Script 'mail_helper' called by obssrc
Hello community,
here is the log from the commit of package octave-forge-nan for
openSUSE:Factory checked in at 2021-03-17 20:16:43
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/octave-forge-nan (Old)
and /work/SRC/openSUSE:Factory/.octave-forge-nan.new.2401 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "octave-forge-nan"
Wed Mar 17 20:16:43 2021 rev:12 rq:879588 version:3.5.3
Changes:
--------
--- /work/SRC/openSUSE:Factory/octave-forge-nan/octave-forge-nan.changes
2020-12-04 21:27:56.902078371 +0100
+++
/work/SRC/openSUSE:Factory/.octave-forge-nan.new.2401/octave-forge-nan.changes
2021-03-17 20:20:04.859327858 +0100
@@ -1,0 +2,8 @@
+Sat Mar 13 13:56:09 UTC 2021 - Atri Bhattacharya <[email protected]>
+
+- Update to version 3.5.3
+ * kappa: Youden index (YI), and SSE as return value
+ * roc: add maxYI as output value
+ * naninsttest: check ttest for NaN handling
+
+-------------------------------------------------------------------
Old:
----
nan-3.5.2.tar.gz
New:
----
nan-3.5.3.tar.gz
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ octave-forge-nan.spec ++++++
--- /var/tmp/diff_new_pack.EhoqwO/_old 2021-03-17 20:20:05.315328482 +0100
+++ /var/tmp/diff_new_pack.EhoqwO/_new 2021-03-17 20:20:05.319328487 +0100
@@ -1,7 +1,7 @@
#
# spec file for package octave-forge-nan
#
-# Copyright (c) 2020 SUSE LLC
+# Copyright (c) 2021 SUSE LLC
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
@@ -18,7 +18,7 @@
%define octpkg nan
Name: octave-forge-%{octpkg}
-Version: 3.5.2
+Version: 3.5.3
Release: 0
Summary: A statistics and machine learning toolbox
License: GPL-3.0-or-later
++++++ nan-3.5.2.tar.gz -> nan-3.5.3.tar.gz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/DESCRIPTION new/nan-3.5.3/DESCRIPTION
--- old/nan-3.5.2/DESCRIPTION 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/DESCRIPTION 2021-02-15 07:41:05.000000000 +0100
@@ -1,6 +1,6 @@
Name: NaN
-Version: 3.5.2
-Date: 2020-10-31
+Version: 3.5.3
+Date: 2021-02-15
Author: Alois Schl??gl <[email protected]>
Maintainer: Alois Schl??gl
Title: The NaN-toolbox
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/NEWS new/nan-3.5.3/NEWS
--- old/nan-3.5.2/NEWS 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/NEWS 2021-02-15 07:41:05.000000000 +0100
@@ -1,3 +1,9 @@
+2021-02-15: Release of NaN-toolbox 3.5.3
+
+* kappa: Youden index (YI), and SSE as return value
+* roc: add maxYI as output value
+* naninsttest: check ttest for NaN handling
+
2020-10-31: Release of NaN-toolbox 3.5.2
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/doc/README.TXT new/nan-3.5.3/doc/README.TXT
--- old/nan-3.5.2/doc/README.TXT 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/doc/README.TXT 2021-02-15 07:41:05.000000000 +0100
@@ -1,6 +1,6 @@
NaN-Tb: A statistics toolbox
------------------------------------------------------------
-Copyright (C) 2000-2005,2009,2010,2011,2014 Alois Schloegl
<[email protected]>
+Copyright (C) 2000-2021 Alois Schl??gl <[email protected]>
FEATURES of the NaN-tb:
@@ -18,7 +18,7 @@
- fixes known bugs
- compatible with Matlab and Octave
- easy to use
- - The toolbox is tested with Octave 3.x and Matlab 7.x
+ - The toolbox is tested with Octave 4.4+ and Matlab 7.x
Currently are implemented:
@@ -121,7 +121,7 @@
KAPPA performance evaluation
TRAIN_LDA_SPARSE utility function
FSS feature subset selection and feature ranking
- CAT2BIN converts categorial to binary data
+ CAT2BIN converts categorical to binary data
SVMTRAIN_MEX libSVM-training algorithm
ROW_COL_DELETION heuristic to select rows and columns to remove missing
values
@@ -279,8 +279,7 @@
Run NANINSTTEST again to check the stability of the compiled SUMSKIPNAN.
- $Id$
- Copyright (C) 2000-2005,2009,2010,2011,2014 by Alois Schloegl
<[email protected]>
+ Copyright (C) 2000-2021 by Alois Schl??gl <[email protected]>
http://pub.ist.ac.at/~schloegl/matlab/NaN/
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/inst/cat2bin.m new/nan-3.5.3/inst/cat2bin.m
--- old/nan-3.5.2/inst/cat2bin.m 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/inst/cat2bin.m 2021-02-15 07:41:05.000000000 +0100
@@ -1,12 +1,12 @@
function [B,BLab]=cat2bin(D, Label, MODE)
-% CAT2BIN converts categorial into binary data
+% CAT2BIN converts categorical into binary data
% each category of each column in D is converted into a logical column
%
% B = cat2bin(C);
% [B,BinLabel] = cat2bin(C,Label);
% [B,BinLabel] = cat2bin(C,Label,MODE)
%
-% C categorial data
+% C categorical data
% B binary data
% Label description of each column in C
% BinLabel description of each column in B
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/inst/kappa.m new/nan-3.5.3/inst/kappa.m
--- old/nan-3.5.2/inst/kappa.m 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/inst/kappa.m 2021-02-15 07:41:05.000000000 +0100
@@ -21,8 +21,8 @@
% MI Mutual information or transfer information (in [bits])
% X is a struct containing all the fields above
% For two classes, a number of additional summary statistics including
-% TPR, FPR, FDR, PPV, NPF, F1, dprime, Matthews Correlation
coefficient (MCC) or
-% Phi coefficient (PHI=MCC), Specificity and Sensitivity
+% TPR, FPR, FDR, PPV, NPF, F1, dprime, Matthews Correlation
coefficient (MCC) or
+% Phi coefficient (PHI=MCC), Specificity and Sensitivity, Youden index
(YI)
% are provided. Note, the positive category must the larger label (in d
and c), otherwise
% the confusion matrix becomes transposed and the summary statistics are
messed up.
%
@@ -37,7 +37,7 @@
% [5] http://ourworld.compuserve.com/homepages/jsuebersax/kappa.htm
% [6] http://en.wikipedia.org/wiki/Receiver_operating_characteristic
-% Copyright (c) 1997-2020 by Alois Schloegl <[email protected]>
+% Copyright (c) 1997-2021 by Alois Schloegl <[email protected]>
% This function is part of the NaN-toolbox
% http://pub.ist.ac.at/~schloegl/matlab/NaN/
%
@@ -158,11 +158,12 @@
X.ACC = p0;
X.sACC = SA;
X.MI = R;
+X.SSE = sum(X.data(:))-trace(X.data);
X.datatype = 'confusion';
if length(H)==2,
% see http://en.wikipedia.org/wiki/Receiver_operating_characteristic
- % Note that the confusion matrix used here is has positive values in
+ % Note that the confusion matrix used here uses more positive values in
% the 2nd row and column, moreover the true values are indicated by
% rows (transposed). Thus, in summary H(1,1) and H(2,2) are exchanged
% as compared to the wikipedia article.
@@ -183,6 +184,7 @@
X.Specificity = 1 - X.FPR;
X.Precision = X.PPV;
X.dprime = norminv(X.TPR) - norminv(X.FDR);
+ X.YI = X.Sensitivity + X.Specificity - 1; % Youden Index
% statistical significance test of Matthews' correlation coefficient
NN = sum(H(:));
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/inst/naninsttest.m
new/nan-3.5.3/inst/naninsttest.m
--- old/nan-3.5.2/inst/naninsttest.m 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/inst/naninsttest.m 2021-02-15 07:41:05.000000000 +0100
@@ -118,8 +118,7 @@
if exist('nanstd','file'),
r(33,k)=k*(~isnan(nanstd(0)));
end;
-
- %%% check mex files
+
try
histo_mex([1:5]');
r(34,k)=0;
@@ -144,6 +143,10 @@
if ~exist('train','file'),
r(38,k)=k;
end;
+
+ if exist('ttest','file'),
+ r(39,k)=ttest([x,x,x],10);
+ end;
end;
% check if result is correct
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/inst/roc.m new/nan-3.5.3/inst/roc.m
--- old/nan-3.5.2/inst/roc.m 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/inst/roc.m 2021-02-15 07:41:05.000000000 +0100
@@ -66,7 +66,7 @@
% return the optimal threshold for the respective measure.
% RES.H_kappa: confusion matrix when Threshold of maximum Kappa is applied.
% RES.H_{yi,acc,kappa,mcc,mi,f1,phi}: confusion matrix when threshold of
-% optimum {...} is applied.
+% optimum {...} is applied. Its structure is [TN, FN; FP; TP].
%
% see also: AUC, PLOT, ROC
%
@@ -81,7 +81,7 @@
% (Eds.) G. Dornhege, J.R. Millan, T. Hinterberger, D.J. McFarland,
K.-R.M??ller;
% Towards Brain-Computer Interfacing, MIT Press, 2007, p.327-342
-% Copyright (c) 1997-2019 Alois Schloegl <[email protected]>
+% Copyright (c) 1997-2021 Alois Schloegl <[email protected]>
% This is part of the BIOSIG-toolbox http://biosig.sf.net/
%
% This library is free software; you can redistribute it and/or
@@ -202,9 +202,9 @@
%%% compute Cohen's kappa coefficient
N = size(d,1);
-%H = [TP,FN;FP,TN];
-p_i = [TP+FP,FN+TN];%sum(H,1);
-pi_ = [TP+FN,FP+TN];%sum(H,2)';
+% H =[TN, FN; FP, TP]
+p_i = [TP+FP, FN+TN];
+pi_ = [TP+FN, FP+TN];
pe = sum(p_i.*pi_,2)/(N*N); % estimate of change agreement
kap = (ACC - pe) ./ (1 - pe);
mcc = (TP .* TN - FN .* FP) ./ sqrt(prod( [p_i, pi_], 2));
@@ -274,7 +274,7 @@
% Cohen's kappa is best tested for borderline cases, like, few
% samples only, or when multiple options are possible.
% others are not that sophisticated.
-[tmp,ix] = max(SEN+SPEC-1);
+[RES.maxYI,ix] = max(SEN+SPEC-1);
ix = min(ix,length(D));
RES.THRESHOLD.maxYI = D(ix);
RES.THRESHOLD.maxYIix = ix;
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/src/Makefile.in
new/nan-3.5.3/src/Makefile.in
--- old/nan-3.5.2/src/Makefile.in 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/src/Makefile.in 2021-02-15 07:41:05.000000000 +0100
@@ -125,7 +125,7 @@
# -DMATLAB_DEFAULT_RELEASE=R2018a: Interleaved Complex
MATLABMEX += -DMATLAB_DEFAULT_RELEASE=R2017b
-CFLAGS := -fexceptions -fPIC -fno-omit-frame-pointer -pthread
+CFLAGS += -fexceptions -fPIC -fno-omit-frame-pointer -pthread
COPTIMFLAGS := -O -DNDEBUG
CDEBUGFLAGS := -g
INCLUDE := -I"$(MWROOT)/extern/include" -I"$(MWROOT)/simulink/include"
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/src/configure.ac
new/nan-3.5.3/src/configure.ac
--- old/nan-3.5.2/src/configure.ac 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/src/configure.ac 2021-02-15 07:41:05.000000000 +0100
@@ -2,7 +2,7 @@
# Process this file with autoconf to produce a configure script.
AC_PREREQ([2.69])
-AC_INIT([nan-toolbox], [3.5.0], [[email protected]])
+AC_INIT([nan-toolbox], [3.5.3], [[email protected]])
AC_CONFIG_SRCDIR([train.c])
AC_CONFIG_HEADERS([config.h])
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/nan-3.5.2/src/linear.cpp new/nan-3.5.3/src/linear.cpp
--- old/nan-3.5.2/src/linear.cpp 2020-10-31 17:44:32.000000000 +0100
+++ new/nan-3.5.3/src/linear.cpp 2021-02-15 07:41:05.000000000 +0100
@@ -65,7 +65,7 @@
fputs(s,stdout);
fflush(stdout);
}
-static void print_null(const char *s) {}
+static void print_null(const char*) {}
static void (*liblinear_print_string) (const char *) = &print_string_stdout;
@@ -3073,7 +3073,7 @@
free(param->init_sol);
}
-const char *check_parameter(const problem *prob, const parameter *param)
+const char *check_parameter(const problem*, const parameter *param)
{
if(param->eps <= 0)
return "eps <= 0";
