ó ‡ˆ\c@s{ddlZddlZddlmZddlmZmZddlm Z ddl m Z dee fd „ƒYZ dS( iÿÿÿÿNi(t MinCovDeti(tcheck_is_fittedt check_array(taccuracy_score(t OutlierMixintEllipticEnvelopecBskeZdZeed dd d„Zd d„Zd d„Zd„Z d„Z d d„Z e d„ƒZ RS( sÐ An object for detecting outliers in a Gaussian distributed dataset. Read more in the :ref:`User Guide `. Parameters ---------- store_precision : boolean, optional (default=True) Specify if the estimated precision is stored. assume_centered : boolean, optional (default=False) If True, the support of robust location and covariance estimates is computed, and a covariance estimate is recomputed from it, without centering the data. Useful to work with data whose mean is significantly equal to zero but is not exactly zero. If False, the robust location and covariance are directly computed with the FastMCD algorithm without additional treatment. support_fraction : float in (0., 1.), optional (default=None) The proportion of points to be included in the support of the raw MCD estimate. If None, the minimum value of support_fraction will be used within the algorithm: `[n_sample + n_features + 1] / 2`. contamination : float in (0., 0.5), optional (default=0.1) The amount of contamination of the data set, i.e. the proportion of outliers in the data set. random_state : int, RandomState instance or None, optional (default=None) The seed of the pseudo random number generator to use when shuffling the data. 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`. Attributes ---------- location_ : array-like, shape (n_features,) Estimated robust location covariance_ : array-like, shape (n_features, n_features) Estimated robust covariance matrix precision_ : array-like, shape (n_features, n_features) Estimated pseudo inverse matrix. (stored only if store_precision is True) support_ : array-like, shape (n_samples,) A mask of the observations that have been used to compute the robust estimates of location and shape. offset_ : float Offset used to define the decision function from the raw scores. We have the relation: ``decision_function = score_samples - offset_``. The offset depends on the contamination parameter and is defined in such a way we obtain the expected number of outliers (samples with decision function < 0) in training. See Also -------- EmpiricalCovariance, MinCovDet Notes ----- Outlier detection from covariance estimation may break or not perform well in high-dimensional settings. In particular, one will always take care to work with ``n_samples > n_features ** 2``. References ---------- .. [1] Rousseeuw, P.J., Van Driessen, K. "A fast algorithm for the minimum covariance determinant estimator" Technometrics 41(3), 212 (1999) gš™™™™™¹?c Cs8tt|ƒjd|d|d|d|ƒ||_dS(Ntstore_precisiontassume_centeredtsupport_fractiont random_state(tsuperRt__init__t contamination(tselfRRRR R ((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pyR Xs cCs:tt|ƒj|ƒtj|j d|jƒ|_|S(s Fit the EllipticEnvelope model. Parameters ---------- X : numpy array or sparse matrix, shape (n_samples, n_features). Training data y : Ignored not used, present for API consistency by convention. gY@(R Rtfittnpt percentiletdist_R toffset_(R tXty((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pyRbs  cCsat|dƒ|j|ƒ}|dk rVtjdtƒ|sV|j d| dSn||jS(s]Compute the decision function of the given observations. Parameters ---------- X : array-like, shape (n_samples, n_features) raw_values : bool, optional Whether or not to consider raw Mahalanobis distances as the decision function. Must be False (default) for compatibility with the others outlier detection tools. .. deprecated:: 0.20 ``raw_values`` has been deprecated in 0.20 and will be removed in 0.22. Returns ------- decision : array-like, shape (n_samples, ) Decision function of the samples. It is equal to the shifted Mahalanobis distances. The threshold for being an outlier is 0, which ensures a compatibility with other outlier detection algorithms. RsGraw_values parameter is deprecated in 0.20 and will be removed in 0.22.g…ëQ¸Õ?N(Rt score_samplestNonetwarningstwarntDeprecationWarningR(R Rt raw_valuestnegative_mahal_dist((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pytdecision_functionrs   cCst|dƒ|j|ƒ S(s(Compute the negative Mahalanobis distances. Parameters ---------- X : array-like, shape (n_samples, n_features) Returns ------- negative_mahal_distances : array-like, shape (n_samples, ) Opposite of the Mahalanobis distances. R(Rt mahalanobis(R R((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pyR™s cCsNt|ƒ}tj|jdddtƒ}|j|ƒ}d||dk<|S(sU Predict the labels (1 inlier, -1 outlier) of X according to the fitted model. Parameters ---------- X : array-like, shape (n_samples, n_features) Returns ------- is_inlier : array, shape (n_samples,) Returns -1 for anomalies/outliers and +1 for inliers. iiÿÿÿÿtdtypei(RRtfulltshapetintR(R Rt is_inliertvalues((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pytpredict¨s  cCst||j|ƒd|ƒS(s¦Returns the mean accuracy on the given test data and labels. In multi-label classification, this is the subset accuracy which is a harsh metric since you require for each sample that each label set be correctly predicted. Parameters ---------- X : array-like, shape (n_samples, n_features) Test samples. y : array-like, shape (n_samples,) or (n_samples, n_outputs) True labels for X. sample_weight : array-like, shape (n_samples,), optional Sample weights. Returns ------- score : float Mean accuracy of self.predict(X) wrt. y. t sample_weight(RR$(R RRR%((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pytscore½scCstjdtƒ|jS(NsGthreshold_ attribute is deprecated in 0.20 and will be removed in 0.22.(RRRR(R ((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pyt threshold_×s N(t__name__t __module__t__doc__tTruetFalseRR RRRR$R&tpropertyR'(((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pyR sJ   '   ( tnumpyRRtRtutils.validationRRtmetricsRtbaseRR(((sClib/python2.7/site-packages/sklearn/covariance/elliptic_envelope.pyts