Wi$>ddlZddlmZmZddlmZGddeZy)N)KDTreeBallTree)DistanceMetricc&eZdZdZeedZ ddZy)BranchDetectionDataaInput data for branch detection functionality. Recreates and caches internal data structures from the clustering stage. Parameters ---------- data : array (n_samples, n_features) The original data set that was clustered. labels : array (n_samples) The cluster labels for every point in the data set. condensed_tree : array (n_points + n_merges, 4) The condensed tree produced during clustering, used to extract outliers. min_samples : int The min_samples value used in clustering. tree_type : string, optional Which type of space tree to use for core distance computation. One of: * ``kdtree`` * ``balltree`` metric : string, optional The metric used to determine distance for the clustering. This is the metric that will be used for the space tree to determine core distances etc. **kwargs : Any further arguments to the metric. Attributes ---------- all_finite : bool Whether the data set contains any infinite or NaN values. finite_index : array (n_samples) The indices of the finite data points in the original data set. internal_to_raw : dict A mapping from the finite data set indices to the original data set. tree : KDTree or BallTree A space partitioning tree that can be queried for nearest neighbors if the metric is supported by a KDTree or BallTree. neighbors : array (n_samples, min_samples) The nearest neighbor for every non-noise point in the original data set. core_distances : array (n_samples) The core distance for every non-noise point in the original data set. dist_metric : callable Accelerated distance metric function. )kdtreeballtreec |jtj}tj|ddd} | dk(rd|_d|_d|_nd|_tjtj|jd|dd| |_||j }||j }t|j D cic]\} } | |  c} } |_|j||fd |i||_ tj|fi||_tj |jdtj"|_tj |jd|fd tj& |_|d k7} | j+rK|jj-|| | \} |j(| ddf<| ddd f|j$| <yycc} } w) N lambda_valgright)siderTFchildmetric)dtype)k)astypenpfloat64 searchsorted all_finiteinternal_to_raw finite_index setdiff1darangeshape enumerate_tree_type_maptreer get_metric dist_metricfullnancore_distancesint64 neighborsanyquery)selfdatalabelscondensed_tree min_samples tree_typerkwargs clean_data last_outlierxy noise_mask distancess _/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/hdbscan/branch_data.py__init__zBranchDetectionData.__init__Ds[[, ~l'CSwW 1 "DO#'D $D #DO "  $**Q-(w' 6!D D--.F#D$5$56J!*4+<+> 7;yy:&+8G8 4It~~j!m4/82.>D   + $s G3N)r euclidean)__name__ __module__ __qualname____doc__rrrr8r7rrs!9v!'H=N*?r?r) numpyrsklearn.neighborsrr dist_metricsrobjectrr>r?r7rDs.(h?&h?r?