Shapley function

Prediction explanations with game theory

Shapley computes feature contributions for single predictions with the Shapley value, an approach from cooperative game theory. The features values of an instance cooperate to achieve the prediction. The Shapley value fairly distributes the difference of the instance's prediction and the datasets average prediction among the features.

Details

For more details on the algorithm see https://christophm.github.io/interpretable-ml-book/shapley.html

Examples

library("rpart")
# First we fit a machine learning model on the Boston housing data
data("Boston", package = "MASS")
rf <- rpart(medv ~ ., data = Boston)
X <- Boston[-which(names(Boston) == "medv")]
mod <- Predictor$new(rf, data = X)

# Then we explain the first instance of the dataset with the Shapley method:
x.interest <- X[1, ]
shapley <- Shapley$new(mod, x.interest = x.interest)
shapley

# Look at the results in a table
shapley$results
# Or as a plot
plot(shapley)

# Explain another instance
shapley$explain(X[2, ])
plot(shapley)
## Not run:

# Shapley() also works with multiclass classification
rf <- rpart(Species ~ ., data = iris)
X <- iris[-which(names(iris) == "Species")]
mod <- Predictor$new(rf, data = X, type = "prob")

# Then we explain the first instance of the dataset with the Shapley() method:
shapley <- Shapley$new(mod, x.interest = X[1, ])
shapley$results
plot(shapley)

# You can also focus on one class
mod <- Predictor$new(rf, data = X, type = "prob", class = "setosa")
shapley <- Shapley$new(mod, x.interest = X[1, ])
shapley$results
plot(shapley)
## End(Not run)

References

Strumbelj, E., Kononenko, I. (2014). Explaining prediction models and individual predictions with feature contributions. Knowledge and Information Systems, 41(3), 647-665. https://doi.org/10.1007/s10115-013-0679-x

See Also

Shapley

A different way to explain predictions: LocalModel

Super class

iml::InterpretationMethod -> Shapley

Public fields

• x.interest: data.frame

   Single row with the instance to be explained.
  

• y.hat.interest: numeric

   Predicted value for instance of interest.
  

• y.hat.average: numeric(1)

   Average predicted value for data `X`.
  

• sample.size: numeric(1)

   The number of times coalitions/marginals are sampled from data X. The higher the more accurate the explanations become.
  

Methods

Public methods

• list("Shapley$new()")

• list("Shapley$explain()")

• list("Shapley$clone()")

Method new()

Create a Shapley object

Usage

Shapley$new(predictor, x.interest = NULL, sample.size = 100)

Arguments

• predictor: Predictor

   The object (created with `Predictor$new()`) holding the machine learning model and the data.
  

• x.interest: data.frame

   Single row with the instance to be explained.
  

• sample.size: numeric(1)

   The number of Monte Carlo samples for estimating the Shapley value.
  

Returns

data.frame

data.frame with the Shapley values (phi) per feature.

Method explain()

Set a new data point which to explain.

Usage

Shapley$explain(x.interest)

Arguments

• x.interest: data.frame

   Single row with the instance to be explained.
  

Method clone()

The objects of this class are cloneable with this method.

Usage

Shapley$clone(deep = FALSE)

Arguments

• deep: Whether to make a deep clone.