colCounts subject to (in)equality

colCounts.R

library(profmem)
library(Matrix)
dgt <- readMM("~/sparse.mtx.gz")
dgc <- as(dgt, "dgCMatrix")

colCountsEqualZero <- function(x) {
  if (length(x@x) / length(x) > 0.5) {
    # If majority of data are non-zero
    Matrix::colSums(x == 0)
  } else {
    # If majority of data are zero
    nrow(x) - Matrix::colSums(x > 0)
  }
}

colCountsLessThan <- function(x, threshold) {
  if (length(x@x) / length(x) > 0.5) {
    # If majority of data are non-zero
    Matrix::colSums(x < threshold)
  } else {
    # If majority of data are zero
    nrow(x) - Matrix::colSums(x >= threshold)
  }
}

colCountsGreaterThan <- function(x, threshold) {
  if (length(x@x) / length(x) > 0.5) {
    # If majority of data are non-zero
    nrow(x) - Matrix::colSums(x <= threshold)
  } else {
    # If majority of data are zero
    Matrix::colSums(x > threshold)
  }
}

total(profmem(colCountsEqualZero(dgc)))
#> [1] 295577544
total(profmem(colCountsLessThan(dgc, 5)))
#> [1] 787204208
total(profmem(colCountsGreaterThan(dgc, 4)))
#> [1] 787098032