plsmod (version 0.1.0)

multi_predict._mixo_pls: Model predictions across many sub-models

Description

Model predictions across many sub-models

Usage

# S3 method for `_mixo_pls`
multi_predict(object, new_data, num_comp = NULL, type = NULL, ...)
# S3 method for `_mixo_spls`
multi_predict(object, new_data, num_comp = NULL, type = NULL, ...)
# S3 method for `_mixo_plsda`
multi_predict(object, new_data, num_comp = NULL, type = NULL, ...)
# S3 method for `_mixo_splsda`
multi_predict(object, new_data, num_comp = NULL, type = NULL, ...)

Arguments

object

An object of class model_fit

new_data

A rectangular data object, such as a data frame.

num_comp

An integer vector for the number of PLS terms to retain.

type

A single character value or NULL. Possible values are "numeric", "class", or "prob". When NULL, predict() will choose an appropriate value based on the model's mode.

...

Not currently used.

Examples

# NOT RUN {
data(meats, package = "modeldata")

mv_meats <-
  pls(num_comp = 20) %>%
  set_engine("mixOmics") %>%
  set_mode("regression") %>%
  fit_xy(x = meats[-(1:5), 1:100], y = meats[-(1:5), 101:103])

pred_vals <- multi_predict(mv_meats, meats[1:5, 1:100], num_comp = 1:10)
# Predictions over components nested within sample rows
pred_vals

# For first sample:
pred_vals$.pred[[1]]

# }