Fast approximate Shapley values

Compute fast (approximate) Shapley values for a set of features using the Monte Carlo algorithm described in Strumbelj and Igor (2014). An efficient algorithm for tree-based models, commonly referred to as Tree SHAP, is also supported for lightgbm and xgboost models; see Lundberg et. al. (2020) for details.

Usage

explain(object, ...)

# S3 method for default
explain(
  object,
  feature_names = NULL,
  X = NULL,
  nsim = 1,
  pred_wrapper = NULL,
  newdata = NULL,
  adjust = FALSE,
  baseline = NULL,
  shap_only = TRUE,
  parallel = FALSE,
  ...
)

# S3 method for lm
explain(
  object,
  feature_names = NULL,
  X,
  nsim = 1,
  pred_wrapper,
  newdata = NULL,
  adjust = FALSE,
  exact = FALSE,
  baseline = NULL,
  shap_only = TRUE,
  parallel = FALSE,
  ...
)

# S3 method for xgb.Booster
explain(
  object,
  feature_names = NULL,
  X = NULL,
  nsim = 1,
  pred_wrapper,
  newdata = NULL,
  adjust = FALSE,
  exact = FALSE,
  baseline = NULL,
  shap_only = TRUE,
  parallel = FALSE,
  ...
)

# S3 method for lgb.Booster
explain(
  object,
  feature_names = NULL,
  X = NULL,
  nsim = 1,
  pred_wrapper,
  newdata = NULL,
  adjust = FALSE,
  exact = FALSE,
  baseline = NULL,
  shap_only = TRUE,
  parallel = FALSE,
  ...
)

Arguments

object

A fitted model object (e.g., a ranger::ranger(), xgboost::xgboost(), or earth::earth() object, to name a few).

...

Additional optional arguments to be passed on to foreach::foreach() whenever parallel = TRUE. For example, you may need to supply additional packages that the parallel task depends on via the .packages argument to foreach::foreach(). NOTE: foreach::foreach()'s .combine argument is already set internally by explain(), so passing it via the ... argument would likely result in an error.

feature_names

Character string giving the names of the predictor variables (i.e., features) of interest. If NULL (default) they will be taken from the column names of X.

X

A matrix-like R object (e.g., a data frame or matrix) containing ONLY the feature columns from the training data (or suitable background data set). NOTE: This argument is required whenever exact = FALSE.

nsim

The number of Monte Carlo repetitions to use for estimating each Shapley value (only used when exact = FALSE). Default is 1. NOTE: To obtain the most accurate results, nsim should be set as large as feasibly possible.

pred_wrapper

Prediction function that requires two arguments, object and newdata. NOTE: This argument is required whenever exact = FALSE. The output of this function should be determined according to:

Regression: A numeric vector of predicted outcomes.
Binary classification: A vector of predicted class probabilities for the reference class.
Multiclass classification: A vector of predicted class probabilities for the reference class.

newdata

A matrix-like R object (e.g., a data frame or matrix) containing ONLY the feature columns for the observation(s) of interest; that is, the observation(s) you want to compute explanations for. Default is NULL which will produce approximate Shapley values for all the rows in X (i.e., the training data).

adjust

Logical indicating whether or not to adjust the sum of the estimated Shapley values to satisfy the local accuracy property; that is, to equal the difference between the model's prediction for that sample and the average prediction over all the training data (i.e., X). Default is FALSE and setting to TRUE requires nsim > 1.

baseline

Numeric baseline to use when adjusting the computed Shapley values to achieve local accuracy. Adjusted Shapley values for a single prediction (fx) will sum to the difference fx - baseline. Defaults to NULL, which corresponds to the average predictions computed from X, and zero otherwise (i.e., no additional predictions will be computed and the baseline attribute of the output will be set to zero).

shap_only

Logical indicating whether or not to include additional output useful for plotting (i.e., newdata and the baseline value.). This is convenient, for example, when using shapviz::shapviz() for plotting. Default is TRUE.

parallel

Logical indicating whether or not to compute the approximate Shapley values in parallel across features; default is FALSE. NOTE: setting parallel = TRUE requires setting up an appropriate (i.e., system-specific) parallel backend as described in the foreach; for details, see vignette("foreach", package = "foreach") in R.

exact

Logical indicating whether to compute exact Shapley values. Currently only available for stats::lm(), xgboost::xgboost(), and lightgbm::lightgbm() objects. Default is FALSE. Note that setting exact = TRUE will return explanations for each of the stats::terms() in an stats::lm() object. Default is FALSE.

Value

If shap_only = TRUE (the default), a matrix is returned with one column for each feature specified in feature_names (if feature_names = NULL, the default, there will be one column for each feature in X) and one row for each observation in newdata (if newdata = NULL, the default, there will be one row for each observation in X). Additionally, the returned matrix will have an attribute called "baseline" containing the baseline value. If shap_only = FALSE, then a list is returned with three components:

shapley_values - a matrix of Shapley values (as described above);
feature_values - the corresponding feature values (for plotting with shapviz::shapviz());
baseline - the corresponding baseline value (for plotting with shapviz::shapviz()).

Note

Setting exact = TRUE with a linear model (i.e., an stats::lm() or stats::glm() object) assumes that the input features are independent. Also, setting adjust = TRUE is experimental and we follow the same approach as in shap.

References

Strumbelj, E., and Igor K. (2014). Explaining prediction models and individual predictions with feature contributions. Knowledge and information systems, 41(3), 647-665.

Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., and Lee, Su-In (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1), 2522–5839.

Examples