[Subgroup-commits] r71 - in pkg/rsubgroup: . R inst/java java man tests
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Mon Feb 22 23:38:28 CET 2021
Author: atzmueller
Date: 2021-02-22 23:38:27 +0100 (Mon, 22 Feb 2021)
New Revision: 71
Modified:
pkg/rsubgroup/DESCRIPTION
pkg/rsubgroup/NEWS
pkg/rsubgroup/R/classes.R
pkg/rsubgroup/R/subgroup.R
pkg/rsubgroup/inst/java/subgroup.jar
pkg/rsubgroup/java/readme-subgroup-jar.txt
pkg/rsubgroup/man/SDTaskConfig-class.Rd
pkg/rsubgroup/tests/test.R
Log:
Changes in version 1.1 (2021-02-22)
===================================
* provide automatic discretization options of VIKAMINE kernel for
numeric attributes, they are internally discretized
SDTaskConfig provides new options.
defaults: discretize = TRUE, nbins = 3
* Improved/extended tests for this.
Modified: pkg/rsubgroup/DESCRIPTION
===================================================================
--- pkg/rsubgroup/DESCRIPTION 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/DESCRIPTION 2021-02-22 22:38:27 UTC (rev 71)
@@ -1,8 +1,8 @@
Package: rsubgroup
Type: Package
Title: Subgroup Discovery and Analytics
-Version: 1.0
-Date: 2020-04-20
+Version: 1.1
+Date: 2021-02-22
Author: Martin Atzmueller
Maintainer: Martin Atzmueller <martin at atzmueller.net>
Description: A collection of efficient and effective tools and
@@ -15,4 +15,4 @@
Depends: R (>= 2.6.0), methods, rJava (>= 0.6-3), foreign (>= 0.8-40)
SystemRequirements: Java (>= 8)
Collate: 'AAAonLoad.R' 'randomSeed.R' 'classes.R' 'subgroup.R'
-URL: http://www.rsubgroup.org
\ No newline at end of file
+URL: https://rsubgroup.org
\ No newline at end of file
Modified: pkg/rsubgroup/NEWS
===================================================================
--- pkg/rsubgroup/NEWS 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/NEWS 2021-02-22 22:38:27 UTC (rev 71)
@@ -3,6 +3,15 @@
For a detailed list of changes, see the svn commit history at
svn://r-forge.r-project.org/svnroot/subgroup/
+Changes in version 1.1 (2021-02-22)
+===================================
+* provide automatic discretization options of VIKAMINE kernel for
+ numeric attributes, they are internally discretized
+ SDTaskConfig provides new options.
+ defaults: discretize = TRUE, nbins = 3
+* Improved/extended tests for this.
+
+
Changes in version 1.0 (2020-04-20)
===================================
* internal enhancements in subgroup.jar, i.e., the VIKAMINE kernel library,
@@ -9,11 +18,13 @@
e.g. according to better error messages relating to the R connection.
* Improved documentation and examples.
+
Changes in version 0.9 (2020-03-04)
===================================
* internal enhancements in subgroup.jar, i.e., the VIKAMINE kernel library
* rsubgroup requires >= Java 8 (i.e., >= java.version 1.8)
+
Changes in version 0.8 (2019-05-23)
===================================
* Improvements
@@ -26,6 +37,7 @@
* Bug fixes.
* fixed bug in automatic discretization used in rsubgroup VIKAMINE kernel
+
Changes in version 0.7 (2015-07-01)
===================================
* Improvements
@@ -55,7 +67,6 @@
of two few selectors in subgroup discovery methods
-
Changes in version 0.6 (2014-09-10)
===================================
* Improvements:
Modified: pkg/rsubgroup/R/classes.R
===================================================================
--- pkg/rsubgroup/R/classes.R 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/R/classes.R 2021-02-22 22:38:27 UTC (rev 71)
@@ -44,12 +44,15 @@
relfilter = "logical",
postfilter = ".vectorOrCharacter",
attributes = ".vectorOrNull",
- parfilter = "numeric"
+ parfilter = "numeric",
+ discretize = "logical",
+ nbins = "numeric"
),
prototype(qf="ps", method="sdmap", k = as.integer(20),
minqual = as.integer(0), minsize = as.integer(0), mintp = as.integer(0),
maxlen = as.integer(7), nodefaults = FALSE, relfilter = FALSE,
- postfilter = "", parfilter = 0.05, attributes = NULL)
+ postfilter = "", parfilter = 0.05, discretize = TRUE, nbins = 3,
+ attributes = NULL)
)
SDTaskConfig <- function(...){
Modified: pkg/rsubgroup/R/subgroup.R
===================================================================
--- pkg/rsubgroup/R/subgroup.R 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/R/subgroup.R 2021-02-22 22:38:27 UTC (rev 71)
@@ -107,14 +107,23 @@
if (!is.na(config at parfilter)) {
J(task, "setPostFilterParameter", config at parfilter)
}
+
+ doDiscretize = config at discretize
+ if (is.na(config at nbins)) {
+ doDiscretize = FALSE
+ }
+ intBins = as.integer(config at nbins)
+
+
if (is.null(config at attributes)) {
attributesArrayObject <- .GetAllAttributesAsJArray(ontology = ontology)
- J(task, "setAttributes", attributesArrayObject)
+ J(task, "setAttributes", attributesArrayObject, doDiscretize, intBins)
} else if ((!is.null(config at attributes)) && (length(config at attributes) > 0)) {
- J(task, "setAttributes", .jarray(config at attributes))
+ J(task, "setAttributes", .jarray(config at attributes), doDiscretize, intBins)
} else {
- J(task, "setAttributes", .jarray(character(0)))
+ J(task, "setAttributes", .jarray(character(0)), doDiscretize, intBins)
}
+
return(task)
}
Modified: pkg/rsubgroup/inst/java/subgroup.jar
===================================================================
(Binary files differ)
Modified: pkg/rsubgroup/java/readme-subgroup-jar.txt
===================================================================
--- pkg/rsubgroup/java/readme-subgroup-jar.txt 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/java/readme-subgroup-jar.txt 2021-02-22 22:38:27 UTC (rev 71)
@@ -4,7 +4,7 @@
VIKAMINE is licensed under LGPL >= 2.1.
Copyright (C) 2003-2008 by Martin Atzmueller, and contributors.
-Copyright (C) 2008-2020 by Martin Atzmueller, Florian Lemmerich, and contributors.
+Copyright (C) 2008-2021 by Martin Atzmueller, Florian Lemmerich, and contributors.
The source code can be obtained at www.vikamine.org, and the SVN repository
sourceforge.net/p/vikamine/code/HEAD/tree/trunk/ => org.vikamine.kernel
Modified: pkg/rsubgroup/man/SDTaskConfig-class.Rd
===================================================================
--- pkg/rsubgroup/man/SDTaskConfig-class.Rd 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/man/SDTaskConfig-class.Rd 2021-02-22 22:38:27 UTC (rev 71)
@@ -17,6 +17,11 @@
\item{\code{attributes}:}{The list of attributes to consider for mining.
Either a vector of attribute names, or NULL (the default),
which includes all attributes.}
+ \item{\code{discretize}:}{Boolean, indicating whether to (automatically)
+ discretize numeric attributes (default \code{discretize=TRUE}. Depends on
+ parameter nbins. Either creates distinct values, if their number in the
+ dataset is <= nbins, or applies equal-frequency discretization for the
+ respective numeric attribute.}
\item{\code{method}:}{A mining method; one of
Beam-Search \code{beam},
BSD \code{bsd},
@@ -24,6 +29,8 @@
SD-Map enabling internal disjunctions \code{sdmap-dis}.
The default is \code{method = "sdmap"}.
}
+ \item{\code{nbins}:}{Specifies the number of bins to be used when
+ discretizing numeric attributes (see \code{discretize} above).}
\item{\code{qf}:}{A quality function; one of:
Adjusted Residuals \code{ares},
Binomial Test \code{bin},
Modified: pkg/rsubgroup/tests/test.R
===================================================================
--- pkg/rsubgroup/tests/test.R 2020-04-20 07:41:18 UTC (rev 70)
+++ pkg/rsubgroup/tests/test.R 2021-02-22 22:38:27 UTC (rev 71)
@@ -23,5 +23,15 @@
data(credit.data)
-patterns.from.data.table <- DiscoverSubgroups(credit.data, as.target("class", "bad"))
+patterns.from.data.table <- DiscoverSubgroups(
+ credit.data,
+ as.target("class", "bad"),
+ new("SDTaskConfig", discretize = FALSE))
+result.data.frame <- ToDataFrame(patterns.from.data.table)
+
+patterns.from.data.table <- DiscoverSubgroups(
+ credit.data,
+ as.target("class", "bad"),
+ new("SDTaskConfig", discretize = TRUE, nbins = 3,
+ attributes = c("checking_status", "duration", "credit_amount")))
result.data.frame <- ToDataFrame(patterns.from.data.table)
\ No newline at end of file
More information about the Subgroup-commits
mailing list