ó ‡ˆ\c@ sÔdZddlmZddlZddlZddlmZddlmZddlm Z dd l m Z dd l m Z dd l mZd „Zd ddd„Zd„Zd d„Zd„Zd„ZdS(s Unsupervised evaluation metrics.iÿÿÿÿ(tdivisionNi(tcheck_random_state(t check_X_y(t safe_indexingi(tpairwise_distances_chunked(tpairwise_distances(t LabelEncodercC s3d|ko|kns/td|ƒ‚ndS(s¥Check that number of labels are valid. Parameters ---------- n_labels : int Number of labels n_samples : int Number of samples isGNumber of labels is %d. Valid values are 2 to n_samples - 1 (inclusive)N(t ValueError(tn_labelst n_samples((sClib/python2.7/site-packages/sklearn/metrics/cluster/unsupervised.pytcheck_number_of_labelss t euclideancK s¸|dk r™t||dddgƒ\}}t|ƒ}|j|jdƒ| }|dkr||j|j||}}q™||||}}ntjt||d||ƒS(s Compute the mean Silhouette Coefficient of all samples. The Silhouette Coefficient is calculated using the mean intra-cluster distance (``a``) and the mean nearest-cluster distance (``b``) for each sample. The Silhouette Coefficient for a sample is ``(b - a) / max(a, b)``. To clarify, ``b`` is the distance between a sample and the nearest cluster that the sample is not a part of. Note that Silhouette Coefficient is only defined if number of labels is 2 <= n_labels <= n_samples - 1. This function returns the mean Silhouette Coefficient over all samples. To obtain the values for each sample, use :func:`silhouette_samples`. The best value is 1 and the worst value is -1. Values near 0 indicate overlapping clusters. Negative values generally indicate that a sample has been assigned to the wrong cluster, as a different cluster is more similar. Read more in the :ref:`User Guide `. Parameters ---------- X : array [n_samples_a, n_samples_a] if metric == "precomputed", or, [n_samples_a, n_features] otherwise Array of pairwise distances between samples, or a feature array. labels : array, shape = [n_samples] Predicted labels for each sample. metric : string, or callable The metric to use when calculating distance between instances in a feature array. If metric is a string, it must be one of the options allowed by :func:`metrics.pairwise.pairwise_distances `. If X is the distance array itself, use ``metric="precomputed"``. sample_size : int or None The size of the sample to use when computing the Silhouette Coefficient on a random subset of the data. If ``sample_size is None``, no sampling is used. random_state : int, RandomState instance or None, optional (default=None) The generator used to randomly select a subset of samples. If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. Used when ``sample_size is not None``. **kwds : optional keyword parameters Any further parameters are passed directly to the distance function. If using a scipy.spatial.distance metric, the parameters are still metric dependent. See the scipy docs for usage examples. Returns ------- silhouette : float Mean Silhouette Coefficient for all samples. References ---------- .. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the Interpretation and Validation of Cluster Analysis". Computational and Applied Mathematics 20: 53-65. `_ .. [2] `Wikipedia entry on the Silhouette Coefficient `_ t accept_sparsetcsctcsrit precomputedtmetricN( tNoneRRt permutationtshapetTtnptmeantsilhouette_samples(tXtlabelsRt sample_sizet random_statetkwdstindices((sClib/python2.7/site-packages/sklearn/metrics/cluster/unsupervised.pytsilhouette_score&sG !  "c C sßtjt|ƒt|ƒfd|jƒ}xItt|ƒƒD]5}||ctj|d||dt|ƒƒ7`. Parameters ---------- X : array [n_samples_a, n_samples_a] if metric == "precomputed", or, [n_samples_a, n_features] otherwise Array of pairwise distances between samples, or a feature array. labels : array, shape = [n_samples] label values for each sample metric : string, or callable The metric to use when calculating distance between instances in a feature array. If metric is a string, it must be one of the options allowed by :func:`sklearn.metrics.pairwise.pairwise_distances`. If X is the distance array itself, use "precomputed" as the metric. `**kwds` : optional keyword parameters Any further parameters are passed directly to the distance function. If using a ``scipy.spatial.distance`` metric, the parameters are still metric dependent. See the scipy docs for usage examples. Returns ------- silhouette : array, shape = [n_samples] Silhouette Coefficient for each samples. References ---------- .. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the Interpretation and Validation of Cluster Analysis". Computational and Applied Mathematics 20: 53-65. `_ .. [2] `Wikipedia entry on the Silhouette Coefficient `_ R R RRRR,t reduce_funcitmodetcliptdividetignoretinvalidN(RRt fit_transformR$RR&R tclasses_t functoolstpartialR2tzipRt concatenatettaketerrstatetmaximumt nan_to_num( RRRRtleR R,R3tresultsR0R1tdenomt sil_samples((sClib/python2.7/site-packages/sklearn/metrics/cluster/unsupervised.pyR˜s*`. Parameters ---------- X : array-like, shape (``n_samples``, ``n_features``) List of ``n_features``-dimensional data points. Each row corresponds to a single data point. labels : array-like, shape (``n_samples``,) Predicted labels for each sample. Returns ------- score : float The resulting Calinski-Harabaz score. References ---------- .. [1] `T. Calinski and J. Harabasz, 1974. "A dendrite method for cluster analysis". Communications in Statistics `_ gR"iigð?(gg( RRR9RR$R:R RRR%tsum( RRRCR t_Rt extra_dispt intra_dispRtkt cluster_ktmean_k((sClib/python2.7/site-packages/sklearn/metrics/cluster/unsupervised.pytcalinski_harabaz_scoreïs    % c C szt||ƒ\}}tƒ}|j|ƒ}|j\}}t|jƒ}t||ƒtj|ƒ}tj|t|dƒfdtj ƒ}xdt |ƒD]V}t |||kƒ} | j ddƒ} | ||`. Parameters ---------- X : array-like, shape (``n_samples``, ``n_features``) List of ``n_features``-dimensional data points. Each row corresponds to a single data point. labels : array-like, shape (``n_samples``,) Predicted labels for each sample. Returns ------- score: float The resulting Davies-Bouldin score. References ---------- .. [1] Davies, David L.; Bouldin, Donald W. (1979). `"A Cluster Separation Measure" `__. IEEE Transactions on Pattern Analysis and Machine Intelligence. PAMI-1 (2): 224-227 iRR"gNi(RRR9RR$R:R RR#tfloatR%RRtaverageRtallcloseRtnanR(tnanmax( RRRCR RHRt intra_distst centroidsRKRLtcentroidtcentroid_distancestscore((sClib/python2.7/site-packages/sklearn/metrics/cluster/unsupervised.pytdavies_bouldin_score#s(  (   $(t__doc__t __future__RR;tnumpyRtutilsRRRtpairwiseRRt preprocessingRR RRR2RRNRY(((sClib/python2.7/site-packages/sklearn/metrics/cluster/unsupervised.pyts     Q W 4