U 3d @sTddlZddlmZddlmZmZdgZddZdd Z d d Z d d ddZ dS)N)linear_sum_assignment)check_consistent_length check_arrayconsensus_scorecCs@t|t|dd}t||\}}t||\}}||||fS)z9Unpacks the row and column arrays and checks their shape.cSs t|ddS)NF)Z ensure_2d)r)xrF/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/metrics/cluster/_bicluster.py z)_check_rows_and_columns..)rmap)abZchecksa_rowsa_colsb_rowsb_colsrrr _check_rows_and_columns s rcCsH||||}||}||}||||S)z:Jaccard coefficient on the elements of the two biclusters.)sum)rrrr intersectionZa_sizeZb_sizerrr _jaccardsrcsPt||\jd}jdtfddt|D}|S)zComputes pairwise similarity matrix. result[i, j] is the Jaccard coefficient of a's bicluster i and b's bicluster j. rcs,g|]$fddtDqS)cs*g|]"}||qSrr).0j)rrrri similarityrr )sz3_pairwise_similarity...)range)rrrrrn_br)rr r(sz(_pairwise_similarity..)rshapenparrayr)r rrn_aresultrrr _pairwise_similaritys  r$jaccard)rcCsZ|dkr t}t|||}td|\}}t|d}t|d}|||ft||S)a{The similarity of two sets of biclusters. Similarity between individual biclusters is computed. Then the best matching between sets is found using the Hungarian algorithm. The final score is the sum of similarities divided by the size of the larger set. Read more in the :ref:`User Guide `. Parameters ---------- a : (rows, columns) Tuple of row and column indicators for a set of biclusters. b : (rows, columns) Another set of biclusters like ``a``. similarity : 'jaccard' or callable, default='jaccard' May be the string "jaccard" to use the Jaccard coefficient, or any function that takes four arguments, each of which is a 1d indicator vector: (a_rows, a_columns, b_rows, b_columns). Returns ------- consensus_score : float Consensus score, a non-negative value, sum of similarities divided by size of larger set. References ---------- * Hochreiter, Bodenhofer, et. al., 2010. `FABIA: factor analysis for bicluster acquisition `__. r%g?r)rr$rlenrmax)r rrZmatrixZ row_indicesZ col_indicesr"rrrr r0s$   ) Znumpyr Zscipy.optimizerZutils.validationrr__all__rrr$rrrrr s