Check argument specifications for a glmnet model.

Usage

tof_check_model_args(
  split_data,
  model_type = c("linear", "two-class", "multiclass", "survival"),
  best_model_type = c("best", "best with sparsity"),
  response_col,
  time_col,
  event_col
)

Arguments

split_data: An `rsplit` or `rset` object from the rsample package containing the sample-level data to use for modeling. Alternatively, an unsplit tbl_df can be provided, though this is not recommended.
model_type: A string indicating which kind of elastic net model to build. If a continuous response is being predicted, use "linear" for linear regression; if a categorical response with only 2 classes is being predicted, use "two-class" for logistic regression; if a categorical response with more than 2 levels is being predicted, use "multiclass" for multinomial regression; and if a time-to-event outcome is being predicted, use "survival" for Cox regression.
best_model_type: Currently unused.
response_col: Unquoted column name indicating which column in the data contained in `split_data` should be used as the outcome in a "two-class", "multiclass", or "linear" elastic net model. Must be a factor for "two-class" and "multiclass" models and must be a numeric for "linear" models. Ignored if `model_type` is "survival".
time_col: Unquoted column name indicating which column in the data contained in `split_data` represents the time-to-event outcome in a "survival" elastic net model. Must be numeric. Ignored if `model_type` is "two-class", "multiclass", or "linear".
event_col: Unquoted column name indicating which column in the data contained in `split_data` represents the time-to-event outcome in a "survival" elastic net model. Must be a binary column - all values should be either 0 or 1 (with 1 indicating the adverse event) or FALSE and TRUE (with TRUE indicating the adverse event). Ignored if `model_type` is "two-class", "multiclass", or "linear".

Value

A tibble. If arguments are specified correctly, this tibble can be used to create a recipe for preprocessing.