U 9hu>@stddlZddlmZddlmZddlmZddlm Z ddd Z d d Z dddZ ddZ dddZdddZdS)N)pairwise_distances)cdist)mst_linkage_core)isclose@cCsfd||dk|||dk<|jdd}||jdd}|dkrVtt|}n |d|C}|S)a Compute the all-points-core-distance for all the points of a cluster. Parameters ---------- distance_matrix : array (cluster_size, cluster_size) The pairwise distance matrix between points in the cluster. d : integer The dimension of the data set, which is used in the computation of the all-point-core-distance as per the paper. Returns ------- core_distances : array (cluster_size,) The all-points-core-distance of each point in the cluster References ---------- Moulavi, D., Jaskowiak, P.A., Campello, R.J., Zimek, A. and Sander, J., 2014. Density-Based Clustering Validation. In SDM (pp. 839-847). g?rrZaxisg)sumshapenpZzeroslen)distance_matrixdresultrc/var/www/html/CrowdFlow/HYROX/ble_analysis_env_py38/lib/python3.8/site-packages/hdbscan/validity.pyall_points_core_distances    rcCsnd}t|jdD]V}t|jdD]B}|||d}|||d}|dks$|||kr^q$||}q$q|S)Nrr)ranger )stacked_distances max_ratioijdistZcoredistrrrr+s r euclideanFc Ks|dkr>|dkrtd|||kddfdd||kf}n2|||kddf} t| fd|i|}|jd}|r||dfSt||d} t| | jddf} t|| | jg} |rt dt t | | j d d | fSdS) aa Compute pairwise distances for all the points of a cluster. If metric is 'precomputed' then assume X is a distance matrix for the full dataset. Note that in this case you must pass in 'd' the dimension of the dataset. Parameters ---------- X : array (n_samples, n_features) or (n_samples, n_samples) The input data of the clustering. This can be the data, or, if metric is set to `precomputed` the pairwise distance matrix used for the clustering. labels : array (n_samples) The label array output by the clustering, providing an integral cluster label to each data point, with -1 for noise points. cluster_id : integer The cluster label for which to compute the distances metric : string The metric used to compute distances for the clustering (and to be re-used in computing distances for mr distance). If set to `precomputed` then X is assumed to be the precomputed distance matrix between samples. d : integer (or None) The number of features (dimension) of the dataset. This need only be set in the case of metric being set to `precomputed`, where the ambient dimension of the data is unknown to the function. **kwd_args : Extra arguments to pass to the distance computation for other metrics, such as minkowski, Mahanalobis etc. Returns ------- distances : array (n_samples, n_samples) The distances between all points in `X` with `label` equal to `cluster_id`. core_distances : array (n_samples,) The all-points-core_distance of all points in `X` with `label` equal to `cluster_id`. References ---------- Moulavi, D., Jaskowiak, P.A., Campello, R.J., Zimek, A. and Sander, J., 2014. Density-Based Clustering Validation. In SDM (pp. 839-847). precomputedNz4If metric is precomputed a d value must be provided!metricr)rrz(Max raw distance to coredistance ratio: r) ValueErrorrr rcopyr tiledstackTprintstrrmax) Xlabels cluster_idrr no_coredistprint_max_raw_to_coredist_ratiokwd_argsr Zsubset_Xcore_distancesZcore_dist_matrixrrrrdistances_between_points8s&6&   r,c Cs,t|}|}t|dddD]z\}}tt|t|d|dd}t||d|ddft}|||dk}t |dkst |d|d<q"t |j dt |jddtjdk}t |sdg}tjt|jdd|ddt}t|r||}n|}||fS)a6 Compute the 'internal' minimum spanning tree given a matrix of mutual reachability distances. Given a minimum spanning tree the 'internal' graph is the subgraph induced by vertices of degree greater than one. Parameters ---------- mr_distances : array (cluster_size, cluster_size) The pairwise mutual reachability distances, inferred to be the edge weights of a complete graph. Since MSTs are computed per cluster this is the all-points-mutual-reacability for points within a single cluster. Returns ------- internal_nodes : array An array listing the indices of the internal nodes of the MST internal_edges : array (?, 3) An array of internal edges in weighted edge list format; that is an edge is an array of length three listing the two vertices forming the edge and weight of the edge. References ---------- Moulavi, D., Jaskowiak, P.A., Campello, R.J., Zimek, A. and Sander, J., 2014. Density-Based Clustering Validation. In SDM (pp. 839-847). rNrr)rr enumerater whererintZ intersect1dZastyper AssertionErrorZaranger Zbincountr!flattenZintpprodisinboolany) Z mr_distancesZsingle_linkage_dataZ min_span_treeindexrow candidatesZverticesZedge_selectionedgesrrrinternal_minimum_spanning_trees6$"  r;c Ks|dkrJ|||kddfdd||kf} | |ddfdd|f} n0|||k|} |||k|}t| ||f| } | r| St||| jddfj}t||| jddf}t| ||gjdd}|SdS)a Compute the density separation between two clusters. This is the minimum distance between pairs of points, one from internal nodes of MSTs of each cluster. Parameters ---------- X : array (n_samples, n_features) or (n_samples, n_samples) The input data of the clustering. This can be the data, or, if metric is set to `precomputed` the pairwise distance matrix used for the clustering. labels : array (n_samples) The label array output by the clustering, providing an integral cluster label to each data point, with -1 for noise points. cluster_id1 : integer The first cluster label to compute separation between. cluster_id2 : integer The second cluster label to compute separation between. internal_nodes1 : array The vertices of the MST for `cluster_id1` that were internal vertices. internal_nodes2 : array The vertices of the MST for `cluster_id2` that were internal vertices. core_distances1 : array (size of cluster_id1,) The all-points-core_distances of all points in the cluster specified by cluster_id1. core_distances2 : array (size of cluster_id2,) The all-points-core_distances of all points in the cluster specified by cluster_id2. metric : string The metric used to compute distances for the clustering (and to be re-used in computing distances for mr distance). If set to `precomputed` then X is assumed to be the precomputed distance matrix between samples. **kwd_args : Extra arguments to pass to the distance computation for other metrics, such as minkowski, Mahanalobis etc. Returns ------- The 'density separation' between the clusters specified by `cluster_id1` and `cluster_id2`. References ---------- Moulavi, D., Jaskowiak, P.A., Campello, R.J., Zimek, A. and Sander, J., 2014. Density-Based Clustering Validation. In SDM (pp. 839-847). rNrrrr)rminr rr r!r r$)r%r&Z cluster_id1Z cluster_id2Zinternal_nodes1Zinternal_nodes2Zcore_distances1Zcore_distances2rr(r*Z sub_selectr Zcluster1Zcluster2Zcore_dist_matrix1Zcore_dist_matrix2Zmr_dist_matrixrrrdensity_separations*;$    r=c Ks"i}i} i} i} |d} tjtj| | ftjd} tj| tjd}t| D]h}t||kdkrfqNt|||||f||d|\}||<t |\| |<| |<| |j d| |<qNt| D]}t||kdkrq| |}t|d| D]j}t||kdkrq| |}t ||||||||||f||d|| ||f<| ||f| ||f<qqt |j d}d}t| D]}t||kdkrqv| |}|| |t|| |||<|rtdt|tdt| |t||k}|||||7}qv|r||fS|Sd S) a^ Compute the density based cluster validity index for the clustering specified by `labels` and for each cluster in `labels`. Parameters ---------- X : array (n_samples, n_features) or (n_samples, n_samples) The input data of the clustering. This can be the data, or, if metric is set to `precomputed` the pairwise distance matrix used for the clustering. labels : array (n_samples) The label array output by the clustering, providing an integral cluster label to each data point, with -1 for noise points. metric : optional, string (default 'euclidean') The metric used to compute distances for the clustering (and to be re-used in computing distances for mr distance). If set to `precomputed` then X is assumed to be the precomputed distance matrix between samples. d : optional, integer (or None) (default None) The number of features (dimension) of the dataset. This need only be set in the case of metric being set to `precomputed`, where the ambient dimension of the data is unknown to the function. per_cluster_scores : optional, boolean (default False) Whether to return the validity index for individual clusters. Defaults to False with the function returning a single float value for the whole clustering. mst_raw_dist : optional, boolean (default False) If True, the MST's are constructed solely via 'raw' distances (depending on the given metric, e.g. euclidean distances) instead of using mutual reachability distances. Thus setting this parameter to True avoids using 'all-points-core-distances' at all. This is advantageous specifically in the case of elongated clusters that lie in close proximity to each other . **kwd_args : Extra arguments to pass to the distance computation for other metrics, such as minkowski, Mahanalobis etc. Returns ------- validity_index : float The density based cluster validity index for the clustering. This is a numeric value between -1 and 1, with higher values indicating a 'better' clustering. per_cluster_validity_index : array (n_clusters,) The cluster validity index of each individual cluster as an array. The overall validity index is the weighted average of these values. Only returned if per_cluster_scores is set to True. References ---------- Moulavi, D., Jaskowiak, P.A., Campello, R.J., Zimek, A. and Sander, J., 2014. Density-Based Clustering Validation. In SDM (pp. 839-847). r)Zdtyper)r(r)r-)rr(zMinimum density separation: zDensity sparseness: N)r$r infZonesZfloat64emptyrr r,r;r!r=floatr r<r"r#)r%r&rrZper_cluster_scoresZ mst_raw_distverboser*r+Zdensity_sparsenessZ mst_nodesZ mst_edgesZmax_cluster_idZ density_sepZcluster_validity_indicesr'Zdistances_for_mstrZinternal_nodes_irZinternal_nodes_jZ n_samplesrZmin_density_sepZ cluster_sizerrrvalidity_indexs;        rB)r)rNFF)rF)rNFFF)numpyr Zsklearn.metricsrZscipy.spatial.distancerZ_hdbscan_linkagerZhdbscan_rrrr,r;r=rBrrrrs*     $ PF S