 02 Sep, 2011 1 commit


Tiago Peixoto authored
This fixes a bug in the "correlated" mode in random_rewire().

 26 Aug, 2011 1 commit


Tiago Peixoto authored
This implements a general "blockmodel" generation / rewiring algorithm, using Gibbs acceptence / rejection sampling (a.k.a MetropolisHastings). This also implements some optimizations in the rewiring code, which makes it more efficient on filtered graphs.

 24 Aug, 2011 2 commits


Tiago Peixoto authored
This introduces several simplifications and corrections to the graph rewire algorithm, to guarantee unbiased sampling. Now a move is outright rejected if it produces a selfloop/paralleledge, instead of retried. This also adds a "nonsweep" mode, where edges are rewired randomly, possibly with repetition. The edge moves are now simplified to the target of the edges only, since swaping sources is redundant. The number of iterations can now be explicitly modified, so it is not necessary to call the function more than once, and it is emphasized in the documentation that only after sufficiently many iterations can the graph be guaranteed to be fully mixed.

Tiago Peixoto authored

 28 Jun, 2011 1 commit


Tiago Peixoto authored

 03 May, 2011 1 commit


Tiago Peixoto authored
This makes the calculation coherent with the definition given in the documentation.

 02 Mar, 2011 1 commit


Tiago Peixoto authored
This fixes a leftover bug from the removal of the 'core' submodule.

 10 Feb, 2011 1 commit


Tiago Peixoto authored

 09 Feb, 2011 1 commit


Tiago Peixoto authored

 04 Feb, 2011 1 commit


Tiago Peixoto authored

 25 Jan, 2011 1 commit


Tiago Peixoto authored

 26 Dec, 2010 1 commit


Tiago Peixoto authored

 21 Dec, 2010 1 commit


Tiago Peixoto authored
Added more DOI links to references, and other cosmetic changes.

 13 Nov, 2010 1 commit


Tiago Peixoto authored

 04 Oct, 2010 1 commit


Tiago Peixoto authored

 13 Jul, 2010 1 commit


Tiago Peixoto authored

 11 May, 2010 1 commit


Tiago Peixoto authored
absolute_trust() is now called trust_transitivity(), and the whole trust matrix can now be efficiently calculated.

 03 May, 2010 2 commits


Tiago Peixoto authored

Tiago Peixoto authored

 07 Mar, 2010 1 commit


Tiago Peixoto authored

 20 Feb, 2010 2 commits


Tiago Peixoto authored

Tiago Peixoto authored
This fixes the expected values for several doctests, after random_graph() refactoring.

 01 Dec, 2009 5 commits


Tiago Peixoto authored

Tiago Peixoto authored
Now use _best weights_ to inneighbours to determine trust, to avoid path multiplicity catastrophe.

Tiago Peixoto authored
This also adds the epsilon parameter, which drops paths with weight below this value.

Tiago Peixoto authored

Tiago Peixoto authored

 09 Nov, 2009 1 commit


Tiago Peixoto authored

 06 Nov, 2009 1 commit


Tiago Peixoto authored

 05 Nov, 2009 2 commits


Tiago Peixoto authored
Small fixes of some examples in the docstrings.

Tiago Peixoto authored
Use the original, simpler, path weight calculation.

 12 Oct, 2009 1 commit


Tiago Peixoto authored
This fixes how paths are weighted in the absolute_trust algorithm.

 05 Oct, 2009 1 commit


Tiago Peixoto authored
This completes all the documentation up to this point.

 18 Sep, 2009 1 commit


Tiago Peixoto authored
This dumps the randompath approach, and implements a deterministic, priority queue algorithm.

 09 Aug, 2009 1 commit


Tiago Peixoto authored
Path sampling is done using different bias, and the edge sampling is now done correctly. There is now only one parameter 'n_iter' which replaces 'min/max_iter' and 'epslon'.

 04 Aug, 2009 1 commit


Tiago Peixoto authored
The RNG object must be passed by _reference_ not by value, as is the default! Otherwise the RNG state does not change...

 15 Jul, 2009 2 commits


Tiago Peixoto authored

Tiago Peixoto authored
This modified several docstrings and introduces a quickstart guide.

 23 May, 2009 1 commit


Tiago Peixoto authored

 11 May, 2009 1 commit


Tiago Peixoto authored
Now paths are weighted according to their trust value until the last hop, and paths are not counted twice.
