在R中，mean()和median()是标准函数，它们执行您所期望的功能。Mode()告诉您对象的内部存储模式，而不是参数中出现次数最多的值。但是是否存在一个标准库函数来实现向量(或列表)的统计模式?
当前回答
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)
其他回答
假设你的观测值是来自实数的类，当你的观测值是2,2,3,3时，你期望模态为2.5，然后你可以用mode = l1 + I * (f1-f0) / (2f1 -f0 - f2)来估计模态，其中l1..最频繁类的下限，f1..最频繁类的频率，f0..在最频繁类之前的类的频率，f2..在最频繁类之后的类的频率，i..分类间隔，如在1,2,3中给出:
#Small Example
x <- c(2,2,3,3) #Observations
i <- 1 #Class interval
z <- hist(x, breaks = seq(min(x)-1.5*i, max(x)+1.5*i, i), plot=F) #Calculate frequency of classes
mf <- which.max(z$counts) #index of most frequent class
zc <- z$counts
z$breaks[mf] + i * (zc[mf] - zc[mf-1]) / (2*zc[mf] - zc[mf-1] - zc[mf+1]) #gives you the mode of 2.5
#Larger Example
set.seed(0)
i <- 5 #Class interval
x <- round(rnorm(100,mean=100,sd=10)/i)*i #Observations
z <- hist(x, breaks = seq(min(x)-1.5*i, max(x)+1.5*i, i), plot=F)
mf <- which.max(z$counts)
zc <- z$counts
z$breaks[mf] + i * (zc[mf] - zc[mf-1]) / (2*zc[mf] - zc[mf-1] - zc[mf+1]) #gives you the mode of 99.5
如果你想要最频繁的级别，并且你有多个最频繁的级别，你可以得到所有的级别，例如:
x <- c(2,2,3,5,5)
names(which(max(table(x))==table(x)))
#"2" "5"
效果很好
> a<-c(1,1,2,2,3,3,4,4,5)
> names(table(a))[table(a)==max(table(a))]
添加raster::modal()作为一个选项，不过请注意，raster是一个很大的包，如果不做地理空间方面的工作，可能不值得安装。
源代码可以从https://github.com/rspatial/raster/blob/master/src/modal.cpp和https://github.com/rspatial/raster/blob/master/R/modal.R中取出，放入个人R包中，供那些特别热衷的人使用。
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)
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()
}
