ó ‡ˆ\c@s§dZddlZddlmZddlmZmZddlm Z ddl m Z ddl m Z dd lmZmZd e jeeeƒfd „ƒYZdS( s)Principal Component Analysis Base ClassesiÿÿÿÿN(tlinalgi(t BaseEstimatortTransformerMixin(t check_array(tcheck_is_fitted(tsix(tABCMetatabstractmethodt_BasePCAcBsDeZdZd„Zd„Zedd„ƒZd„Zd„Z RS(swBase class for PCA methods. Warning: This class should not be used directly. Use derived classes instead. cCs£|j}|j}|jrD|tj|dd…tjfƒ}ntj||jdƒ}tj|j ||ƒ}|j ddt |ƒd…c|j7<|S(srCompute data covariance with the generative model. ``cov = components_.T * S**2 * components_ + sigma2 * eye(n_features)`` where S**2 contains the explained variances, and sigma2 contains the noise variances. Returns ------- cov : array, shape=(n_features, n_features) Estimated covariance of data. Ngi( t components_texplained_variance_twhitentnptsqrttnewaxistmaximumtnoise_variance_tdottTtflattlen(tselfR texp_vart exp_var_difftcov((s9lib/python2.7/site-packages/sklearn/decomposition/base.pytget_covariances   ))cCse|jjd}|jdkr3tj|ƒ|jS|j|krUtj|jƒƒS|j}|j }|j r™|tj |dd…tj fƒ}ntj ||jdƒ}tj||jƒ|j}|jddt|ƒd…cd|7>> import numpy as np >>> from sklearn.decomposition import IncrementalPCA >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]]) >>> ipca = IncrementalPCA(n_components=2, batch_size=3) >>> ipca.fit(X) IncrementalPCA(batch_size=3, copy=True, n_components=2, whiten=False) >>> ipca.transform(X) # doctest: +SKIP tmean_R t all_or_anyN( RtallRR$tNoneR RR RR R R (RR!t X_transformed((s9lib/python2.7/site-packages/sklearn/decomposition/base.pyt transformcs  cCsd|jrFtj|tj|jdd…tjfƒ|jƒ|jStj||jƒ|jSdS(s_Transform data back to its original space. In other words, return an input X_original whose transform would be X. Parameters ---------- X : array-like, shape (n_samples, n_components) New data, where n_samples is the number of samples and n_components is the number of components. Returns ------- X_original array-like, shape (n_samples, n_features) Notes ----- If whitening is enabled, inverse_transform will compute the exact inverse operation, which includes reversing whitening. N(R R RR R RR R$(RR!((s9lib/python2.7/site-packages/sklearn/decomposition/base.pytinverse_transformˆs +N( t__name__t __module__t__doc__RR RR'R#R)R*(((s9lib/python2.7/site-packages/sklearn/decomposition/base.pyRs  ! %(R-tnumpyR tscipyRtbaseRRtutilsRtutils.validationRt externalsRtabcRRtwith_metaclassR(((s9lib/python2.7/site-packages/sklearn/decomposition/base.pyts