State metrics module

sekupy.analysis.states.metrics.W(X, labels, precomputed=True)

sekupy.analysis.states.metrics.bgss(X, labels, distance=<function euclidean>)

sekupy.analysis.states.metrics.ch_criterion(X, labels, distance=<function euclidean>)

sekupy.analysis.states.metrics.cross_validation_index(X, labels)

sekupy.analysis.states.metrics.explained_variance(X, labels)

sekupy.analysis.states.metrics.gap(X, labels, nrefs=20, refs=None)

Compute the Gap statistic for an nxm dataset in X. Either give a precomputed set of reference distributions in refs as an (n,m,k) scipy array, or state the number k of reference distributions in nrefs for automatic generation with a uniformed distribution within the bounding box of X. Give the list of k-values for which you want to compute the statistic in ks.

sekupy.analysis.states.metrics.get_centers(X, labels)

sekupy.analysis.states.metrics.get_k(labels)

sekupy.analysis.states.metrics.get_triu_array_index(i, j, n_row)

sekupy.analysis.states.metrics.global_explained_variance(X, labels)

sekupy.analysis.states.metrics.index_i(X, labels)

sekupy.analysis.states.metrics.kl_criterion(X, labels, previous_labels=None, next_labels=None, precomputed=True)

sekupy.analysis.states.metrics.m(X, labels, precomputed=True)

sekupy.analysis.states.metrics.wgss(X, labels, distance=<function euclidean>)