R-找数据的波谷：找出位置和数值并画在图上

1. 普通函数

Assuming your data is stored in a variable called data

data <- c(1,0,9,8,77,5,3,0,0,8,9,55,4,33,22,11,2) # Replace with your actual data

Calculate density

dens <- density(data)

Find indices of local minima

find_minima <- function(dens_y) {    
  local_minima <- c(FALSE, diff(sign(diff(dens_y))) > 0, FALSE)    
  return(local_minima)
}

Apply the function to density values

minima_indices <- find_minima(dens$y)

Get the x value corresponding to the valley

valley_x <- dens$x[minima_indices]

Plot the density and highlight the valley

plot(dens, main = "Density Distribution with Valley")
polygon(dens, col="lightcoral", border="black")
points(valley_x, dens$y[minima_indices], col="blue", pch=19)

image.png

2. ggplot2的实现

加载必要的包

library(ggplot2)

假设数据存储在变量 data 中，这里顺便换组数据试试看

data <- c(1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 2, 3, 3, 3, 3, 3, 3)

计算密度

dens <- density(data)

找到局部极小值的索引

find_minima <- function(dens_y) {
    local_minima <- c(FALSE, diff(sign(diff(dens_y))) > 0, FALSE)
    return(local_minima)
}

应用函数找出密度中的极小值

minima_indices <- find_minima(dens$y)

获取波谷对应的x值和y值

valley_x <- dens$x[minima_indices]
valley_y <- dens$y[minima_indices]

将密度估计结果转化为数据框，以便使用ggplot2

df <- data.frame(x = dens$x, y = dens$y)

使用ggplot2绘制密度图，并标注波谷

ggplot(df, aes(x = x, y = y)) +
    geom_line(size = 1) +
    geom_area(fill = "lightcoral", alpha = 0.5) +
    geom_point(aes(x = valley_x, y = valley_y), color = "blue", size = 3) +
    ggtitle("let us see 1 see") +
    labs(x = "Value", y = "Density") +
    theme_minimal(base_size = 15) +
    theme(
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        panel.border = element_rect(color = "black", fill = NA, size = 1)
    )

image.png