validate_outcomes_are_binary: Ensure that the outcome has binary factors
In DavisVaughan/hardhat: Construct Modeling Packages

Description Usage Arguments Details Value Validation See Also Examples

validate - asserts the following:

outcomes must have binary factor columns.

check - returns the following:

ok A logical. Does the check pass?
bad_cols A character vector. The names of the columns with problems.
num_levels An integer vector. The actual number of levels of the columns with problems.

1
2
3

validate_outcomes_are_binary(outcomes)

check_outcomes_are_binary(outcomes)

outcomes

An object to check.

The expected way to use this validation function is to supply it the $outcomes element of the result of a call to mold().

validate_outcomes_are_binary() returns outcomes invisibly.

check_outcomes_are_binary() returns a named list of three components, ok, bad_cols, and num_levels.

hardhat provides validation functions at two levels.

check_*(): check a condition, and return a list. The list always contains at least one element, ok, a logical that specifies if the check passed. Each check also has check specific elements in the returned list that can be used to construct meaningful error messages.
validate_*(): check a condition, and error if it does not pass. These functions call their corresponding check function, and then provide a default error message. If you, as a developer, want a different error message, then call the check_*() function yourself, and provide your own validation function.

Other validation functions: validate_column_names(), validate_no_formula_duplication(), validate_outcomes_are_factors(), validate_outcomes_are_numeric(), validate_outcomes_are_univariate(), validate_prediction_size(), validate_predictors_are_numeric()

# Not a binary factor. 0 levels
check_outcomes_are_binary(data.frame(x = 1))

# Not a binary factor. 1 level
check_outcomes_are_binary(data.frame(x = factor("A")))

# All good
check_outcomes_are_binary(data.frame(x = factor(c("A", "B"))))