medSTC: A max-margin supervised Sparse Topical Coding Model

This is a C++ implementation of Sparse Topical Coding (STC), a model of discrete data which is fully described in Zhu et al. (2011) (http://www.cs.cmu.edu/~junzhu/stc/stc.pdf). It can be used for multi-class classification and describing documents with underlying sparse topics.

Install the latest version of this package by entering the following in R:
install.packages("medSTC")
AuthorJun Zhu <junzhu@cs.cmu.edu>, Aykut FIRAT <aykut@mit.edu>
Date of publication2013-01-24 08:24:00
MaintainerAykut FIRAT <aykut@crimsonhexagon.com>
Licensefile LICENSE
Version1.0.0

View on CRAN

Files

data
data/datalist
data/newsgroup.test.documents.rda
data/newsgroup.test.labels.rda
data/newsgroup.train.documents.rda
data/newsgroup.train.labels.rda
data/newsgroup.vocab.rda
data/stopwords.rda
demo
demo/00Index
demo/medSTC.R
DESCRIPTION
LICENSE
man
man/medSTC-package.Rd man/medSTC.Rd man/newsgroups.Rd man/predict.medSTC.Rd
NAMESPACE
R
R/medSTCSource.R
src
src/dummy.cc
src/Makevars
src/Makevars.win
src/medstc
src/medstc/cokus.cpp
src/medstc/cokus.h
src/medstc/corpus.cpp
src/medstc/corpus.h
src/medstc/lbfgscpp.cpp
src/medstc/lbfgscpp.h
src/medstc/main.cpp
src/medstc/medstc.cpp
src/medstc/medstc.h
src/medstc/params.cpp
src/medstc/params.h
src/medstc/utils.cpp
src/medstc/utils.h
src/svm_multiclass
src/svm_multiclass/svm_struct_api.cpp
src/svm_multiclass/svm_struct_api.h
src/svm_multiclass/svm_struct_api_types.h
src/svm_multiclass/svm_struct_common.cpp
src/svm_multiclass/svm_struct_common.h
src/svm_multiclass/svm_struct_learn.cpp
src/svm_multiclass/svm_struct_learn.h
src/svmlight
src/svmlight/kernel.h
src/svmlight/svm_common.cpp
src/svmlight/svm_common.h
src/svmlight/svm_hideo.cpp
src/svmlight/svm_learn.cpp
src/svmlight/svm_learn.h
MD5

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.