Select observation variables.

variable_select selects observation variables based on the specified variable selection method.

variable_select(
  population,
  variables,
  sample = NULL,
  operation = "variance_threshold",
  ...
)

Arguments

population	tbl with grouping (metadata) and observation variables.
variables	character vector specifying observation variables.
sample	tbl containing sample that is used by some variable selection methods. sample has same structure as population.
operation	optional character string specifying method for variable selection. This must be one of the strings "variance_threshold", "correlation_threshold", "drop_na_columns".
...	arguments passed to selection operation.

Value

variable-selected data of the same class as population.

Examples

# In this example, we use `correlation_threshold` as the operation for
# variable selection.

suppressMessages(suppressWarnings(library(magrittr)))
population <- tibble::tibble(
  x = rnorm(100),
  y = rnorm(100) / 1000
)

population %<>% dplyr::mutate(z = x + rnorm(100) / 10)

sample <- population %>% dplyr::slice(1:30)

variables <- c("x", "y", "z")

operation <- "correlation_threshold"

cor(sample)
#>             x           y           z
#> x  1.00000000 -0.08022343  0.99463331
#> y -0.08022343  1.00000000 -0.06732153
#> z  0.99463331 -0.06732153  1.00000000

# `x` and `z` are highly correlated; one of them will be removed

head(population)
#> # A tibble: 6 x 3
#>        x         y      z
#>    <dbl>     <dbl>  <dbl>
#> 1  0.380  0.00105   0.328
#> 2 -0.502 -0.00105  -0.551
#> 3 -0.333 -0.00126  -0.328
#> 4 -1.02   0.00324  -0.889
#> 5 -1.07  -0.000417 -0.842
#> 6  0.304  0.000298  0.458

futile.logger::flog.threshold(futile.logger::ERROR)
#> NULL

variable_select(population, variables, sample, operation) %>% head()
#> # A tibble: 6 x 2
#>           y      z
#>       <dbl>  <dbl>
#> 1  0.00105   0.328
#> 2 -0.00105  -0.551
#> 3 -0.00126  -0.328
#> 4  0.00324  -0.889
#> 5 -0.000417 -0.842
#> 6  0.000298  0.458