Prints a textual description of experimental settings given the specified parameters.

dai.preview_experiment(
  training_frame,
  target_col,
  is_classification,
  is_timeseries,
  accuracy,
  time,
  interpretability,
  enable_gpus = TRUE,
  reproducible = FALSE,
  validation_frame = NULL,
  cols_to_drop = NULL,
  time_col = NULL,
  resumed_model = NULL,
  fold_col = NULL,
  weight_col = NULL,
  config_overrides = "",
  progress = getOption("dai.progress", TRUE)
)

Arguments

training_frame

DAIFrame to be used for the model training.

target_col

The name of the target variable.

is_classification

Whether the predicted variable is categorical (true) or numerical (false).

is_timeseries

Whether the target variable is a time-series or not.

accuracy

Accuracy setting [1-10] (optional).

time

Time setting [1-10] (optional).

interpretability

Interpretability setting [1-10] (optional).

enable_gpus

Whether to use GPUs (optional).

reproducible

Whether to set the experiment to be reproducible or not.

validation_frame

DAIFrame to use for the model validation during the model training (optional).

cols_to_drop

A character vector of column names to be dropped from the data (optional).

time_col

Time column name, containing time ordering for timeseries problems (optional).

resumed_model

Model used for retraining/re-ensembling/starting from checkpoint (optional). You may want to also set the resume_mode parameter. Any parameter not set here will be taken from the resumed model.

fold_col

Fold column name (optional).

weight_col

Weight column name (optional).

config_overrides

Raw config.toml file content (UTF8-encoded string) or a list/vector of config variables.

progress

Whether to display a progress bar.

Value

A character vector of the lines of the experiment preview (invisibly).

See also