CRAN上现在可用的折叠包中的通用函数fmode实现了基于索引哈希的基于c++的模式。它比上述任何一种方法都要快得多。它提供了向量、矩阵、data.frames和dplyr分组tibbles的方法。语法:

libary(collapse)
fmode(x, g = NULL, w = NULL, ...)

其中x可以是上述对象之一，g提供一个可选的分组向量或分组向量列表(用于分组模式计算，也在c++中执行)，w(可选)提供一个数值权重向量。在分组tibble方法中，没有g参数，您可以执行data %>% group_by(idvar) %>% fmode。

效果很好

> a<-c(1,1,2,2,3,3,4,4,5)
> names(table(a))[table(a)==max(table(a))]

下面的函数有三种形式:

method = "mode"[默认值]:计算单模态向量的模式，否则返回NA Method = "nmodes":计算vector中模式的个数 Method = "modes":列出单模态或多模态向量的所有模态

modeav <- function (x, method = "mode", na.rm = FALSE)
{
  x <- unlist(x)
  if (na.rm)
    x <- x[!is.na(x)]
  u <- unique(x)
  n <- length(u)
  #get frequencies of each of the unique values in the vector
  frequencies <- rep(0, n)
  for (i in seq_len(n)) {
    if (is.na(u[i])) {
      frequencies[i] <- sum(is.na(x))
    }
    else {
      frequencies[i] <- sum(x == u[i], na.rm = TRUE)
    }
  }
  #mode if a unimodal vector, else NA
  if (method == "mode" | is.na(method) | method == "")
  {return(ifelse(length(frequencies[frequencies==max(frequencies)])>1,NA,u[which.max(frequencies)]))}
  #number of modes
  if(method == "nmode" | method == "nmodes")
  {return(length(frequencies[frequencies==max(frequencies)]))}
  #list of all modes
  if (method == "modes" | method == "modevalues")
  {return(u[which(frequencies==max(frequencies), arr.ind = FALSE, useNames = FALSE)])}  
  #error trap the method
  warning("Warning: method not recognised.  Valid methods are 'mode' [default], 'nmodes' and 'modes'")
  return()
}

这建立在jprockbelly的答案上，通过对非常短的向量增加速度。这在将mode应用到data.frame或包含很多小组的数据表时非常有用:

Mode <- function(x) {
   if ( length(x) <= 2 ) return(x[1])
   if ( anyNA(x) ) x = x[!is.na(x)]
   ux <- unique(x)
   ux[which.max(tabulate(match(x, ux)))]
}

抱歉，我可能把它理解得太简单了，但这不是可以工作的吗?(我的机器上的1E6值在1.3秒内):

t0 <- Sys.time()
summary(as.factor(round(rnorm(1e6), 2)))[1]
Sys.time()-t0

你只需要用你的向量替换“round(rnorm(1e6)，2)”。

为了生成模式，我写了下面的代码。

MODE <- function(dataframe){
    DF <- as.data.frame(dataframe)

    MODE2 <- function(x){      
        if (is.numeric(x) == FALSE){
            df <- as.data.frame(table(x))  
            df <- df[order(df$Freq), ]         
            m <- max(df$Freq)        
            MODE1 <- as.vector(as.character(subset(df, Freq == m)[, 1]))

            if (sum(df$Freq)/length(df$Freq)==1){
                warning("No Mode: Frequency of all values is 1", call. = FALSE)
            }else{
                return(MODE1)
            }

        }else{ 
            df <- as.data.frame(table(x))  
            df <- df[order(df$Freq), ]         
            m <- max(df$Freq)        
            MODE1 <- as.vector(as.numeric(as.character(subset(df, Freq == m)[, 1])))

            if (sum(df$Freq)/length(df$Freq)==1){
                warning("No Mode: Frequency of all values is 1", call. = FALSE)
            }else{
                return(MODE1)
            }
        }
    }

    return(as.vector(lapply(DF, MODE2)))
}

让我们试试吧:

MODE(mtcars)
MODE(CO2)
MODE(ToothGrowth)
MODE(InsectSprays)