a j@sddlZddlmZddlmZmZddlmZm Z dgZ ddZ d d Z d d Z eegegeed hgdddd dddZdS)N)linear_sum_assignment) StrOptionsvalidate_params) check_arraycheck_consistent_lengthconsensus_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)xr HE:\soccer\ml_env\Lib\site-packages\sklearn/metrics/cluster/_bicluster.pyz)_check_rows_and_columns..)rmap)abZchecksa_rowsa_colsb_rowsb_colsr r r _check_rows_and_columns s rcCsH||||}||}||}||||S)z:Jaccard coefficient on the elements of the two biclusters.)sum)rrrr intersectionZa_sizeZb_sizer r r _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|]$fddtDqS)cs*g|]"}||qSr r ).0j)rrrri similarityr r -r z3_pairwise_similarity...)range)rrrrrn_br)rr r,sz(_pairwise_similarity..)rshapenparrayr)rrrn_aresultr rr _pairwise_similarity!s  r&jaccard)rrrT)Zprefer_skip_nested_validation)rcCsZ|dkr t}t|||}td|\}}t|d}t|d}|||ft||S)adThe similarity of two sets of biclusters. Similarity between individual biclusters is computed. Then the best matching between sets is found by solving a linear sum assignment problem, using a modified Jonker-Volgenant algorithm. The final score is the sum of similarities divided by the size of the larger set. Read more in the :ref:`User Guide `. Parameters ---------- a : tuple (rows, columns) Tuple of row and column indicators for a set of biclusters. b : tuple (rows, columns) Another set of biclusters like ``a``. similarity : 'jaccard' or callable, default='jaccard' May be the string "jaccard" to use the Jaccard coefficient, or any function that takes four arguments, each of which is a 1d indicator vector: (a_rows, a_columns, b_rows, b_columns). Returns ------- consensus_score : float Consensus score, a non-negative value, sum of similarities divided by size of larger set. See Also -------- scipy.optimize.linear_sum_assignment : Solve the linear sum assignment problem. References ---------- * Hochreiter, Bodenhofer, et. al., 2010. `FABIA: factor analysis for bicluster acquisition `__. Examples -------- >>> from sklearn.metrics import consensus_score >>> a = ([[True, False], [False, True]], [[False, True], [True, False]]) >>> b = ([[False, True], [True, False]], [[True, False], [False, True]]) >>> consensus_score(a, b, similarity='jaccard') np.float64(1.0) r'g?r)rr&rlenrmax)rrrmatrixZ row_indicesZ col_indicesr$r r r r r4s8   )numpyr"Zscipy.optimizerZutils._param_validationrrZutils.validationrr__all__rrr&tuplecallablerr r r r s