Guess task type by the target value from the dataset

For now, supported types are binary classification and regression. Multilabel classification is planned to be added later on.

guess_type(data, y, max_unique_numeric = 5, max_unique_not_numeric = 15)

Arguments

data: A data source, that is one of the major R formats: data.table, data.frame, matrix, and so on.
y: A string that indicates a target column name.
max_unique_numeric: An integer describing the maximal number of unique values in `y` if `y` is numeric.
max_unique_not_numeric: An integer describing the maximal number of unique values in `y` if `y` is NOT numeric.

A string describing the type of ml task: `binary_clf`, `multi_clf` or `regression`.

data(compas)
guess_type(compas,'Two_yr_Recidivism')
#> [1] "binary_clf"