rtj?ddlZddlmZddlmZmZddlmZm Z dgZ dZ dZ dZ eegegeed hgd d d d dZdS)N)linear_sum_assignment) StrOptionsvalidate_params) check_arraycheck_consistent_lengthconsensus_scorect|t|d}t||\}}t||\}}||||fS)z9Unpacks the row and column arrays and checks their shape.c$t|dS)NF) ensure_2d)r)xs `/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/sklearn/metrics/cluster/_bicluster.pyz)_check_rows_and_columns..s{1666)rmap)abchecksa_rowsa_colsb_rowsb_colss r _check_rows_and_columnsr sQQQ 6 6F^^NFF^^NFF 666 ))rc||z||zz}||z}||z}|||z|z z S)z:Jaccard coefficient on the elements of the two biclusters.)sum)rrrr intersectiona_sizeb_sizes r _jaccardrstVO((**fvo-B-B-D-DDL ZZ\\FJJLL (F ZZ\\FJJLL (F 6F?\9 ::rc t||\jd}jd tj fdt |D}|S)zComputes pairwise similarity matrix. result[i, j] is the Jaccard coefficient of a's bicluster i and b's bicluster j. rcRg|]"fdtD#S)c \g|](}||)Sr").0jrrrri similaritys r z3_pairwise_similarity...-s9 X X XZZq 6!9fQi C C X X Xr)range)r#r%rrrrn_br&s @r r'z(_pairwise_similarity..,sU    Y X X X X X X X XUSVZZ X X X   r)rshapenparrayr() rrr&n_aresultrrrrr)s ` @@@@@r _pairwise_similarityr/!s&=Q%B%B"FFFF ,q/C ,q/C X         3ZZ   F Mrjaccard)rrr&T)prefer_skip_nested_validation)r&c0|dkrt}t|||}td|z \}}t|d}t|d}t |||ft ||z S)aXThe 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') 1.0 r0g?r)rr/rlenfloatrmax)rrr&matrix row_indices col_indicesr-r)s r rr4spY !!Q 3 3F4S6\BBK ad))C ad))C  [015577#c3--G H HHr)numpyr+scipy.optimizersklearn.utils._param_validationrrsklearn.utils.validationrr__all__rrr/tuplecallablerr"rr r@s000000GGGGGGGGIIIIIIII  ***;;;&WWYK!8!89 #' )26I6I6I6I6I6I6Ir