Source: shogun
Section: science
Priority: optional
Maintainer: Soeren Sonnenburg <sonne@debian.org>
Build-Depends: libatlas-base-dev [!powerpc !alpha !arm !armel !sh4] | liblapack-dev,
 debhelper (>= 5), libreadline-dev | libreadline5-dev, octave3.2-headers, python-all-dev,
 ghostscript, python-support (>= 1.0.0), python-numpy (>= 1:1.4.1-4~), cdbs,
 r-base-core (>= 2.6.1-2), libblas-dev, swig (>= 1.3.40), xutils-dev, doxygen (>= 1.6.0),
 graphviz, texlive-latex-base, libglpk-dev, liblzo2-dev, zlib1g-dev, liblzma-dev,
 libhdf5-serial-dev (>= 1.8.3)
XS-Python-Version: 2.6
Standards-Version: 3.9.1.0
Homepage: http://www.shogun-toolbox.org
Vcs-Svn: http://bollin.googlecode.com/svn/shogun/trunk/
Vcs-Browser: http://bollin.googlecode.com/svn/shogun/trunk/

Package: libshogun8
Architecture: any
Section: libs
Depends: ${shlibs:Depends}, ${misc:Depends}
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the core
 library all interfaces are based on.

Package: libshogun-dev
Section: libdevel
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, libshogun8 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This package
 includes the developer files required to create stand-a-lone executables.

Package: libshogunui5
Architecture: any
Section: libs
Depends: ${shlibs:Depends}, ${misc:Depends}, libshogun8 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the
 interface library that all static interfaces use.

Package: libshogunui-dev
Section: libdevel
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, libshogunui5 (= ${binary:Version}),
 libshogun-dev
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This package
 includes the developer files required to create stand-a-lone executables.

Package: shogun-doc-en
Conflicts: shogun-doc
Replaces: shogun-doc
Section: doc
Architecture: all
Recommends: shogun-python-modular, libshogun-dev
Depends: ${misc:Depends}
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the English
 user and developer documentation.

Package: shogun-doc-cn
Section: doc
Architecture: all
Recommends: shogun-python-modular, libshogun-dev
Depends: ${misc:Depends}
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the 
 Chinese user and developer documentation.

Package: shogun-dbg
Section: debug
Priority: extra
Architecture: any
Depends: ${misc:Depends}, libshogun8 (= ${binary:Version}),
 libshogunui5 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This package
 contains debug symbols for all interfaces.

Package: shogun-python-modular
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, ${python:Depends},
 libshogun8 (= ${binary:Version})
Recommends: python-matplotlib, python-scipy
Provides: ${python:Provides}
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the modular
 Python package employing swig.

Package: shogun-python
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, ${python:Depends},
 libshogun8 (= ${binary:Version}), libshogunui5 (= ${binary:Version})
Recommends: python-matplotlib
Provides: ${python:Provides}
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the static
 Python package without using swig.

Package: shogun-cmdline
Conflicts: shogun-readline
Replaces: shogun-readline
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, libshogun8 (= ${binary:Version}),
 libshogunui5 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the Readline
 package.

Package: shogun-octave-modular
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, ${octave:Depends},
 libshogun8 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the modular
 Octave package employing swig.

Package: shogun-octave
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, ${octave:Depends},
 libshogun8 (= ${binary:Version}), libshogunui5 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the Octave
 package.

Package: shogun-r
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, r-base-core,
 libshogun8 (= ${binary:Version}), libshogunui5 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the R
 package.

Package: shogun-elwms
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}, r-base-core, ${octave:Depends},
 ${python:Depends}, libshogun8 (= ${binary:Version}),
 libshogunui5 (= ${binary:Version})
Description: Large Scale Machine Learning Toolbox
 SHOGUN - is a new machine learning toolbox with focus on large scale kernel
 methods and especially on Support Vector Machines (SVM) with focus to
 bioinformatics. It provides a generic SVM object interfacing to several
 different SVM implementations. Each of the SVMs can be combined with a variety
 of the many kernels implemented. It can deal with weighted linear combination
 of a number of sub-kernels, each of which not necessarily working on the same
 domain, where  an optimal sub-kernel weighting can be learned using Multiple
 Kernel Learning.  Apart from SVM 2-class classification and regression
 problems, a number of linear methods like Linear Discriminant Analysis (LDA),
 Linear Programming Machine (LPM), (Kernel) Perceptrons and also algorithms to
 train hidden markov models are implemented. The input feature-objects can be
 dense, sparse or strings and of type int/short/double/char and can be
 converted into different feature types. Chains of preprocessors (e.g.
 substracting the mean) can be attached to each feature object allowing for
 on-the-fly pre-processing.
 .
 SHOGUN comes in different flavours, a stand-a-lone version and also with
 interfaces to Matlab(tm), R, Octave, Readline and Python. This is the
 eierlegendewollmilchsau package, providing interfaces and interoperability
 commands to R, Octave and Python all at once.
