partialDependence: Generate partial dependence plots

In XanderHorn/autoML: Automated machine learning

Description

Creates a list of partial dependence plots for each feature used by the model. Partial dependence is simply the average prediction path a model takes whilst iterating through unique values of a feature and keeping the rest of the features static

Usage

partialDependence(train, trainedModel, sample = 0.1, seed = 1991)

Arguments

train	[data.frame | Required] Training set on which the model was trained
trainedModel	[mlr obj | Required] MLR trained moodel object
sample	[numeric | Optional] A number between 0 - 1 to sub-sample the training set for faster computational time. Default of 0.1
seed	[integer | Optional] Random seed number for reproducable results. Default of 1991

Value

List object containing a plot for each feature in the dataset.

Author(s)

Xander Horn

Examples

mod <- mlr::train(makeLearner("classif.ranger"), iris.task)
partialDependence(train = iris, mod)

XanderHorn/autoML documentation built on Aug. 5, 2020, 11:45 a.m.