augment.kerasnip_step_view: Augment Method for 'kerasnip_step_view' Objects

In kerasnip: A Bridge Between 'keras' and 'tidymodels'

Augment Method for kerasnip_step_view Objects

Description

Binds predict(x, new_data, type = "numeric")'s .pred column with the step's truth (from kerasnip_step_truth()) and new_data, mirroring workflows:::augment.workflow(). Used internally by int_conformal_split.kerasnip_step_view(). Rows step_sequence() drops for lacking a full window of history are dropped here too, to stay aligned with predict()'s row count.

Usage

## S3 method for class 'kerasnip_step_view'
augment(x, new_data, ...)

Arguments

x	A kerasnip_step_view.
new_data	A data frame of raw predictors (and the original outcome column step_lead() was applied to).
...	Not used.

Value

A tibble: .pred, the step's truth column (named x$outcome_col), and new_data's columns, aligned to the rows that survived windowing.

kerasnip documentation built on Sept. 4, 2026, 1:06 a.m.