получить наиболее распространенные траектории источника-назначения в R

Все, о чем вы просите, — это многомерный биннинг.

Я создал случайный набор данных dt о происхождении и назначении для демонстрации. Выходным результатом является data.table, который дает следующую информацию о наиболее часто встречающейся траектории:

• Нижний и верхний пределы координат x-y, которые определяют исходную сетку
• Нижний и верхний пределы координат x-y, которые определяют сетку назначения
• Считать

library(data.table)
library(magrittr)

N <- 5000
set.seed(123)
gp <- 0.1 #grid precision

# Generate an example dataset -----
{
  dt <- data.table(
    origin_x = rnorm(N, 1, 0.1),
    origin_y = rnorm(N, 2, 0.1),
    destination_x = rnorm(N, 11, 0.1),
    destination_y = rnorm(N, 12, 0.1)
  )
}

# Grid formation ----
{
  ## Defining the ranges (LL and UL stand for lower and upper limits, respectively) ----
  {
    origin_x_LL <- dt[, origin_x] %>% min %>% divide_by(gp) %>% floor %>% multiply_by(gp)
    origin_x_UL <- dt[, origin_x] %>% max %>% divide_by(gp) %>% ceiling %>% multiply_by(gp)
    origin_y_LL <- dt[, origin_y] %>% min %>% divide_by(gp) %>% floor %>% multiply_by(gp)
    origin_y_UL <- dt[, origin_y] %>% max %>% divide_by(gp) %>% ceiling %>% multiply_by(gp)
    destination_x_LL <- dt[, destination_x] %>% min %>% divide_by(gp) %>% floor %>% multiply_by(gp)
    destination_x_UL <- dt[, destination_x] %>% max %>% divide_by(gp) %>% ceiling %>% multiply_by(gp)
    destination_y_LL <- dt[, destination_y] %>% min %>% divide_by(gp) %>% floor %>% multiply_by(gp)
    destination_y_UL <- dt[, destination_y] %>% max %>% divide_by(gp) %>% ceiling %>% multiply_by(gp)
  }
  ## Forming the breaks for binning ----
  {
    origin_x_brks <- seq(origin_x_LL, origin_x_UL, by = gp)
    origin_y_brks <- seq(origin_y_LL, origin_y_UL, by = gp)
    destination_x_brks <- seq(destination_x_LL, destination_x_UL, by = gp)
    destination_y_brks <- seq(destination_y_LL, destination_y_UL, by = gp)
  }
  ## Computing the number of bins ----
  {
    origin_x_Nbin <- length(origin_x_brks) - 1L
    origin_y_Nbin <- length(origin_y_brks) - 1L
    destination_x_Nbin <- length(destination_x_brks) - 1L
    destination_y_Nbin <- length(destination_y_brks) - 1L
  }
  ## Binning ----
  {
    origin_x_bin <- .bincode(dt[, origin_x], origin_x_brks, include.lowest = T)
    origin_y_bin <- .bincode(dt[, origin_y], origin_y_brks, include.lowest = T)
    destination_x_bin <- .bincode(dt[, destination_x], destination_x_brks, include.lowest = T)
    destination_y_bin <- .bincode(dt[, destination_y], destination_y_brks, include.lowest = T)
  }
}

# Counting grid frequency ----
{
  grid_count <-
    lapply(seq(origin_x_Nbin), function(i) {
      lapply(seq(origin_y_Nbin), function(j) {
        lapply(seq(destination_x_Nbin), function(m) {
          lapply(seq(destination_y_Nbin), function(n) {
            this_count = which(origin_x_bin == i & origin_y_bin == j & destination_x_bin == m & destination_y_bin == n) %>% length
            return(data.table(origin_x_LL = origin_x_brks[i], origin_x_UL = origin_x_brks[i + 1],
                              origin_y_LL = origin_y_brks[j], origin_y_UL = origin_y_brks[j + 1],
                              destination_x_LL = destination_x_brks[m], destination_x_UL = destination_x_brks[m + 1],
                              destination_y_LL = destination_y_brks[n], destination_y_UL = destination_y_brks[n + 1],
                              count = this_count))
          }) %>% rbindlist
        }) %>% rbindlist
      }) %>% rbindlist
    }) %>% rbindlist
}

# Getting the most frequent grid ----
{
  print(grid_count[count == max(count)])
}