R6 Class representing a forward marginal effect (FME)

The FME is a forward difference in prediction due to a specified change in feature values.

Public fields

feature

vector of features

predictor

Predictor object

step.size

vector of step sizes for features specified by "feature"

data.step

the data.table with the data matrix after the step

ep.method

string specifying extrapolation detection method

compute.nlm

logical specifying if NLM should be computed

nlm.intervals

number of intervals for computing NLMs

step.type

"numerical" or "categorical"

extrapolation.ids

vector of observation ids classified as extrapolation points

results

data.table with FMEs and NLMs computed

ame

Average Marginal Effect (AME) of observations in results

anlm

Average Non-linearity Measure (ANLM) of observations in results

computed

logical specifying if compute() has been run

Methods

Public methods

• ForwardMarginalEffect$new()

• ForwardMarginalEffect$compute()

• ForwardMarginalEffect$plot()

• ForwardMarginalEffect$clone()

---

Method new()

Create a new ForwardMarginalEffect object.

Usage

ForwardMarginalEffect$new(
  predictor,
  features,
  ep.method = "none",
  compute.nlm = FALSE,
  nlm.intervals = 1
)

Arguments

predictor

Predictor object.

features

A named list with the feature name(s) and step size(s).

ep.method

String specifying extrapolation detection method.

compute.nlm

Compute NLM with FMEs? Defaults to FALSE.

nlm.intervals

How many intervals for NLM computation. Defaults to 1.

Returns

A new ForwardMarginalEffect object.

Examples

# Train a model:

library(mlr3verse)
library(ranger)
data(bikes, package = "fmeffects")
forest = lrn("regr.ranger")$train(as_task_regr(x = bikes, target = "count"))

# Create an `ForwardMarginalEffect` object:
effects = ForwardMarginalEffect$new(makePredictor(forest, bikes),
                  features = list("temp" = 1, "humidity" = 0.01),
                  ep.method = "envelope")

---

Method compute()

Computes results, i.e., FME (and NLMs) for non-extrapolation points, for a ForwardMarginalEffect object.

Usage

ForwardMarginalEffect$compute()

Returns

A ForwardMarginalEffect object with results.

Examples

# Compute results:
effects$compute()

---

Method plot()

Plots results, i.e., FME (and NLMs) for non-extrapolation points, for an FME object.

Usage

ForwardMarginalEffect$plot(with.nlm = FALSE, bins = 40, binwidth = NULL)

Arguments

with.nlm

Plots NLMs if computed, defaults to FALSE.

bins

Numeric vector giving number of bins in both vertical and horizontal directions. Applies only to univariate or bivariate numeric effects. See ggplot2::stat_summary_hex() for details.

binwidth

Numeric vector giving bin width in both vertical and horizontal directions. Overrides bins if both set. Applies only to univariate or bivariate numeric effects. See ggplot2::stat_summary_hex() for details.

Examples

# Compute results:
effects$plot()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

ForwardMarginalEffect$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

## ------------------------------------------------
## Method `ForwardMarginalEffect$new`
## ------------------------------------------------


# Train a model:

library(mlr3verse)
library(ranger)
data(bikes, package = "fmeffects")
forest = lrn("regr.ranger")$train(as_task_regr(x = bikes, target = "count"))

# Create an `ForwardMarginalEffect` object:
effects = ForwardMarginalEffect$new(makePredictor(forest, bikes),
                  features = list("temp" = 1, "humidity" = 0.01),
                  ep.method = "envelope")

## ------------------------------------------------
## Method `ForwardMarginalEffect$compute`
## ------------------------------------------------

# Compute results:
effects$compute()

## ------------------------------------------------
## Method `ForwardMarginalEffect$plot`
## ------------------------------------------------

# Compute results:
effects$plot()