dot-prepare_familiar_data_sets: Prepare familiarData objects for evaluation at runtime.

In familiar: End-to-End Automated Machine Learning and Model Evaluation

Prepare familiarData objects for evaluation at runtime.

Description

Information concerning models, features and the experiment is processed and stored in familiarData objects. Information can be extracted from these objects as csv files, or by plotting, or multiple objects can be combined into familiarCollection objects, which allows aggregated exports.

Usage

.prepare_familiar_data_sets(
  cl = NULL,
  only_pooling = FALSE,
  message_indent = 0L,
  verbose = FALSE
)

Arguments

cl	Cluster for parallel processing.
only_pooling	Flag that, if set, forces evaluation of only the top-level data, and not e.g. ensembles.
message_indent	indent that messages should have.
verbose	Sets verbosity

Details

This function generates the names of familiarData object files, and their corresponding generating ensemble, which allows the familiarData objects to be created.

Value

A data.table with created links to created data objects.

familiar documentation built on Sept. 30, 2024, 9:18 a.m.