zIf7'ddlZddlmZddlmZddlmZ ddlZn #e$rYnwxYwddl m Z Gdde Z dZ d Z Gd d ZGd d ZdS)N)abstractmethod)sqrt)stdout)ClusterIcleZdZdZd dZddZedZdZedZ d Z d Z d Z d Z dS)VectorSpaceClustererz Abstract clusterer which takes tokens and maps them into a vector space. Optionally performs singular value decomposition to reduce the dimensionality. FNc0d|_||_||_dS)a) :param normalise: should vectors be normalised to length 1 :type normalise: boolean :param svd_dimensions: number of dimensions to use in reducing vector dimensionsionality with SVD :type svd_dimensions: int N)_Tt_should_normalise_svd_dimensions)self normalisesvd_dimensionss E/var/www/piapp/venv/lib/python3.11/site-packages/nltk/cluster/util.py__init__zVectorSpaceClusterer.__init__s!!*-ct|dksJjr"ttj|}jrjt|dkrt jt j t j |\}}}|djt j jt j z}|dddjf}|djddf} t j t j || }t j |_|||rfd|DSdS)Nrc:g|]}|S)classify).0vectorr s r z0VectorSpaceClusterer.cluster..?s%@@@fDMM&))@@@r)lenr listmap _normaliser numpylinalgsvd transposearrayidentityfloat64dotr cluster_vectorspace) r vectorsassign_clusterstraceudvtSTDts ` rclusterzVectorSpaceClusterer.cluster(sr7||a  ! :3t8899G   *D$83wqz??$J$J))%/%+g:N:N*O*OPPJQ2(D(()EN$em--A!!!+t+++,A*d**AAA-.Boei2&6&677Gq))DH   %000  A@@@@@@@ @ A ArcdS)zD Finds the clusters using the given set of vectors. Nr)r r'r)s rr&z(VectorSpaceClusterer.cluster_vectorspaceArc|jr||}|jtj|j|}||}||SN)r rr rr%classify_vectorspace cluster_name)r rr0s rrzVectorSpaceClusterer.classifyGs`  ! -__V,,F 8 Ytx00F++F33  )))rcdS)zN Returns the index of the appropriate cluster for the vector. Nrr rs rr5z)VectorSpaceClusterer.classify_vectorspaceOr2rc|jr||}|jtj|j|}|||Sr4)r rr rr%likelihood_vectorspace)r rlabels r likelihoodzVectorSpaceClusterer.likelihoodUsO  ! -__V,,F 8 Ytx00F**65999rc@||}||krdndS)zP Returns the likelihood of the vector belonging to the cluster. g?g)r5)r rr0 predicteds rr:z+VectorSpaceClusterer.likelihood_vectorspace\s+--f55 **ss3rc|jr||}|jtj|j|}|S)zU Returns the vector after normalisation and dimensionality reduction )r rr rr%r8s rrzVectorSpaceClusterer.vectorcs@  ! -__V,,F 8 Ytx00F rcL|ttj||z S)z7 Normalises the vector to unit length. rrr%r8s rrzVectorSpaceClusterer._normalisems#UYvv667777r)FN)FF)__name__ __module__ __qualname____doc__rr0rr&rr5r<r:rrrrrrrs . . . .AAAA2  ^ ***  ^ :::44488888rrcP||z }ttj||S)z} Returns the euclidean distance between vectors u and v. This is equivalent to the length of the vector (u - v). rA)r*vdiffs reuclidean_distancerIts' q5D  $%% & &&rc dtj||ttj||ttj||zz z S)zw Returns 1 minus the cosine of the angle between vectors v and u. This is equal to ``1 - (u.v / |u||v|)``. )rr%r)r*rGs rcosine_distancerL}sG  !Q4 !Q#8#84 !Q;P;P#PQ RRrc,eZdZdZdZddZdZdZdS) _DendrogramNodezTree node of a dendrogram.c"||_||_dSr4)_value _children)r valuechildrens rrz_DendrogramNode.__init__s !rTc|jr6g}|jD]*}|||+|S|r|jgS|gSr4)rQextendleavesrP)r valuesrVchilds rrVz_DendrogramNode.leavessa > F 4 4 ell6223333M  K= 6Mrc|j|fg}t||kr|\}}|js|||fnl|jD]=}|jr||j|f&|d|f>|t||kg}|D],\}}||-|SNr)rPrpoprQpushappendsortrV)r nqueueprioritynoderXgroupss rrcz_DendrogramNode.groupss+t$%%jj1nn"YY[[NHd>  Hd+,,, - -?-LL%,!67777LL!U,,,, JJLLL%jj1nn# ) )NHd MM$++-- ( ( ( ( rc>t|j|jdkSrZ)rLrP)r comparators r__lt__z_DendrogramNode.__lt__st{J,=>>BBrN)T)rBrCrDrErrVrcrfrrrrNrNs`$$"""    *CCCCCrrNc8eZdZdZgfdZdZdZgfdZdZdS) Dendrograma Represents a dendrogram, a tree with a specified branching order. This must be initialised with the leaf items, then iteratively call merge for each branch. This class constructs a tree representing the order of calls to the merge function. crd|D|_tj|j|_d|_dS)zs :param items: the items at the leaves of the dendrogram :type items: sequence of (any) c,g|]}t|Sr)rN)ritems rrz'Dendrogram.__init__..s ???t,,???rrKN)_itemscopy_original_items_merge)r itemss rrzDendrogram.__init__s9 @???? #y55 rct|dksJtjgfd|DR}xjdz c_|j|d<|ddD] }j|= dS)a= Merges nodes at given indices in the dendrogram. The nodes will be combined which then replaces the first node specified. All other nodes involved in the merge will be removed. :param indices: indices of the items to merge (at least two) :type indices: seq of int c32K|]}j|VdSr4)rl)rir s r z#Dendrogram.merge..s)-N-Ndk!n-N-N-N-N-N-NrrKrN)rrNrorl)r indicesrbrts` rmergezDendrogram.merges7||q    t{O-N-N-N-Ng-N-N-NOOO q "& GAJ  A A  rct|jdkrt|jg|jR}n |jd}||S)z Finds the n-groups of items (leaves) reachable from a cut at depth n. :param n: number of groups :type n: int rKr)rrlrNrorc)r r_roots rrczDendrogram.groupssO t{  a  "4;====DD;q>D{{1~~rcBd\}}}t|jdkrt|jg|jR}n |jd}|j}|r|}n d|D}t t t|dzdztz dz dfd d}|j|fg} fd |D} | r| \} } tt d | j } tt |j | }| rt|}t |}tt|D]}||| vr_||kr||d|n3||kr|||dn|||||| |<k||cxkr|krnn|||||| ||d | j D]%}|j r| |j|f&| | D] }|||d | |d fd |D|d dS)z Print the dendrogram in ASCII art to standard out. :param leaf_labels: an optional list of strings to use for labeling the leaves :type leaf_labels: list )+-|rKrc"g|] }d|jz S)z%s)rP)rleafs rrz#Dendrogram.show..s>>>tt{*>>>rrr c |z||zSr4r)centreleftrightlhalfrhalfs rformatzDendrogram.show..formats!dl;F;EEM;; ;rc.tj|dSr4)rwrite)strs rdisplayz Dendrogram.show..displays L     rc&g|] }dS)rr)rrrs rrz#Dendrogram.show..s!444TVVC[[444rc8|ddS)NFr)rV)cs rz!Dendrogram.show..s%1Cr c3BK|]}|VdSr4)center)rrkwidths rruz"Dendrogram.show..#s/@@t E**@@@@@@rN)rr)rrlrNrornmaxrintrPr[rrQindexminranger]r^join)r leaf_labelsJOINHLINKVLINKryrVlast_rowrr` verticalsrarbchild_left_leafrvmin_idxmax_idxrtrXverticalrrrrs @@@@rshowzDendrogram.showsX+eU t{  a  "4;====DD;q>D%  ?"HH>>v>>>HCX&&''!+ EEMA%&& < < < < < < <   +t$%4444V444  "YY[[NHd"3'C'CT^#T#TUUO3v|_==>>G 'g,,g,,3v;;'' * *!9//G||tS% 8 89999gtUC 8 89999tUE : :;;;#)6%==IaLL,,,,W,,,,,GFF5%778888GIaL)))) GDMMM 8 8?8LL%,!6777 JJLLL% " "!!!! GDMMM9 > @@@@x@@@@@AAA rct|jdkrt|jg|jR}n |jd}|d}dt|zS)NrKrFz)rrlrNrorV)r ryrVs r__repr__zDendrogram.__repr__&s_ t{  a  "4;====DD;q>DU##,s6{{::rN) rBrCrDrErrwrcrrrrrrhrhs     "GGGGR;;;;;rrh)rmabcrmathrsysrr ImportErrornltk.cluster.apirrrIrLrNrhrrrrsK  LLLL   D &%%%%%\8\8\8\8\88\8\8\8~'''SSS(C(C(C(C(C(C(C(CV|;|;|;|;|;|;|;|;|;|;s %%