U mdI@sdZddlZddlmZmZddlmZddlmZmZddl Z ddl m Z ddl mZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZmZddZGdddeeedZdS)zBase class for mixture models.N)ABCMetaabstractmethod)time)IntegralReal) logsumexp)cluster)kmeans_plusplus) BaseEstimator) DensityMixin)ConvergenceWarning)check_random_state)check_is_fitted)Interval StrOptionscCs,t|}|j|kr(td|||jfdS)zValidate the shape of the input parameter 'param'. Parameters ---------- param : array param_shape : tuple name : str z:The parameter '%s' should have the shape of %s, but got %sN)nparrayshape ValueError)paramZ param_shapenamerN/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/mixture/_base.py _check_shapes   rc@speZdZUdZeeddddgeeddddgeeddddgeeddddgeeddddgedd d d hgd gd gdgeeddddgd Ze e d<ddZ e ddZ ddZe ddZd=ddZd>ddZddZe dd Ze d!d"Ze d#d$Zd%d&Zd?d'd(Zd)d*Zd+d,Zd@d-d.Zd/d0Ze d1d2Ze d3d4Zd5d6Zd7d8Zd9d:Z d;d<Z!dS)A BaseMixturezBase class for mixture models. This abstract class specifies an interface for all mixture classes and provides basic common methods for mixture models. Nleft)closedgrkmeansrandomrandom_from_data k-means++ random_statebooleanverbose n_componentstol reg_covarmax_itern_init init_paramsr# warm_startr%verbose_interval_parameter_constraintsc Cs@||_||_||_||_||_||_||_||_| |_| |_ dSNr&) selfr'r(r)r*r+r,r#r-r%r.rrr__init__Bs zBaseMixture.__init__cCsdS)zCheck initial parameters of the derived class. Parameters ---------- X : array-like of shape (n_samples, n_features) Nrr1Xrrr_check_parametersZszBaseMixture._check_parameterscCs4|j\}}|jdkrRt||jf}tj|jd|d|j}d|t ||f<n|jdkr|j ||jfd}||j ddddtj f}n|jdkrt||jf}|j ||jd d }d||t |jf<nT|jd krt||jf}t||j|d \}}d||t |jf<ntd |j|||dS)a?Initialize the model parameters. Parameters ---------- X : array-like of shape (n_samples, n_features) random_state : RandomState A random number generator instance that controls the random seed used for the method chosen to initialize the parameters. rr)Z n_clustersr+r#r sizeZaxisNr!F)r7replacer")r#z(Unimplemented initialization method '%s')rr,rZzerosr'r ZKMeansfitZlabels_Zarangeuniformsumnewaxischoicer r _initialize)r1r4r# n_samples_resplabelindicesrrr_initialize_parametersdsF       z"BaseMixture._initialize_parameterscCsdS)zInitialize the model parameters of the derived class. Parameters ---------- X : array-like of shape (n_samples, n_features) resp : array-like of shape (n_samples, n_components) Nr)r1r4rBrrrr?s zBaseMixture._initializecCs||||S)aEstimate model parameters with the EM algorithm. The method fits the model ``n_init`` times and sets the parameters with which the model has the largest likelihood or lower bound. Within each trial, the method iterates between E-step and M-step for ``max_iter`` times until the change of likelihood or lower bound is less than ``tol``, otherwise, a ``ConvergenceWarning`` is raised. If ``warm_start`` is ``True``, then ``n_init`` is ignored and a single initialization is performed upon the first call. Upon consecutive calls, training starts where it left off. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : Ignored Not used, present for API consistency by convention. Returns ------- self : object The fitted mixture. ) fit_predictr1r4yrrrr:s zBaseMixture.fitcCs||j|tjtjgdd}|jd|jkrLtd|jd|jd|||j odt |d }|rr|j nd}tj }d|_ t|j}|j\}}t|D]} || |r||||rtj n|j} |jdkr|} d} qtd|jdD]\} | }||\}}||||||} | |}|| |t||jkrd |_ qVq|| | |ksv|tj kr| }|} | } q|j s|jdkrtd | dt| | | |_!||_||\}}|j"dd S) aEstimate model parameters using X and predict the labels for X. The method fits the model n_init times and sets the parameters with which the model has the largest likelihood or lower bound. Within each trial, the method iterates between E-step and M-step for `max_iter` times until the change of likelihood or lower bound is less than `tol`, otherwise, a :class:`~sklearn.exceptions.ConvergenceWarning` is raised. After fitting, it predicts the most probable label for the input data points. .. versionadded:: 0.20 Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : Ignored Not used, present for API consistency by convention. Returns ------- labels : array, shape (n_samples,) Component labels. r)dtypeZensure_min_samplesrz:Expected n_samples >= n_components but got n_components = z, n_samples = converged_rFTzzInitialization %d did not converge. Try different init parameters, or increase max_iter, tol or check for degenerate data.r8)#Z_validate_params_validate_datarZfloat64Zfloat32rr'rr5r-hasattrr+infrJrr#range_print_verbose_msg_init_begrEZ lower_bound_r*_get_parameters_e_step_m_stepZ_compute_lower_bound_print_verbose_msg_iter_endabsr(_print_verbose_msg_init_endwarningswarnr _set_parametersZn_iter_argmax)r1r4rHZdo_initr+Zmax_lower_boundr#r@rAinit lower_boundZ best_paramsZ best_n_itern_iterZprev_lower_bound log_prob_normlog_respZchangerrrrFs`            zBaseMixture.fit_predictcCs||\}}t||fS)aE step. Parameters ---------- X : array-like of shape (n_samples, n_features) Returns ------- log_prob_norm : float Mean of the logarithms of the probabilities of each sample in X log_responsibility : array, shape (n_samples, n_components) Logarithm of the posterior probabilities (or responsibilities) of the point of each sample in X. )_estimate_log_prob_resprmean)r1r4r]r^rrrrQ%szBaseMixture._e_stepcCsdS)a*M step. Parameters ---------- X : array-like of shape (n_samples, n_features) log_resp : array-like of shape (n_samples, n_components) Logarithm of the posterior probabilities (or responsibilities) of the point of each sample in X. Nr)r1r4r^rrrrR8s zBaseMixture._m_stepcCsdSr0rr1rrrrPFszBaseMixture._get_parameterscCsdSr0r)r1paramsrrrrXJszBaseMixture._set_parameterscCs(t||j|dd}t||ddS)aCompute the log-likelihood of each sample. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. Returns ------- log_prob : array, shape (n_samples,) Log-likelihood of each sample in `X` under the current model. Fresetrr8)rrKr_estimate_weighted_log_probr3rrr score_samplesNszBaseMixture.score_samplescCs||S)aCompute the per-sample average log-likelihood of the given data X. Parameters ---------- X : array-like of shape (n_samples, n_dimensions) List of n_features-dimensional data points. Each row corresponds to a single data point. y : Ignored Not used, present for API consistency by convention. Returns ------- log_likelihood : float Log-likelihood of `X` under the Gaussian mixture model. )rfr`rGrrrscoreaszBaseMixture.scorecCs(t||j|dd}||jddS)aPredict the labels for the data samples in X using trained model. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. Returns ------- labels : array, shape (n_samples,) Component labels. Frcrr8)rrKrerYr3rrrpredicttszBaseMixture.predictcCs.t||j|dd}||\}}t|S)aEvaluate the components' density for each sample. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. Returns ------- resp : array, shape (n_samples, n_components) Density of each Gaussian component for each sample in X. Frc)rrKr_rexp)r1r4rAr^rrr predict_probaszBaseMixture.predict_probacst|dkrtdjjj\}tj|j}j dkrrt fddt jj |D}nTj dkrt fddt j|D}n&t fddt jj |D}t d dt|D}||fS) ayGenerate random samples from the fitted Gaussian distribution. Parameters ---------- n_samples : int, default=1 Number of samples to generate. Returns ------- X : array, shape (n_samples, n_features) Randomly generated sample. y : array, shape (nsamples,) Component labels. rzNInvalid value for 'n_samples': %d . The sampling requires at least one sample.fullcs$g|]\}}}||t|qSr)multivariate_normalint.0r`Z covariancesample)rngrr sz&BaseMixture.sample..Ztiedcs$g|]\}}|jt|qSr)rl covariances_rm)ror`rp)rqr1rrrrscs0g|](\}}}|j|fdt|qS)r6)Zstandard_normalrsqrtrn) n_featuresrqrrrrs cSs g|]\}}tj||tdqS))rI)rrkrm)rojrprrrrrs)rrr'Zmeans_rrr#Z multinomialZweights_Zcovariance_typerZvstackziprsZ concatenate enumerate)r1r@rAZn_samples_compr4rHr)rurqr1rrpsN         zBaseMixture.samplecCs|||S)aEstimate the weighted log-probabilities, log P(X | Z) + log weights. Parameters ---------- X : array-like of shape (n_samples, n_features) Returns ------- weighted_log_prob : array, shape (n_samples, n_component) )_estimate_log_prob_estimate_log_weightsr3rrrres z'BaseMixture._estimate_weighted_log_probcCsdS)zEstimate log-weights in EM algorithm, E[ log pi ] in VB algorithm. Returns ------- log_weight : array, shape (n_components, ) Nrrarrrrzsz!BaseMixture._estimate_log_weightscCsdS)a9Estimate the log-probabilities log P(X | Z). Compute the log-probabilities per each component for each sample. Parameters ---------- X : array-like of shape (n_samples, n_features) Returns ------- log_prob : array, shape (n_samples, n_component) Nrr3rrrryszBaseMixture._estimate_log_probc CsL||}t|dd}tjdd||ddtjf}W5QRX||fS)a@Estimate log probabilities and responsibilities for each sample. Compute the log probabilities, weighted log probabilities per component and responsibilities for each sample in X with respect to the current state of the model. Parameters ---------- X : array-like of shape (n_samples, n_features) Returns ------- log_prob_norm : array, shape (n_samples,) log p(X) log_responsibilities : array, shape (n_samples, n_components) logarithm of the responsibilities rr8ignore)ZunderN)rerrZerrstater=)r1r4Zweighted_log_probr]r^rrrr_s    z#BaseMixture._estimate_log_prob_respcCsB|jdkrtd|n&|jdkr>td|t|_|j|_dS)(Print verbose message on initialization.rzInitialization %drN)r%printr_init_prev_time_iter_prev_time)r1r+rrrrOs    z'BaseMixture._print_verbose_msg_init_begcCsX||jdkrT|jdkr&td|n.|jdkrTt}td|||j|f||_dS)r|rrz Iteration %drz0 Iteration %d time lapse %.5fs ll change %.5fN)r.r%r}rr)r1r\Zdiff_llZcur_timerrrrS!s  z'BaseMixture._print_verbose_msg_iter_endcCsD|jdkrtd|jn&|jdkr@td|jt|j|fdS)z.Print verbose message on the end of iteration.rzInitialization converged: %srz7Initialization converged: %s time lapse %.5fs ll %.5fN)r%r}rJrr~)r1llrrrrU.s  z'BaseMixture._print_verbose_msg_init_end)N)N)N)r)"__name__ __module__ __qualname____doc__rrrrr/dict__annotations__r2rr5rEr?r:rFrQrRrPrXrfrgrhrjrprerzryr_rOrSrUrrrrr,sT  /  h     >     r) metaclass)rrVabcrrrnumbersrrnumpyrZ scipy.specialrr r baser r exceptionsr utilsrZutils.validationrZutils._param_validationrrrrrrrrs