Stratify operations.

stratify stratifies operations.

stratify(population, sample, reducer, strata, ...)

Arguments

population	tbl with grouping (metadata) and observation variables.
sample	tbl with the same structure as population. This is typically used by operations to estimate parameters.
reducer	operation that is to applied in a stratified manner.
strata	optional character vector specifying grouping variables for stratification.
...	arguments passed to operation.

Value

population with potentially extra columns.

Examples

suppressMessages(suppressWarnings(library(magrittr)))
population <- tibble::tibble(
  Metadata_group = sample(c("a", "b"), 100, replace = TRUE),
  Metadata_type = sample(c("control", "trt"), 100, replace = TRUE),
  AreaShape_Area = c(rnorm(98), 20, 30),
  AreaShape_Eccentricity = rnorm(100)
)
variables <- c("AreaShape_Area", "AreaShape_Eccentricity")
strata <- c("Metadata_group")
sample <- population %>% dplyr::filter(Metadata_type == "control")
population_marked <-
  cytominer::stratify(
    reducer = cytominer::mark_outlier_rows,
    method = "svd+iqr",
    population = population,
    variables = variables,
    sample = sample,
    strata = strata
  )
population_marked %>%
  dplyr::group_by(is_outlier) %>%
  dplyr::sample_n(3)
#> # A tibble: 6 x 5
#> # Groups:   is_outlier [2]
#>   Metadata_group Metadata_type AreaShape_Area AreaShape_Eccentricity is_outlier
#>   <chr>          <chr>                  <dbl>                  <dbl> <lgl>     
#> 1 a              control                0.244                 2.04   FALSE     
#> 2 b              control               -0.476                -1.05   FALSE     
#> 3 b              control                2.20                  0.0210 FALSE     
#> 4 b              control               20                     0.651  TRUE      
#> 5 b              trt                    0.601                 2.00   TRUE      
#> 6 a              trt                    1.96                  1.34   TRUE