基于其他列1的出现次数重新赋值score列的实现方案咨询

给定如下R数据集：

structure(list(ID = c(1, 2, 3, 4, 6, 7), V = c(0, 0, 1, 1, 
1, 0), Mus = c(1, 0, 1, 1, 1, 0), R = c(1, 0, 1, 1, 1, 1), 
    E = c(1, 0, 0, 1, 0, 0), S = c(1, 0, 1, 1, 1, 0), t = c(0, 
    0, 0, 1, 0, 0), score = c(1, 0.4, 1, 0.4, 0.4, 0.4)), row.names = c(NA, 
-6L), class = c("tbl_df", "tbl", "data.frame"), na.action = structure(c(`5` = 5L, 
`12` = 12L, `15` = 15L, `21` = 21L, `22` = 22L, `23` = 23L, `34` = 34L, 
`44` = 44L, `46` = 46L, `52` = 52L, `56` = 56L, `57` = 57L, `58` = 58L
), class = "omit"))

需按以下规则重新赋值score列：

• 若当前行除ID和score外的列中，数字1的出现次数>3，score设为1；
• 若次数=3，score设为0.4；
• 若次数<3，score设为0。

方法1：for循环实现 #

先将数据存入变量，再逐行计算1的个数并赋值：

# 存储数据集
df <- structure(list(ID = c(1, 2, 3, 4, 6, 7), V = c(0, 0, 1, 1, 1, 0), Mus = c(1, 0, 1, 1, 1, 0), R = c(1, 0, 1, 1, 1, 1), E = c(1, 0, 0, 1, 0, 0), S = c(1, 0, 1, 1, 1, 0), t = c(0, 0, 0, 1, 0, 0), score = c(1, 0.4, 1, 0.4, 0.4, 0.4)), row.names = c(NA, -6L), class = c("tbl_df", "tbl", "data.frame"), na.action = structure(c(`5` = 5L, `12` = 12L, `15` = 15L, `21` = 21L, `22` = 22L, `23` = 23L, `34` = 34L, `44` = 44L, `46` = 46L, `52` = 52L, `56` = 56L, `57` = 57L, `58` = 58L), class = "omit"))

# 循环处理每一行
for (i in 1:nrow(df)) {
  # 统计目标列中1的数量
  count_ones <- sum(df[i, c("V", "Mus", "R", "E", "S", "t")] == 1)
  # 按规则赋值
  if (count_ones > 3) {
    df$score[i] <- 1
  } else if (count_ones == 3) {
    df$score[i] <- 0.4
  } else {
    df$score[i] <- 0
  }
}

方法2：dplyr实现 #

用rowwise()做行操作，搭配case_when()写条件逻辑，代码更简洁：

library(dplyr)

df <- df %>%
  rowwise() %>%
  mutate(
    count_ones = sum(c_across(V:t) == 1), # 统计V到t列的1的数量
    score = case_when(
      count_ones > 3 ~ 1,
      count_ones == 3 ~ 0.4,
      TRUE ~ 0
    )
  ) %>%
  ungroup() # 取消行分组

# 若不需要保留count_ones列，可追加：
# select(-count_ones)

方法3：apply函数实现 #

用apply()按行处理目标列，直接返回赋值结果：

# 选取需要统计的列（排除ID和score）
target_cols <- df[, c("V", "Mus", "R", "E", "S", "t")]

# 按行计算并赋值
df$score <- apply(target_cols, 1, function(x) {
  cnt <- sum(x == 1)
  if (cnt > 3) 1 else if (cnt == 3) 0.4 else 0
})

方法4：purrr::map实现 #

用map_dbl()遍历每行数据，计算后返回数值型结果：

library(purrr)

# 方法4.1：拆分数据为行列表后处理
target_cols <- df[, c("V", "Mus", "R", "E", "S", "t")]
row_list <- split(target_cols, seq(nrow(target_cols)))

df$score <- map_dbl(row_list, function(row) {
  cnt <- sum(row == 1)
  if (cnt > 3) 1 else if (cnt == 3) 0.4 else 0
})

# 方法4.2：结合dplyr用pmap_dbl
df <- df %>%
  mutate(
    score = pmap_dbl(select(., V:t), function(...) {
      cnt <- sum(c(...) == 1)
      if (cnt > 3) 1 else if (cnt == 3) 0.4 else 0
    })
  )

内容的提问来源于stack exchange，提问作者12666727b9