An implementation of Multi-View Clustering (Bickel and Scheffer, 2004). Documents are generated by drawing word values from a categorical distribution for each word, given the cluster. This means words are not counted (multinomial, as in the paper), but words take on different values from a finite set of values (categorical). Thus, it implements Mixture of Categoricals EM (as opposed to Mixture of Multinomials developed in the paper), and Spherical k-Means. The latter represents documents as vectors in the categorical space.

Author | Andreas Maunz <andreas@maunz.de> |

Date of publication | 2014-02-24 08:05:39 |

Maintainer | Andreas Maunz <andreas@maunz.de> |

License | BSD_3_clause + file LICENSE |

Version | 1.3 |

http://cs.maunz.de |

**agreementRateBinM:** Agreement rate by maximum posterior values.

**assignFinIdxPerClSkm:** Assign final indices to means that have the smallest angle.

**assignIdxPerClMBinEM:** Assign final indices to data by maximum posterior value.

**checkViews:** Check views for consistency...

**conceptIndicesSkm:** Calculate partitions (concept indices) by assigning each...

**conceptVectorsSkm:** Calculate concept vectors for Spherical k-Means as unit...

**consensusMeansPerClVSkm:** Calculate means per Cluster and view for Spherical k-Means by...

**dbern:** Calculate Bernoulli likelihood...

**dcat:** Calculate categorical likelihood...

**estLogPxBernGthetaJ:** Estimate log document probabilites given specific Bernoulli...

**estLogPxCatGthetaJ:** Estimate log document probabilites given specific Categorical...

**logsum:** Computes the cumulative sum in terms of logarithmic in- and...

**mApplyBern:** Calculate Bernoulli likelihood row-wise for binary events...

**mApplyCat:** Calculate categorical likelihood row-wise for categorical...

**mvcmb:** Multi-View Clustering using mixture of categoricals EM.

**mvcsph:** Multi-View Clustering using Spherical k-Means for categorical...

**oFMixBinEM:** objective function for mixture of binomials EM:...

**oFSkm:** Objective Function (sum of cosines)...

**rowWUL:** Unit length of all vectors row-wise...

**toyView1:** Toy View 1...

**toyView2:** Toy View 2...

**toyViews:** Toy Views...

**UL:** Unit length for vector...

**vectorLength:** Euclidean length of vector...

**viewsClasses:** Counts unique values in both views...

mvc

mvc/NAMESPACE

mvc/data

mvc/data/toyViews.RData

mvc/R

mvc/R/mvc.R
mvc/R/toyView1.R
mvc/R/toyView2.R
mvc/R/toyViews.R
mvc/R/mvc-utils.R
mvc/README.md

mvc/MD5

mvc/DESCRIPTION

mvc/man

mvc/man/assignIdxPerClMBinEM.Rd
mvc/man/viewsClasses.Rd
mvc/man/checkViews.Rd
mvc/man/toyView2.Rd
mvc/man/estLogPxCatGthetaJ.Rd
mvc/man/mvcsph.Rd
mvc/man/agreementRateBinM.Rd
mvc/man/estLogPxBernGthetaJ.Rd
mvc/man/conceptIndicesSkm.Rd
mvc/man/oFMixBinEM.Rd
mvc/man/conceptVectorsSkm.Rd
mvc/man/mApplyCat.Rd
mvc/man/toyView1.Rd
mvc/man/UL.Rd
mvc/man/consensusMeansPerClVSkm.Rd
mvc/man/dbern.Rd
mvc/man/dcat.Rd
mvc/man/rowWUL.Rd
mvc/man/vectorLength.Rd
mvc/man/oFSkm.Rd
mvc/man/assignFinIdxPerClSkm.Rd
mvc/man/toyViews.Rd
mvc/man/mvcmb.Rd
mvc/man/logsum.Rd
mvc/man/mApplyBern.Rd
mvc/LICENSE

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

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