An implementation of the Bayesian version of the Mallows rank model (Vitelli et al., Journal of Machine Learning Research, 2018 < http://jmlr.org/papers/v18/15-481.html>; Crispino et al., to appear in Annals of Applied Statistics). Both Cayley, footrule, Hamming, Kendall, Spearman, and Ulam distances are supported in the models. The rank data to be analyzed can be in the form of complete rankings, top-k rankings, partially missing rankings, as well as consistent and inconsistent pairwise preferences. Several functions for plotting and studying the posterior distributions of parameters are provided. The package also provides functions for estimating the partition function (normalizing constant) of the Mallows rank model, both with the importance sampling algorithm of Vitelli et al. and asymptotic approximation with the IPFP algorithm (Mukherjee, Annals of Statistics, 2016
compute_mallowsnot to work (without giving any errors) when
rankingscontained missing values.
compute_mallowsto fail when
preferenceshad integer columns.
save_ind_clus, to save typing.
save_individual_cluster_probs = TRUEin compute_mallows.
alpha_max, the truncation of the exponential prior for
alpha, as a user option in
?label_switchingfor more info.
compute_importance_sampling_estimatehas been updated to avoid numerical overflow. Previusly, importance sampling failed at below 200 items. Now it works way above 10,000 items.
generate_constraintsnow are able to run in parallel.
estimate_partition_functionnow has an option to run in parallel, leading to significant speed-up.
error_model = "bernoulli"in
compute_mallowsin order to use it. Examples will come later.
parallelto Suggests field.
compute_map_consensushave been removed. Use
factorvariables sorted according to the cluster number. Hence, in plot legends, "Cluster 10" comes after "Cluster 9", rather than after "Cluster 1" which it used to do until now, because it was a
plot.BayesMallowsno longer contains print statements which forces display of plots. Instead plots are returned from the function. Using
p <- plot(fit)hence does no longer display a plot, whereas using
plot(fit)without assigning it to an object, displays a plot. Until now the plot was always shown for
sample_mallowsnow support Ulam distance, with argument
metric = "ulam".
Rcpp, cf. this issue). The long vignette is no longer needed in any case, since all the functions are well documented with executable examples.
Rankclusterpackage has been removed from dependencies.
compute_mallows. It used to be
floor(n_items / 5), which evaluates to zero when
n_items <= 4. Updated it to
max(1L, floor(n_items / 5)).
metric = "hamming") as an option to
sample_mallowsto avoid errors when package
tibbleversion 2.0.0 is released. This update is purely internal.
BayesMallowsMixturesnow have default print functions, hence avoiding excessive amounts of informations printed to the console if the user happens to write the name of such an object and press Return.
compute_mallows_mixturesno longer sets
include_wcd = TRUEby default. The user can choose this argument.
compute_mallowshas a new argument
save_clus, which can be set to
FALSEfor not saving cluster assignments.
assess_convergencenow automatically plots mixtures.
compute_mallows_mixturesnow returns an object of class
assess_convergencenow adds prefix Assessor to plots when
parameter = "Rtilde".
predict_top_kis now an exported function. Previously it was internal.
compute_posterior_intervalsnow has default
parameter = "alpha". Until now, this argument has had no default.
assess_convergencehas been renamed to
parameter, to be more consistent.
compute_mallowshas been renamed to
compute_mallowsfills in implied ranks when an assessor has only one missing rank. This avoids unnecessary augmentation in MCMC.
generate_orderingnow work with missing ranks.
compute_mallows has been renamed to
Change the interface for computing consensus ranking. Now, CP and MAP consensus are both computed with the
compute_consensus function, with argument
type equal to either