exprso-predict: Deploy Model

In tpq/exprso: Rapid Deployment of Machine Learning Algorithms

Description

Deploy a model to predict outcomes from the data.

Usage

## S4 method for signature 'ExprsMachine'
predict(object, array, verbose = TRUE)

## S4 method for signature 'ExprsModule'
predict(object, array, verbose = TRUE)

## S4 method for signature 'RegrsModel'
predict(object, array, verbose = TRUE)

## S4 method for signature 'ExprsEnsemble'
predict(object, array, how = "majority",
  verbose = TRUE)

Arguments

object	An exprso model.
array	An exprso object. The test data.
verbose	A boolean. Argument passed to calcStats.
how	A string. Describes how the ensemble decides. By default, it uses "majority" voting. However, the user can select "probability" voting for binary classifier ensembles.

Details

Models can only get deployed on an object of the type used to build the model. This method now supports binary classification, multi-class classification, and regression.

For regression ensembles, the average outcome is reported. For multi-class classifier ensembles, the majority vote is reported. For binary classifier ensembles, the majority vote or probability-weighted vote is reported. For probability-weighted voting considers the threshold, the average "Case" probability is reported. All ties broken randomly.

Value

Returns an exprso prediction object.

tpq/exprso documentation built on July 27, 2019, 8:44 a.m.