,2,3,4)")
colnames(dat) <- c("Subject","Session","other","option")

# 处理流程
dat_processed <- dat %>%
  # 提取每个option中的数字
  mutate(nums = str_extract_all(option, "\\d+")) %>%
  # 对比完整的1-4序列，缺失位置填NA
  mutate(option = lapply(nums, function(x) {
    full_seq <- 1:4
    ifelse(full_seq %in% as.integer(x), full_seq, NA)
  })) %>%
  # 拆分向量为单独列并重命名
  unnest_wider(option, names_sep = "") %>%
  rename(pk1 = option1, pk2 = option2, pk3 = option3, pk4 = option4) %>%
  # 移除中间临时列
  select(-nums)

# 查看结果
dat_processed

内容的提问来源于Stack Exchange，提问作者jc2525