get_y_weight_input: Create input list for 'get_y_weight'
In benkeser/cvma: Cross-validation-based maximal association

Create input list for get_y_weight

1 2	get_y_weight_input(split_Y, Ynames, valid_folds, all_fits, all_sl, all_fit_tasks, sl_control, V, learners)

`split_Y`	The outcome matrix split by relevant validation folds.
`Ynames`	The names of the outcomes. Used to search `all_fits` and `all_sl`.
`valid_folds`	If not `NULL`, identifies validation folds used in the inner most super learner. Set to `NULL` when getting weights for outer cross-validation folds (where all folds are used for training super learner).
`all_fits`	List of all learner fits.
`all_sl`	List of all super learner weight fits
`all_fit_tasks`	List of all learner fit tasks (faster to search over than search over all_fits).
`sl_control`	List of super learner controls.
`V`	Number of folds.
`learners`	Vector of super learner vectors.

List with each entry a list with entries: valid_fold (the number of the corresponding fold), Y (the outcome matrix in this validation fold), pred (matrix of outcome predictions for this validation fold from the super learner fit in training folds). The length of the list varies according to what is input into valid_folds so that this function may be used both in the outer and inner layers of cross-validation.

benkeser/cvma documentation built on May 5, 2019, 1:37 p.m.