ó ‡ˆ\c@ s­dZddlmZddlZddlZddlmZddlm Z ddl m Z ddl m Z dd lmZd „Zed „Zd e fd „ƒYZdS(s+ Maximum likelihood covariance estimator. iÿÿÿÿ(tdivisionN(tlinalgi(t BaseEstimator(t check_array(t fast_logdet(tpairwise_distancescC sW|jd}tj||ƒ t|ƒ}||tjdtjƒ8}|d}|S(s9Computes the sample mean of the log_likelihood under a covariance model computes the empirical expected log-likelihood (accounting for the normalization terms and scaling), allowing for universal comparison (beyond this software package) Parameters ---------- emp_cov : 2D ndarray (n_features, n_features) Maximum Likelihood Estimator of covariance precision : 2D ndarray (n_features, n_features) The precision matrix of the covariance model to be tested Returns ------- sample mean of the log-likelihood iig@(tshapetnptsumRtlogtpi(temp_covt precisiontptlog_likelihood_((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pytlog_likelihoods   cC sÂtj|ƒ}|jdkr3tj|dƒ}n|jddkrVtjdƒn|rtj|j|ƒ|jd}ntj |jddƒ}|jdkr¾tj |ggƒ}n|S(sBComputes the Maximum likelihood covariance estimator Parameters ---------- X : ndarray, shape (n_samples, n_features) Data from which to compute the covariance estimate assume_centered : boolean If True, data are not centered before computation. Useful when working with data whose mean is almost, but not exactly zero. If False, data are centered before computation. Returns ------- covariance : 2D ndarray, shape (n_features, n_features) Empirical covariance (Maximum Likelihood Estimator). iiÿÿÿÿisBOnly one sample available. You may want to reshape your data arraytbias(iiÿÿÿÿ( RtasarraytndimtreshapeRtwarningstwarntdottTtcovtarray(tXtassume_centeredt covariance((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pytempirical_covariance2s#tEmpiricalCovariancecB sbeZdZeed„Zd„Zd„Zd d„Z d d„Z deed„Z d„Z RS( sÖMaximum likelihood covariance estimator Read more in the :ref:`User Guide `. Parameters ---------- store_precision : bool Specifies if the estimated precision is stored. assume_centered : bool If True, data are not centered before computation. Useful when working with data whose mean is almost, but not exactly zero. If False (default), data are centered before computation. Attributes ---------- location_ : array-like, shape (n_features,) Estimated location, i.e. the estimated mean. covariance_ : 2D ndarray, shape (n_features, n_features) Estimated covariance matrix precision_ : 2D ndarray, shape (n_features, n_features) Estimated pseudo-inverse matrix. (stored only if store_precision is True) Examples -------- >>> import numpy as np >>> from sklearn.covariance import EmpiricalCovariance >>> from sklearn.datasets import make_gaussian_quantiles >>> real_cov = np.array([[.8, .3], ... [.3, .4]]) >>> np.random.seed(0) >>> X = np.random.multivariate_normal(mean=[0, 0], ... cov=real_cov, ... size=500) >>> cov = EmpiricalCovariance().fit(X) >>> cov.covariance_ # doctest: +ELLIPSIS array([[0.7569..., 0.2818...], [0.2818..., 0.3928...]]) >>> cov.location_ array([0.0622..., 0.0193...]) cC s||_||_dS(N(tstore_precisionR(tselfRR((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyt__init__ˆs cC s@t|ƒ}||_|jr3tj|ƒ|_n d|_dS(srSaves the covariance and precision estimates Storage is done accordingly to `self.store_precision`. Precision stored only if invertible. Parameters ---------- covariance : 2D ndarray, shape (n_features, n_features) Estimated covariance matrix to be stored, and from which precision is computed. N(Rt covariance_RRtpinvht precision_tNone(R R((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyt_set_covarianceŒs   cC s+|jr|j}ntj|jƒ}|S(s¹Getter for the precision matrix. Returns ------- precision_ : array-like The precision matrix associated to the current covariance object. (RR$RR#R"(R R ((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyt get_precision¢s  cC sit|ƒ}|jr1tj|jdƒ|_n|jdƒ|_t|d|jƒ}|j|ƒ|S(sÏFits the Maximum Likelihood Estimator covariance model according to the given training data and parameters. Parameters ---------- X : array-like, shape = [n_samples, n_features] Training data, where n_samples is the number of samples and n_features is the number of features. y not used, present for API consistence purpose. Returns ------- self : object iiR( RRRtzerosRt location_tmeanRR&(R RtyR((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pytfit±s   cC s2t||jdtƒ}t||jƒƒ}|S(sùComputes the log-likelihood of a Gaussian data set with `self.covariance_` as an estimator of its covariance matrix. Parameters ---------- X_test : array-like, shape = [n_samples, n_features] Test data of which we compute the likelihood, where n_samples is the number of samples and n_features is the number of features. X_test is assumed to be drawn from the same distribution than the data used in fit (including centering). y not used, present for API consistence purpose. Returns ------- res : float The likelihood of the data set with `self.covariance_` as an estimator of its covariance matrix. R(RR)tTrueRR'(R tX_testR+ttest_covtres((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pytscoreÎst frobeniuscC s­||j}|dkr/tj|dƒ}nB|dkretjtjtj|j|ƒƒƒ}n tdƒ‚|r‹||j d}n|rš|}ntj |ƒ}|S(s>Computes the Mean Squared Error between two covariance estimators. (In the sense of the Frobenius norm). Parameters ---------- comp_cov : array-like, shape = [n_features, n_features] The covariance to compare with. norm : str The type of norm used to compute the error. Available error types: - 'frobenius' (default): sqrt(tr(A^t.A)) - 'spectral': sqrt(max(eigenvalues(A^t.A)) where A is the error ``(comp_cov - self.covariance_)``. scaling : bool If True (default), the squared error norm is divided by n_features. If False, the squared error norm is not rescaled. squared : bool Whether to compute the squared error norm or the error norm. If True (default), the squared error norm is returned. If False, the error norm is returned. Returns ------- The Mean Squared Error (in the sense of the Frobenius norm) between `self` and `comp_cov` covariance estimators. R2itspectrals1Only spectral and frobenius norms are implementedi( R"RRtamaxRtsvdvalsRRtNotImplementedErrorRtsqrt(R tcomp_covtnormtscalingtsquaredterrort squared_normtresult((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyt error_normìs   *  cC sZ|jƒ}t||jtjdd…fddd|ƒ}tj|t|ƒfƒdS(sùComputes the squared Mahalanobis distances of given observations. Parameters ---------- X : array-like, shape = [n_samples, n_features] The observations, the Mahalanobis distances of the which we compute. Observations are assumed to be drawn from the same distribution than the data used in fit. Returns ------- dist : array, shape = [n_samples,] Squared Mahalanobis distances of the observations. Ntmetrict mahalanobistVIi(R'RR)RtnewaxisRtlen(R RR tdist((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyRA s "N( t__name__t __module__t__doc__R-tFalseR!R&R'R%R,R1R?RA(((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyRYs.     3(RHt __future__RRtnumpyRtscipyRtbaseRtutilsRt utils.extmathRtmetrics.pairwiseRRRIRR(((sGlib/python2.7/site-packages/sklearn/covariance/empirical_covariance_.pyts     '