The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

varPro 3.1.0

Breaking changes

• importance() is now a true S3 generic rather than an alias-style front end.
• partial.ivarpro() has been replaced by plot.ivarpro().
• The supported user-facing interfaces for fitted objects are now the corresponding S3 generics, such as importance(), predict(), and plot().

S3 interface cleanup

• Registered importance() methods for "varpro" and "uvarpro" objects.
• Registered plot() methods for "ivarpro" and "partialpro" objects.
• Continued support for class-specific predict() methods through standard S3 dispatch for "varpro", "uvarpro", "ivarpro", and "isopro" objects.

Documentation

• Help topics retain dotted method names such as plot.ivarpro, plot.partialpro, predict.ivarpro, predict.varpro, predict.uvarpro, and predict.isopro so that method pages remain easy to find in the reference manual and via ?topic.
• Usage sections were updated to show S3 method signatures consistently, for example \method{plot}{ivarpro}(x, ...) and \method{predict}{ivarpro}(object, ...).
• Examples were updated to use the generic forms plot(x, ...), predict(object, ...), and importance(object).
• The iVarPro plotting documentation now uses data for the original feature matrix and documents target explicitly for multivariate and multiclass outputs.

Migration notes

• Replace calls of the form partial.ivarpro(iv, var = ...) with plot(iv, var = ...).
• Prefer importance(fit) over direct calls to importance.varpro(fit).
• Prefer predict(fit, ...) over direct calls to predict.class(fit, ...).

varPro 3.0.0

Improvements

• Refactored varpro.strength() to reduce R-side post-processing overhead after the native varProStrength call, improving performance on large forests and large membership reconstructions.
• Improved scalability and stability of varpro.strength(..., membership = TRUE) for very large analyses.
• For RHF grow objects, varpro.strength() now uses the integrated hazard exposure values stored on the fitted object (int.haz.oob) as the default working response when available.
• Internal cleanup of native-output decoding and membership reconstruction logic.

Bug fixes

• Fixed a failure that could occur on very large analyses when rebuilding membership lists in R after native execution, which could previously surface as an integer-overflow warning from cumsum() followed by a downstream missing-value error in membership reconstruction.

varPro 2.1.0

• Major refactoring and enhancement to functions downstream from the entry varpro() function.

varPro 2.0.0

• Improved ivarPro.
• Refactored code to improve speed.
• Eliminated or replaced mclapply() with PSOCK-based parallel execution, improving Windows compatibility.

varPro 1.0.1

• CRAN compliance fixes.

varPro 1.0.0

• Initial release.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.