ó ‡ˆ\c@sÎdZddlZddlZddlmZddlmZmZddl m Z m Z ddl m Z ddlmZdd lmZd „Zdd d d eeed„Zdeefd„ƒYZdS(s*Affinity Propagation clustering algorithm.iÿÿÿÿN(tConvergenceWarningi(t BaseEstimatort ClusterMixin(tas_float_arrayt check_array(tcheck_is_fitted(teuclidean_distances(tpairwise_distances_argmincs.‡fd†}‡fd†}|ƒo-|ƒS(NcstjˆˆjdkƒS(Ni(tnptalltflat((t preference(sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pytall_equal_preferencesscsMtjˆjdtƒ}tj|dƒtjˆ|jˆ|jdkƒS(Ntdtypei(Rtonestshapetboolt fill_diagonalR R (tmask(tS(sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pytall_equal_similaritiess((RR R R((RR sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pyt#_equal_similarities_and_preferencessiiÈgà?cCs`t|d|ƒ}|jd}|jd|jdkrUtdt|jƒƒ‚n|dkrstj|ƒ}n|dks‹|dkrštdƒ‚ntj|ƒ}|dksÄt||ƒrˆt j dƒ|j d|j |dkr0|rtj |ƒtj |ƒdfStj |ƒtj |ƒfS|r_tjdgƒtjdg|ƒdfStjdgƒtjdg|ƒfSntj jdƒ} ||j dd|d…`. Parameters ---------- S : array-like, shape (n_samples, n_samples) Matrix of similarities between points preference : array-like, shape (n_samples,) or float, optional Preferences for each point - points with larger values of preferences are more likely to be chosen as exemplars. The number of exemplars, i.e. of clusters, is influenced by the input preferences value. If the preferences are not passed as arguments, they will be set to the median of the input similarities (resulting in a moderate number of clusters). For a smaller amount of clusters, this can be set to the minimum value of the similarities. convergence_iter : int, optional, default: 15 Number of iterations with no change in the number of estimated clusters that stops the convergence. max_iter : int, optional, default: 200 Maximum number of iterations damping : float, optional, default: 0.5 Damping factor between 0.5 and 1. copy : boolean, optional, default: True If copy is False, the affinity matrix is modified inplace by the algorithm, for memory efficiency verbose : boolean, optional, default: False The verbosity level return_n_iter : bool, default False Whether or not to return the number of iterations. Returns ------- cluster_centers_indices : array, shape (n_clusters,) index of clusters centers labels : array, shape (n_samples,) cluster labels for each point n_iter : int number of iterations run. Returned only if `return_n_iter` is set to True. Notes ----- For an example, see :ref:`examples/cluster/plot_affinity_propagation.py `. When the algorithm does not converge, it returns an empty array as ``cluster_center_indices`` and ``-1`` as label for each training sample. When all training samples have equal similarities and equal preferences, the assignment of cluster centers and labels depends on the preference. If the preference is smaller than the similarities, a single cluster center and label ``0`` for every sample will be returned. Otherwise, every training sample becomes its own cluster center and is assigned a unique label. References ---------- Brendan J. Frey and Delbert Dueck, "Clustering by Passing Messages Between Data Points", Science Feb. 2007 tcopyiis#S must be a square array (shape=%s)gà?sdamping must be >= 0.5 and < 1sTAll samples have mutually equal similarities. Returning arbitrary cluster center(s).NidtaxissConverged after %d iterations.sDid not convergesTAffinity propagation did not converge, this model will not have any cluster centers.iÿÿÿÿ('RRt ValueErrortreprtNoneRtmediantarrayRtwarningstwarnR tarangetrandomt RandomStatetzerostfinfotdoubletepsttinytrandntrangetaddtargmaxtinftmaxtsubtracttmaximumtsumtdiagRtclipt flatnonzerotsizetwheretnewaxistuniquet searchsortedR(RR tconvergence_itertmax_itertdampingRtverboset return_n_itert n_samplest random_statetAtRttmptetindtittItYtY2tdAtEtKtset unconvergedtctktiitjtlabelstcluster_centers_indices((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pytaffinity_propagation!s K    %/)0#  .  "      %;%  tAffinityPropagationcBsPeZdZddded ded„Zed„ƒZd d„Z d„Z RS( sdPerform Affinity Propagation Clustering of data. Read more in the :ref:`User Guide `. Parameters ---------- damping : float, optional, default: 0.5 Damping factor (between 0.5 and 1) is the extent to which the current value is maintained relative to incoming values (weighted 1 - damping). This in order to avoid numerical oscillations when updating these values (messages). max_iter : int, optional, default: 200 Maximum number of iterations. convergence_iter : int, optional, default: 15 Number of iterations with no change in the number of estimated clusters that stops the convergence. copy : boolean, optional, default: True Make a copy of input data. preference : array-like, shape (n_samples,) or float, optional Preferences for each point - points with larger values of preferences are more likely to be chosen as exemplars. The number of exemplars, ie of clusters, is influenced by the input preferences value. If the preferences are not passed as arguments, they will be set to the median of the input similarities. affinity : string, optional, default=``euclidean`` Which affinity to use. At the moment ``precomputed`` and ``euclidean`` are supported. ``euclidean`` uses the negative squared euclidean distance between points. verbose : boolean, optional, default: False Whether to be verbose. Attributes ---------- cluster_centers_indices_ : array, shape (n_clusters,) Indices of cluster centers cluster_centers_ : array, shape (n_clusters, n_features) Cluster centers (if affinity != ``precomputed``). labels_ : array, shape (n_samples,) Labels of each point affinity_matrix_ : array, shape (n_samples, n_samples) Stores the affinity matrix used in ``fit``. n_iter_ : int Number of iterations taken to converge. Examples -------- >>> from sklearn.cluster import AffinityPropagation >>> import numpy as np >>> X = np.array([[1, 2], [1, 4], [1, 0], ... [4, 2], [4, 4], [4, 0]]) >>> clustering = AffinityPropagation().fit(X) >>> clustering # doctest: +NORMALIZE_WHITESPACE AffinityPropagation(affinity='euclidean', convergence_iter=15, copy=True, damping=0.5, max_iter=200, preference=None, verbose=False) >>> clustering.labels_ array([0, 0, 0, 1, 1, 1]) >>> clustering.predict([[0, 0], [4, 4]]) array([0, 1]) >>> clustering.cluster_centers_ array([[1, 2], [4, 2]]) Notes ----- For an example, see :ref:`examples/cluster/plot_affinity_propagation.py `. The algorithmic complexity of affinity propagation is quadratic in the number of points. When ``fit`` does not converge, ``cluster_centers_`` becomes an empty array and all training samples will be labelled as ``-1``. In addition, ``predict`` will then label every sample as ``-1``. When all training samples have equal similarities and equal preferences, the assignment of cluster centers and labels depends on the preference. If the preference is smaller than the similarities, ``fit`` will result in a single cluster center and label ``0`` for every sample. Otherwise, every training sample becomes its own cluster center and is assigned a unique label. References ---------- Brendan J. Frey and Delbert Dueck, "Clustering by Passing Messages Between Data Points", Science Feb. 2007 gà?iÈit euclideancCsC||_||_||_||_||_||_||_dS(N(R:R9R8RR;R taffinity(tselfR:R9R8RR RVR;((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pyt__init__Qs      cCs |jdkS(Nt precomputed(RV(RW((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pyt _pairwise]scCsôt|ddƒ}|jdkr-||_nA|jdkrUt|dtƒ |_ntdt|jƒƒ‚t|j|jd|j d|j d |j d |j d |j d tƒ\|_|_|_|jdkrð||jj ƒ|_n|S( sr Create affinity matrix from negative euclidean distances, then apply affinity propagation clustering. Parameters ---------- X : array-like, shape (n_samples, n_features) or (n_samples, n_samples) Data matrix or, if affinity is ``precomputed``, matrix of similarities / affinities. y : Ignored t accept_sparsetcsrRYRUtsquareds=Affinity must be 'precomputed' or 'euclidean'. Got %s insteadR9R8R:RR;R<(RRVtaffinity_matrix_RtTrueRtstrRSR R9R8R:RR;tcluster_centers_indices_tlabels_tn_iter_tcluster_centers_(RWtXty((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pytfitas -cCs|t|dƒt|dƒs+tdƒ‚n|jjdkrMt||jƒStjdtƒt j dg|j dƒSdS(sUPredict the closest cluster each sample in X belongs to. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) New data to predict. Returns ------- labels : array, shape (n_samples,) Index of the cluster each sample belongs to. RaRds<Predict method is not supported when affinity='precomputed'.iszThis model does not have any cluster centers because affinity propagation did not converge. Labeling every sample as '-1'.iÿÿÿÿN( RthasattrRRdR3RRRRRRR(RWRe((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pytpredict„s  N( t__name__t __module__t__doc__R_RtFalseRXtpropertyRZRgRi(((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pyRTìsc    #(RltnumpyRRtsklearn.exceptionsRtbaseRRtutilsRRtutils.validationRtmetricsRRRRR_RmRSRT(((sDlib/python2.7/site-packages/sklearn/cluster/affinity_propagation_.pyts      É