validate: sboost Validation Function

In sboost: Machine Learning with AdaBoost on Decision Stumps

sboost Validation Function

Description

A k-fold cross validation algorithm for sboost.

Usage

validate(
  features,
  outcomes,
  iterations = 1,
  k_fold = 6,
  positive = NULL,
  verbose = FALSE
)

Arguments

features	feature set data.frame.
outcomes	outcomes corresponding to the features.
iterations	number of boosts.
k_fold	number of cross-validation subsets.
positive	is the positive outcome to test for; if NULL, the first in alphabetical order will be chosen
verbose	If true, progress bars will be displayed in console.

Value

An sboost_validation S3 object containing:

performance

Final performance statistics for all stumps.

training_summary_statistics

Mean and standard deviations for test statistics generated by assess cumulative statistics for each of the training sets.

testing_summary_statistics

Mean and standard deviations for test statistics generated by assess cumulative statistics for each of the testing sets.

training_statistics

sboost sboost_assessment cumulative statistics objects used to generate training_statistics.

testing_statistics

sboost sboost_assessment cumulative statistics objects used to generate testing_statistics.

classifier_list

sboost sboost_classifier objects created from training sets.

outcomes

Shows which outcome was considered as positive and which negative.

k_fold

number of testing and training sets used in the validation.

call

Shows the parameters that were used for validation.

See Also

sboost documentation.

Examples

# malware
validate(malware[-1], malware[1], iterations = 5, k_fold = 3, positive = 1)

# mushrooms
validate(mushrooms[-1], mushrooms[1], iterations = 5, k_fold = 3, positive = "p")

sboost documentation built on May 28, 2022, 1:12 a.m.