ó ŒqIc@s˜dZddlmZmZmZmZddlmZddlm Z d„Z d„Z d„Z ddd „ƒYZ ed kr”ddlmZd Zd Zd Zd ZdeeefƒZe eeƒZejeƒejeƒejƒZejƒZdeeƒefGHx{edd ƒD]gZeeƒZejeeƒej ƒZej!ƒZe\Z"Z#Z$deeƒee"e#e$fGHq&WndS(sÞ KD tree data structure for searching N-dimensional vectors. The KD tree data structure can be used for all kinds of searches that involve N-dimensional vectors, e.g. neighbor searches (find all points within a radius of a given point) or finding all point pairs in a set that are within a certain radius of each other. See "Computational Geometry: Algorithms and Applications" (Mark de Berg, Marc van Kreveld, Mark Overmars, Otfried Schwarzkopf). Author: Thomas Hamelryck. iÿÿÿÿ(tsumtsqrttdtypetarray(trandom(t_CKDTreecCs||}tt||ƒƒS(N(RR(tptqtdiff((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt_dists c Csðtj||ƒ}t||fƒ}|j|ƒ|j|ƒ}g|D]}|j^qG}|dkrqd} n t|ƒ} |j|ƒ}g|D]}|j^q“}|dkr½d} n t|ƒ} | | krÝdGHnd| | fGHdS(s0 Test all fixed radius neighbor search. Test all fixed radius neighbor search using the KD tree C module. o nr_points - number of points used in test o dim - dimension of coords o bucket_size - nr of points per tree node o radius - radius of search (typically 0.05 or so) isPassed.sNot passed: %i != %i.N( RtKDTreeRtset_datatneighbor_searchtradiustNonetlentneighbor_simple_search( t nr_pointstdimt bucket_sizeR tkdttcoordst neighborstneighbortrtl1tl2((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt_neighbor_tests         c Csëtj||ƒ}t||fƒ}|d}|j|ƒ|j||ƒ|jƒ}|dkrld}n t|ƒ}d} xCtd|ƒD]2} || } t | |ƒ|krŽ| d} qŽqŽW|| krØdGHnd|| fGHdS(sTest neighbor search. Test neighbor search using the KD tree C module. o nr_points - number of points used in test o dim - dimension of coords o bucket_size - nr of points per tree node o radius - radius of search (typically 0.05 or so) iisPassed.sNot passed: %i != %i.N( RR RR tsearch_center_radiust get_indicesRRtrangeR ( RRRR RRtcenterRRRtiR((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt_test;s"         R cBsYeZdZdd„Zd„Zd„Zd„Zd„Zd„Zd„Z d „Z RS( sÒ KD tree implementation (C++, SWIG python wrapper) The KD tree data structure can be used for all kinds of searches that involve N-dimensional vectors, e.g. neighbor searches (find all points within a radius of a given point) or finding all point pairs in a set that are within a certain radius of each other. Reference: Computational Geometry: Algorithms and Applications Second Edition Mark de Berg, Marc van Kreveld, Mark Overmars, Otfried Schwarzkopf published by Springer-Verlag 2nd rev. ed. 2000. ISBN: 3-540-65620-0 The KD tree data structure is described in chapter 5, pg. 99. The following article made clear to me that the nodes should contain more than one point (this leads to dramatic speed improvements for the "all fixed radius neighbor search", see below): JL Bentley, "Kd trees for semidynamic point sets," in Sixth Annual ACM Symposium on Computational Geometry, vol. 91. San Francisco, 1990 This KD implementation also performs a "all fixed radius neighbor search", i.e. it can find all point pairs in a set that are within a certain radius of each other. As far as I know the algorithm has not been published. icCs+||_tj||ƒ|_d|_dS(Ni(RRR Rtbuilt(tselfRR((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt__init__|s cCs‘|jƒdks$|jƒdkr3tdƒ‚nt|jƒdks^|jd|jkrttd|jƒ‚n|jj|ƒd|_dS(sÛAdd the coordinates of the points. o coords - two dimensional NumPy array. E.g. if the points have dimensionality D and there are N points, the coords array should be NxD dimensional. g€„.Ág€„.As&Points should lie between -1e6 and 1e6iisExpected a Nx%i NumPy arrayN( tmintmaxt ExceptionRtshapeRRR R"(R#R((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt set_coordsƒs $+cCsZ|jstdƒ‚n|j|jfkrCtd|jƒ‚n|jj||ƒdS(sÜSearch all points within radius of center. o center - one dimensional NumPy array. E.g. if the points have dimensionality D, the center array should be D dimensional. o radius - float>0 sNo point set specifieds%Expected a %i-dimensional NumPy arrayN(R"R'R(RRR(R#RR ((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pytsearch“s  cCs#|jjƒ}|dkrgS|S(siReturn radii. Return the list of distances from center after a neighbor search. N(Rt get_radiiR(R#ta((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyR+¡s cCs#|jjƒ}|dkrgS|S(s#Return the list of indices. Return the list of indices after a neighbor search. The indices refer to the original coords NumPy array. The coordinates with these indices were within radius of center. For an index pair, the first index0) sNo point set specifiedN(R"R'RR R(R#R ((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt all_search½s cCs2tg|jD]}|j|jg^q ƒ}|S(s¼Return All Fixed Neighbor Search results. Return a Nx2 dim NumPy array containing the indices of the point pairs, where N is the number of neighbor pairs. (RRtindex1tindex2(R#RR,((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pytall_get_indicesÈs.cCsg|jD]}|j^q S(s½Return All Fixed Neighbor Search results. Return an N-dim array containing the distances of all the point pairs, where N is the number of neighbor pairs.. (RR (R#R((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyt all_get_radiiÒs( t__name__t __module__t__doc__R$R)R*R+RR-R0R1(((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyR [s     t__main__i †ii iÈs&Found %i point pairs within radius %f.is>Found %i points in radius %f around center (%.2f, %.2f, %.2f).N((%R4tnumpyRRRRt numpy.randomRt Bio.KDTreeRR RR!R R2RRRt query_radiusRtkdtreeR)R-R0tindicesR1tradiiRRR RR*RR+txtytz(((s„/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/KDTree/KDTree.pyts6"  ! €