Changelog • prova

Prova v2.3.0

Introduced the much faster mutualinfoF() for variates with finite domains.
Introduced the function exputility() for the calculation of expected utilities and their revisability, together with plot() and print() methods.
Changed the name of internal S3 classes to avoid clashes with other packages.
Improved plot labels.
Updated and corrected documentation.
Updated introductory vignette.
Simplified omission of arguments like Y =, X =, K =.

The argument learnt =, common to many functions, has been changed to K = for brevity. Previous “learnt” objects can still be used with the K = argument.
The functions flexiplot() and plotquantiles() are replaced by the single function pplot(); argument type = 'qx' reproduces the usage of plotquantiles().
Changed the display style of the hist() methods.
The function mutualinfo() now outputs also quantile accuracy.
Fixed a bug that prevented use of pre-existing parallel cluster.
print() now prints correctly “probability” objects generated by qPr().
Metadata object meta_penguins for the R dataset datasets::penguins is now included in the package.
Included a minimal example in the README.
Rewrite of some internal code.

The package does not require the package ‘extraDistr’ any longer.
Internal changes to some functions.
Improved and more consistent digit-rounding system for print() output of probabilities.
Fixed some bugs in the use of Pr() with base-rate correction (non-null argument ‘priorY’).
Changed the class of mutual information objects to “mi”.
Introduced a print() method for mutual-information objects.
Improved print() display for probability and mutual-information objects.
Improved plot.probability(); singular probability (e.g. at censored values) are now displayed on a separate scale.
Changed the behaviour of the TRUE value of argument parallel =: now it queries the value of the user’s option “cl.cores”, via getOption(), or uses 2 if that value is NULL (this is the same behaviour as in R’s documentation for the clusterApply functions).
Updated documentation.
Re-tested some functions.
Cleaned some code.

The function mutualinfo() now only outputs the mutual information (and not conditional entropies or entropies), but it also outputs the “revisability” of the values in view of a much larger dataset.
New functions plot.MI() and print.MI() for plotting and printing mutual information and its revisability.
Slight changes in plotting and printing outputs.
The vignette about mutual information now has an additional section about the revisability of mutual information.
Small internal changes in how synthetic datapoints are generated.
Corrected a bug affecting computation of probabilities for censored, non-rounded variates.
Corrected a bug affecting computation of cumulative probabilities (‘tails =’ argument) of ordinal variates.
Corrected typos in documentation.

CRAN release: 2026-07-16

First CRAN release
Improved documentation, also of internal functions.
Introduced argument verbose = in several function, so as to show information to console only if the user so desires. This argument is FALSE for all functions except learn().
Added example of imputation in vignette.
Rewritten README with description of the package’s main features.
Removed unused functions.
Cleaned up code.

Initial CRAN submission.
Introduced the print() method for probability objects.
Slightly modified output of Pr() and related functions.
Added references.
Modified vignettes.
Added examples to all functions visible to the user.
Fixed some bugs (in particular a bug that would allow the input of a non-existent nominal value giving erroneous probabilities).
Corrected typos.

Renamed the package from inferno to Prova. It turns out, unsurprisingly, that the name “inferno” was already in use for several inference-related software packages of various kinds.