[Subgroup-commits] r63 - in pkg/rsubgroup: . R inst/java man

[noreply at r-forge.r-project.org]

Author: atzmueller
Date: 2015-07-01 21:51:32 +0200 (Wed, 01 Jul 2015)
New Revision: 63

Modified:
   pkg/rsubgroup/DESCRIPTION
   pkg/rsubgroup/NEWS
   pkg/rsubgroup/R/subgroup.R
   pkg/rsubgroup/inst/java/subgroup.jar
   pkg/rsubgroup/man/SDTaskConfig-class.Rd
   pkg/rsubgroup/man/subgroup-package.Rd
Log:
  * Implement/enable new quality function (Adjusted residuals, cf. Agresti 2007)
  ==> qf="ares"
  * For a binary target variable, the resulting patterns now also store the
  chi-squared value comparing subgroup and population w.r.t. the target in the
  parameters field.
  * ToDataFrame shows the chi-squared value for a binary target.

Modified: pkg/rsubgroup/DESCRIPTION
===================================================================
--- pkg/rsubgroup/DESCRIPTION	2015-06-19 07:12:54 UTC (rev 62)
+++ pkg/rsubgroup/DESCRIPTION	2015-07-01 19:51:32 UTC (rev 63)
@@ -2,7 +2,7 @@
 Type: Package
 Title: Subgroup Discovery and Analytics
 Version: 0.7
-Date: 2015-06-19
+Date: 2015-07-01
 Author: Martin Atzmueller
 Maintainer: Martin Atzmueller <martin at atzmueller.net>
 Description: A collection of efficient and effective tools and

Modified: pkg/rsubgroup/NEWS
===================================================================
--- pkg/rsubgroup/NEWS	2015-06-19 07:12:54 UTC (rev 62)
+++ pkg/rsubgroup/NEWS	2015-07-01 19:51:32 UTC (rev 63)
@@ -3,7 +3,7 @@
 For a detailed list of changes, see the svn commit history at
 svn://r-forge.r-project.org/svnroot/subgroup/
 
-Changes in version 0.7 (2015-06-xx)
+Changes in version 0.7 (2015-07-xx)
 ===================================
 * Improvements
   * document setting Java heap space before loading the rsubgroup library.
@@ -17,7 +17,13 @@
   function, a match of a pattern and a data instance can be checked now.
   * In SDTaskConfig, postfilter can be a single filter or a vector of filters,
   that are then applied in order on the results. This allows e.g., the combination
-  of minimal improvement filtering with weighted covering post-processing. 
+  of minimal improvement filtering with weighted covering post-processing.
+  * Implement/enable new quality function (Adjusted residuals, cf. Agresti 2007)
+  ==> qf="ares"
+  * For a binary target variable, the resulting patterns now also store the
+  chi-squared value comparing subgroup and population w.r.t. the target in the
+  parameters field.
+  * ToDataFrame shows the chi-squared value for a binary target.
 
 * Bug fixes:
   * fix providing attributes=NULL (i.e., automatically include all attributes)

Modified: pkg/rsubgroup/R/subgroup.R
===================================================================
--- pkg/rsubgroup/R/subgroup.R	2015-06-19 07:12:54 UTC (rev 62)
+++ pkg/rsubgroup/R/subgroup.R	2015-07-01 19:51:32 UTC (rev 63)
@@ -138,7 +138,8 @@
     size <- J(J(sg, "getStatistics"), "getSubgroupSize")
     p <- J(J(sg, "getStatistics"), "getP")
     p0 <- J(J(sg, "getStatistics"), "getP0")
-    return(list(p = p, p0 = p0, size = size))
+    chi2 <- J("org.vikamine.kernel.subgroup.SGUtils")$calculateChi2OfSubgroup(J(sg, "getStatistics"))
+    return(list(p = p, p0 = p0, chi2=chi2, size = size))
   } else if (J(target, "isNumeric")) {
     size <- J(J(sg, "getStatistics"), "getSubgroupSize")
     mean <- J(J(sg, "getStatistics"), "getSGMean")
@@ -263,6 +264,9 @@
   sizes <- list()
   length(sizes) <- length(patterns)
   ps <- list()
+  length(ps) <- length(patterns)
+  chi2 <- list()
+  length(chi2) <- length(patterns)
   
   i <- 1
   for (pattern in patterns) {
@@ -274,6 +278,7 @@
       isNumeric <- TRUE
     } else {
       ps[i] <- .FormatDoubleSignificantDigits(pattern at parameters$p, ndigits)
+      chi2[i] <- .FormatDoubleSignificantDigits(pattern at parameters$chi2, ndigits)
       isNumeric <- FALSE
     }
     i <- i + 1
@@ -289,6 +294,7 @@
         quality=as.vector(qualities, "numeric"),
         p=as.vector(ps, "numeric"), 
         size=as.vector(sizes, "numeric"),
+        chi2=as.vector(chi2, "numeric"),
         description=as.vector(descriptions, "character"))
   }
   return(dataframe)

Modified: pkg/rsubgroup/inst/java/subgroup.jar
===================================================================
(Binary files differ)

Modified: pkg/rsubgroup/man/SDTaskConfig-class.Rd
===================================================================
--- pkg/rsubgroup/man/SDTaskConfig-class.Rd	2015-06-19 07:12:54 UTC (rev 62)
+++ pkg/rsubgroup/man/SDTaskConfig-class.Rd	2015-07-01 19:51:32 UTC (rev 63)
@@ -15,11 +15,12 @@
 \section{Slots}{
   \describe{
     \item{\code{qf}:}{A quality function; one of:
-	Binomial-Test \code{bin},
-	Chi-Square-Test \code{chi2},
+    Adjusted Residuals \code{ares},
+	Binomial Test \code{bin},
+	Chi-Square Test \code{chi2},
+	Gain \code{gain},
 	Lift \code{lift},
 	Piatetsky-Shapiro \code{ps},
-	Gain \code{gain},
 	Relative Gain \code{relgain},
 	Weighted Relative Accuracy \code{wracc}.
 	The default is \code{qf = "ps"}.

Modified: pkg/rsubgroup/man/subgroup-package.Rd
===================================================================
--- pkg/rsubgroup/man/subgroup-package.Rd	2015-06-19 07:12:54 UTC (rev 62)
+++ pkg/rsubgroup/man/subgroup-package.Rd	2015-07-01 19:51:32 UTC (rev 63)
@@ -29,7 +29,7 @@
 Package: \tab rsubgroup\cr
 Type: \tab Package\cr
 Version: \tab 0.7\cr
-Date: \tab 2015-06-xx\cr
+Date: \tab 2015-07-xx\cr
 License: \tab GPL (>= 3)\cr
 LazyLoad: \tab yes\cr
 }