Skip to contents

Changelog

Source: NEWS.md

arulesCBA 1.2.10 (unreleased)

  • Modernized and added tests.
  • Corrected spelling and grammar.

arulesCBA 1.2.9 (2025-11-04)

CRAN release: 2025-11-14

  • Fixed partial argument matches.
  • Fixed broken tests.

arulesCBA 1.2.8 (2025-07-16)

CRAN release: 2025-07-17

  • Fixed the bug report link (reported by Kurt Hornik).
  • Fixed a rowSums bug in pruneCBA_M1.

arulesCBA 1.2.7 (2024-05-15)

CRAN release: 2024-05-15

  • Fixed missing package anchors in the help pages.

arulesCBA 1.2.6 (2024-04-15)

CRAN release: 2024-04-16

  • RCAR: Classifiers with a single rule now work.
  • prepareTransactions gained the logical2factor parameter.
  • Updated man pages.

arulesCBA 1.2.5 (2022-08-19)

CRAN release: 2022-08-19

  • Improved formula interface code.
  • Changes for Matrix 1.4-2.

arulesCBA 1.2.4 (2022-05-30)

CRAN release: 2022-05-30

  • LUCS_KDD algorithms now work in Java headless mode.
  • The rules() function is now defunct. Rules are extracted using $rules because arules has a rules() function.
  • Improved package tests.
  • NAMESPACE is now managed by roxygen.
  • Improved man pages.
  • Added the classes() helper function.
  • CBA_ruleset now requires a default class.

arulesCBA 1.2.3 (2022-05-27)

CRAN release: 2022-05-27

  • LUCS_KDD JARs are now bundled, fixing compilation issues.
  • Fixed RCAR for the zero-rule case.

arulesCBA 1.2.1 (2021-11-20)

CRAN release: 2021-11-20

  • mineCARs now uses by default minimum LHS-support (via parameter originalSupport = FALSE).
  • the CBA_ruleset function is now used consistently as the constructor for CBA objects.
  • added transactionCoverage.
  • added uncoveredClassExamples.
  • added uncoveredMajorityClass.
  • added transactions2DF to convert transactions to a data.frame.
  • RCAR is now faster (does not run glmnet again for the chosen lambda) and returns the whole regularization path.
  • prepareTransactions now automatically adds a negative class item if needed.
  • moved the experimental algorithms wCBA and bCBA to Work.
  • R/Weka-based classifiers have now a default class.

arulesCBA 1.2.0 (2020-04-19)

CRAN release: 2020-04-20

  • Version 1.2.0 has a major interface cleanup. This might require some change in existing code.
  • The classifiers now use as the default a min. confidence of .5 and maxlen of 5 (max. rule length).
  • CBA now includes a default rule in the rule base.
  • added prepareTransactions to discretize and convert a data.frame into transactions.
  • added response to convert class items to class labels (factors).
  • added majorityClass.
  • added FOIL.
  • added RIPPER C4.5, and PART (via RWeka).
  • added PRM, CPAR and CMAR (via LUCS-KDD Software Library).
  • added datasets Mushroom and Lymphography.

arulesCBA 1.1.6 (2020-01-05)

CRAN release: 2020-01-08

  • maintenance release.

arulesCBA 1.1.5 (2019-11-05)

CRAN release: 2019-11-12

  • added RCAR (by Tyler Giallanza).
  • The interface for CBA() was updated.
  • CBA now complains if no rules are found.
  • CBA has now also M1 pruning.
  • mineCARs now uses … to construct the parameters for apriori().

arulesCBA 1.1.4 (2018-12-04)

CRAN release: 2018-12-16

  • discretizeDF.supervised method mdlp now produces a better error message if it fails.
  • cleaned up the predict code to improve speed.
  • mineCARs has now a balanced support option.
  • convenience function classFrequency added.

arulesCBA 1.1.3-1 (2018-04-23)

CRAN release: 2018-04-23

  • added new function discretizeDF.supervised for supervised discretization.
  • added new convenience function mineCARs to mine class association rules.
  • the formula interface now parses the right-hand side to restrict the predictors used.