Date: Fri, 28 Jul 2006 07:06:48 +0800 (CST) From: Gea-Suan Lin <gslin@gslin.org> To: FreeBSD-gnats-submit@FreeBSD.org Cc: gslin@gslin.org Subject: ports/100944: [NEW PORT] science/svmlight: An implementation of Support Vector Machines (SVMs) in C Message-ID: <20060727230648.DAE7E1CE@netnews.NCTU.edu.tw> Resent-Message-ID: <200607272310.k6RNAGNE089130@freefall.freebsd.org>
next in thread | raw e-mail | index | archive | help
>Number: 100944 >Category: ports >Synopsis: [NEW PORT] science/svmlight: An implementation of Support Vector Machines (SVMs) in C >Confidential: no >Severity: non-critical >Priority: low >Responsible: freebsd-ports-bugs >State: open >Quarter: >Keywords: >Date-Required: >Class: change-request >Submitter-Id: current-users >Arrival-Date: Thu Jul 27 23:10:16 GMT 2006 >Closed-Date: >Last-Modified: >Originator: Gea-Suan Lin >Release: FreeBSD 6.1-RELEASE i386 >Organization: >Environment: System: FreeBSD netnews.NCTU.edu.tw 6.1-RELEASE FreeBSD 6.1-RELEASE #0: Sat May 13 03:43:48 CST 2006 >Description: SVMlight is an implementation of Vapnik's Support Vector Machine [Vapnik, 1995] for the problem of pattern recognition, for the problem of regression, and for the problem of learning a ranking function. The optimization algorithms used in SVMlight are described in [Joachims, 2002a ]. [Joachims, 1999a]. The algorithm has scalable memory requirements and can handle problems with many thousands of support vectors efficiently. The software also provides methods for assessing the generalization performance efficiently. It includes two efficient estimation methods for both error rate and precision/recall. XiAlpha-estimates [Joachims, 2002a, Joachims, 2000b] can be computed at essentially no computational expense, but they are conservatively biased. Almost unbiased estimates provides leave-one-out testing. SVMlight exploits that the results of most leave-one-outs (often more than 99%) are predetermined and need not be computed [Joachims, 2002a]. WWW: http://svmlight.joachims.org/ Generated with FreeBSD Port Tools 0.77 >How-To-Repeat: >Fix: --- svmlight-6.01.shar begins here --- # This is a shell archive. Save it in a file, remove anything before # this line, and then unpack it by entering "sh file". Note, it may # create directories; files and directories will be owned by you and # have default permissions. # # This archive contains: # # svmlight # svmlight/pkg-descr # svmlight/Makefile # svmlight/distinfo # svmlight/files # svmlight/files/patch-Makefile # echo c - svmlight mkdir -p svmlight > /dev/null 2>&1 echo x - svmlight/pkg-descr sed 's/^X//' >svmlight/pkg-descr << 'END-of-svmlight/pkg-descr' XSVMlight is an implementation of Vapnik's Support Vector Machine X[Vapnik, 1995] for the problem of pattern recognition, for the problem Xof regression, and for the problem of learning a ranking function. The Xoptimization algorithms used in SVMlight are described in [Joachims, X2002a ]. [Joachims, 1999a]. The algorithm has scalable memory Xrequirements and can handle problems with many thousands of support Xvectors efficiently. X XThe software also provides methods for assessing the generalization Xperformance efficiently. It includes two efficient estimation methods Xfor both error rate and precision/recall. XiAlpha-estimates [Joachims, X2002a, Joachims, 2000b] can be computed at essentially no Xcomputational expense, but they are conservatively biased. Almost Xunbiased estimates provides leave-one-out testing. SVMlight exploits Xthat the results of most leave-one-outs (often more than 99%) are Xpredetermined and need not be computed [Joachims, 2002a]. X XWWW: http://svmlight.joachims.org/ END-of-svmlight/pkg-descr echo x - svmlight/Makefile sed 's/^X//' >svmlight/Makefile << 'END-of-svmlight/Makefile' X# New ports collection makefile for: svmlight X# Date created: 2006-07-18 X# Whom: Gea-Suan Lin <gslin@gslin.org> X# X# $FreeBSD$ X# X XPORTNAME= svmlight XPORTVERSION= 6.01 XCATEGORIES= science XMASTER_SITES= http://kodiak.cs.cornell.edu/svm_light/current/ XDISTNAME= svm_light X XMAINTAINER= gslin@gslin.org XCOMMENT= An implementation of Support Vector Machines (SVMs) in C X XPLIST_FILES= bin/svm_classify bin/svm_learn XRESTRICTED= only for education and research X XWRKSRC= ${WRKDIR} X Xdo-install: X.for file in svm_classify svm_learn X ${INSTALL_PROGRAM} ${WRKSRC}/${file} ${PREFIX}/bin X.endfor X X.include <bsd.port.mk> END-of-svmlight/Makefile echo x - svmlight/distinfo sed 's/^X//' >svmlight/distinfo << 'END-of-svmlight/distinfo' XMD5 (svm_light.tar.gz) = 22dab64a89dbb01141f87641141e75cc XSHA256 (svm_light.tar.gz) = 213177ac93b60055439f0b6742d4b4e728e4401f017b8facbe2e808d4143fb11 XSIZE (svm_light.tar.gz) = 50121 END-of-svmlight/distinfo echo c - svmlight/files mkdir -p svmlight/files > /dev/null 2>&1 echo x - svmlight/files/patch-Makefile sed 's/^X//' >svmlight/files/patch-Makefile << 'END-of-svmlight/files/patch-Makefile' X--- Makefile.orig Tue Jul 18 09:10:51 2006 X+++ Makefile Tue Jul 18 09:11:16 2006 X@@ -6,11 +6,8 @@ X # Thanks to Ralf Herbrich for the initial version. X # X X-CC=gcc # used C-compiler X-CFLAGS= -O3 # release C-Compiler flags X-#CFLAGS= -g -Wall -pedantic # debugging C-Compiler flags X-LD=gcc # used linker X-LFLAGS=-O3 # linker flags X+LD=${CC} # used linker X+LFLAGS=${CFLAGS} # linker flags X LIBS=-L. -lm # used libraries X X END-of-svmlight/files/patch-Makefile exit --- svmlight-6.01.shar ends here --- >Release-Note: >Audit-Trail: >Unformatted:
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060727230648.DAE7E1CE>