HMDA (version 0.2.0)

hmda.test: Normalize a vector based on specified minimum and maximum values

Description

This function normalizes a vector based on specified minimum and maximum values. If the minimum and maximum values are not specified, the function will use the minimum and maximum values of the vector.

Usage

hmda.test(wmshap, features = NULL, domains = NULL, n = 5000)

Value

normalized numeric vector

Arguments

wmshap

object of class 'shapley', as returned by the 'shapley' function

features

character, name of two features to be compared with permutation test

domains

list of two character vectors, each including a number of features.

n

integer, number of permutations

Author

E. F. Haghish

Examples

if (FALSE) {
# load the required libraries for building the base-learners and the ensemble models
library(h2o)            #shapley supports h2o models
library(autoEnsemble)   #autoEnsemble models, particularly useful under severe class imbalance
library(shapley)

# initiate the h2o server
h2o.init(ignore_config = TRUE, nthreads = 2, bind_to_localhost = FALSE, insecure = TRUE)

# upload data to h2o cloud
prostate_path <- system.file("extdata", "prostate.csv", package = "h2o")
prostate <- h2o.importFile(path = prostate_path, header = TRUE)

### H2O provides 2 types of grid search for tuning the models, which are
### AutoML and Grid. Below, I demonstrate how weighted mean shapley values
### can be computed for both types.

set.seed(10)

#######################################################
### PREPARE AutoML Grid (takes a couple of minutes)
#######################################################
# run AutoML to tune various models (GBM) for 60 seconds
y <- "CAPSULE"
prostate[,y] <- as.factor(prostate[,y])  #convert to factor for classification
aml <- h2o.automl(y = y, training_frame = prostate, max_runtime_secs = 120,
                 include_algos=c("GBM"),

                 # this setting ensures the models are comparable for building a meta learner
                 seed = 2023, nfolds = 10,
                 keep_cross_validation_predictions = TRUE)

### call 'shapley' function to compute the weighted mean and weighted confidence intervals
### of SHAP values across all trained models.
### Note that the 'newdata' should be the testing dataset!
result <- shapley(models = aml, newdata = prostate, plot = TRUE)

#######################################################
### Significance testing of contributions of two features
#######################################################
# testing the WMSHAP contributions of two features
hmda.test(result, features = c("GLEASON", "PSA"), n = 5000)

# testing the WMSHAP contributions of two domains (groups of features, latent factors, etc.)
hmda.test(result,
          n = 5000,
          domains = list(Demographic = c("RACE", "AGE"),
                         Cancer = c("VOL", "PSA", "GLEASON")))
}