Changes to 0.3:

  o rank method is default for relation_scores

  o the relations in the SVM Benchmark data are now all reflexive

  o support for sets moved to separate 'sets' package

  o support for fuzzy relations added

  o fitters can now use a sparse constraint matrix representation

  o new SD fitters for the S ("symmetric") and M ("matches") families

  o relations are now subsettable

  o fitters for Cook-Seiford method and Euclidean consensus added

  o new summary method for relations which computes all implemented
    predicates

  o relation_choice() for choosing "winner" objects based on an ensemble
    of relations between these


Changes to 0.2:

  o Copeland's method added to relation_consensus()

  o relation_classes() added to extract and pretty-print
    (ordered) classes from preferences and equivalences.

  o relation_violations() added to compute a measure of remoteness from a
    specified property (e.g., symmetry, transitivity, etc.)

  o set_symdiff() fixed for more than two elements (used to compute 
    the complement of the union and the intersection of a set, which is
    wrong in general). Now, the argument list is treated recursively.

  o Vignette added

  o New SD fitter added for the C ("complete") and A ("antisymmetric") 
    families of relations

  o Summary methods for tuples and sets added

  o Ops and t - methods for the relation_ensemble class added

  o plot.relation() fixed 
    (used to plot the dual, now changes the graphviz layout)

  o Ops.tuple() now correctly handles unary operators, and preserves class

  o transform_incidences() added for transforming incidence matrices of
    endorelations from/to other codings found in literature

Changes to 0.1:

  o Initial release
