小编Vic*_*yuk的帖子

我需要在包含因子和数字列的大型（许多 GB）表中重复查找“最接近”的行。使用dplyr，它看起来像这样：

df <- data.frame(factorA = rep(letters[1:3], 100000),
             factorB = sample(rep(letters[1:3], 100000), 
                              3*100000, replace = FALSE),
             numC = round(rnorm(3*100000), 2),
             numD = round(rnorm(3*100000), 2))

closest <- function(ValueA, ValueB, ValueC, ValueD) {
  df_sub <- df %>%
    filter(factorA == ValueA,
           factorB == ValueB,
           numC >= 0.9 * ValueC,
           numC <= 1.1 * ValueC,
           numD >= 0.9 * ValueD,
           numD <= 1.1 * ValueD)

  if (nrow(df_sub) == 0) stop("Oh-oh, no candidates.")

  minC <- df_sub[which.min(abs(df_sub$numC - ValueC)), "numC"]

  df_sub %>%
    filter(numC == …