rtjRdZddlZddlmZmZddlmZddlmZm Z ddl m Z ddl Z ddl mZddlmZmZmZdd lmZdd lmZdd lmZdd lmZmZmZmZmZmZdd l m!Z!m"Z"ddl#m$Z$m%Z%dZ&GddeeeZ'dS)zBase class for mixture models.N)ABCMetaabstractmethod) nullcontext)IntegralReal)time)cluster) BaseEstimator DensityMixin _fit_context)kmeans_plusplus)ConvergenceWarning)check_random_state)_is_numpy_namespace _logsumexp_max_precision_float_dtype get_namespaceget_namespace_and_devicemove_to)Interval StrOptions)check_is_fitted validate_datacV|j|krtd|d|d|jdS)zValidate the shape of the input parameter 'param'. Parameters ---------- param : array param_shape : tuple name : str zThe parameter 'z' should have the shape of z , but got N)shape ValueError)param param_shapenames S/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/sklearn/mixture/_base.py _check_shaper!sE {k!!jtt[[[%++ /   "!c,eZdZUdZeedddgeedddgeedddgeedddgeedddgehdgd gd gd geedddgd Ze e d <dZ e d&dZ d&dZe dZd&dZedd&dZd&dZe dZe dZe dZdZd&dZdZdZd'dZd&dZe d&d Ze d&d!Zd&d"Zd#Z d$Z!d%Z"dS)( BaseMixturezBase class for mixture models. This abstract class specifies an interface for all mixture classes and provides basic common methods for mixture models. Nleft)closedgr>kmeansrandomrandom_from_data k-means++ random_statebooleanverbose n_componentstol reg_covarmax_itern_init init_paramsr, warm_startr.verbose_interval_parameter_constraintsc ||_||_||_||_||_||_||_||_| |_| |_ dSNr/) selfr0r1r2r3r4r5r,r6r.r7s r __init__zBaseMixture.__init__GsT)"   &($ 0r"cdS)zCheck initial parameters of the derived class. Parameters ---------- X : array-like of shape (n_samples, n_features) Nr;Xxps r _check_parameterszBaseMixture._check_parameters_  r"ct||\}}}|j\}}|jdkrqtj||jf|j}tj|jd| |j }d|tj ||f<n;|jdkrb| | ||jf|j|}|||d d d |jfz}n|jd kr^|||jf|j|}|||jd } t#| D] \} } d|| | f< ne|jdkrZtj||jf|j}t%||j|\}} d|| tj |jf<|||d S)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. rAr()dtyper%) n_clustersr4r,r)sizerFdeviceaxisNr*F)rIreplacer+)r,)rrr5npzerosr0rFr KMeansfitlabels_arangeasarrayuniformsumnewaxischoice enumerater _initialize) r;r@r,rA_rK n_samplesresplabelindicescolindexs r _initialize_parametersz"BaseMixture._initialize_parametersis61r::: Avw 1  x ' '8Y(9:!'JJJD#0Q 12D9%%u, - -   ) )::$$9d6G*H$IIgD BFF4aF((BJ7 7DD  !3 3 388D-.agfD#)) 15*G(00 % % U#$UCZ   %   , ,8Y(9:!'JJJD(!)JAw ;)r;r@r^s r r[zBaseMixture._initializes  r"c2||||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_predict)r;r@ys r rRzBaseMixture.fits6 A r"T)prefer_skip_nested_validationct|\}}t|||j|jgd}|jd|jkr%t d|jd|jd||||jot|d }|r|j nd}|j }g}d |_ t|j} |j\} }t|D]c} || |r||| ||r|j n|j} g} |jdkr|}d}gd }td|jdzD]}| }|||\}}|||||||} | | | |z }|||t5||jkrd }n|| || |ks ||j kr!| }|}|}| }||_ e|j s%|jdkrt;jd t>| ||||_!||_||_"|||\}}|#|d 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. )rFensure_min_samplesrz:Expected n_samples >= n_components but got n_components = z, n_samples = rE converged_r%FTzBest performing initialization did not converge. Try different init parameters, or increase max_iter, tol, or check for degenerate data.rL)$rrfloat64float32rr0rrBr6hasattrr4infrlrr,range_print_verbose_msg_init_begrc lower_bound_r3_get_parameters_e_step_m_step_compute_lower_boundappend_print_verbose_msg_iter_endabsr1_print_verbose_msg_init_endwarningswarnr_set_parametersn_iter_ lower_bounds_argmax)r;r@rgrAr\do_initr4max_lower_boundbest_lower_boundsr,r]init lower_boundcurrent_lower_bounds best_params best_n_iter convergedn_iterprev_lower_bound log_prob_normlog_respchanges r rfzBaseMixture.fit_predictsC8a  A $"*bj)AVW X X X 71:) ) ),*.*;,, wqz,,  qR(((F74+F+FG '.Q6')$*;<< w 1&MM$ 0$ 0D  , ,T 2 2 2 D++A|+CCC%,C26''$2CK#% }!!"2244  ! #At}q'899  F'2$.2ll1l.D.D+M8LLHL444"&";";Hm"T"TK(// <<<(+;;F44VVDDD6{{TX--$( .00iHHH00Ow4N4N&1O"&"6"6"8"8K"(K(<%&/DO  4=1#4#4 M9#     [R000" +. ll1l,, 8yyy***r"ct||\}}|||\}}|||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. rE)r_estimate_log_prob_respmean)r;r@rAr\rrs r ruzBaseMixture._e_step:sN aB'''A"&">">qR">"H"H xww}%%x//r"cdS)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>)r;r@rs r rvzBaseMixture._m_stepNs  r"cdSr:r>)r;s r rtzBaseMixture._get_parameters\ r"cdSr:r>)r;paramss r r~zBaseMixture._set_parameters`rr"ct|t||d}t||dS)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. Fresetr%rL)rrr_estimate_weighted_log_prob)r;r@s r score_sampleszBaseMixture.score_samplesdsG  $ / / /$::1==AFFFFr"ct|\}}t|||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. )rfloatrr)r;r@rgrAr\s r scorezBaseMixture.scorews="a  ARWWT//2233444r"ct|t|\}}t||d}|||dS)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. Frr%rL)rrrrr)r;r@rAr\s r predictzBaseMixture.predicts[ a  A $ / / /yy99!<<1yEEEr"ct|t||d}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. FrrE)rrrrexp)r;r@rAr\rs r predict_probazBaseMixture.predict_probase  $ / / /a  A2212<< 8vvhr"c \ ttj\ }|dkrtdjzjj\}t j |tj tdj dkrdtj fdttjtdtjtdD}nj dkrJtj fdttjtdD}ndtj  fd ttjtdtjtdD}  fd t#t%D}t' } || |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. r%zNInvalid value for 'n_samples': %d . The sampling requires at least one sample.cpurArKfullc `g|]*\}}}||t|+Sr>)multivariate_normalint).0r covariancesamplerngs r z&BaseMixture.sample..sG2z6++D*c&kkJJr"tiedc g|]C\}}|tjtdt |DS)rr)rr covariances_rOr)rrrrr;s r rz&BaseMixture.sample..s`    'v ++ 1bGGGF    r"cxg|]6\}}}||ftj|zz7S)rH)standard_normalrOsqrt)rrrr n_featuresrs r rz&BaseMixture.sample..sa   3z6)) /C)DDgj))**   r"crg|]3}t||j4S)rJ)rrint64)ridevice_n_samples_comprAs r rz&BaseMixture.sample..sL   N1-..'RR   r"rJ)rrmeans_rr0rrr, multinomialrweights_rOcovariance_typevstackziprconcatrqlenrrU) r;r]r\r@rgmax_float_dtyperrrrrAs ` @@@@@r rzBaseMixture.samples 1$+>>Aw q==$'+'8:   ) : !233 wt}EBBB    6 ) ) 69 5AAA 1bGGG&77  AA !V + +       +. 5AAA>++     AA      7: 5AAA 1bGGG&77     A II      s>2233     57KKKzz!?7zCCQFFr"c^|||||zS)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) rE)_estimate_log_prob_estimate_log_weightsr?s r rz'BaseMixture._estimate_weighted_log_probs4&&qR&0043M3MQS3M3T3TTTr"cdS)zEstimate log-weights in EM algorithm, E[ log pi ] in VB algorithm. Returns ------- log_weight : array, shape (n_components, ) Nr>)r;rAs r rz!BaseMixture._estimate_log_weightsrCr"cdS)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) Nr>r?s r rzBaseMixture._estimate_log_probs  r"cDt||\}}|||}t|d|}t|rt jdn t }|5||dd|jfz }dddn #1swxYwY||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 rEr%)rMrAignore)underN)rrrrrOerrstaterrX)r;r@rAr\weighted_log_probrcontext_managerrs r rz#BaseMixture._estimate_log_prob_resp(s &aB'''A <>HI(0$$$ / .#"r"c |rdnd}|jdkrtd|dd S|jdkr3t|jz }td|d|dd |ddd Sd S) z.Print verbose message on the end of iteration.rzdid not converger%zInitialization .rjz . time lapse z.5fzs lower bound N)r.rrr)r;lbinit_has_converged converged_msgts r r{z'BaseMixture._print_verbose_msg_init_end^s'9Q ?Q <1   4M444 5 5 5 5 5 \Q  --A -aT       r"r:)r%)#__name__ __module__ __qualname____doc__rrrrr8dict__annotations__r<rrBrcr[rRr rfrurvrtr~rrrrrrrrrrrryr{r>r"r r$r$1s "(AtFCCCDsD8889htS$v>>>?Xh4???@8Haf===> JLLL M M (( k;%Xh4GGGH $ $D   1110   ^ 5"5"5"5"n   ^  <\555m+m+m+65m+^0000(   ^    ^   ^ GGG&5555(FFF&   (MGMGMGMG^ U U U U   ^     ^  ''''@888 0 0 0     r"r$) metaclass)(rr|abcrr contextlibrnumbersrrrnumpyrOsklearnr sklearn.baser r r sklearn.clusterr sklearn.exceptionsr sklearn.utilsrsklearn.utils._array_apirrrrrrsklearn.utils._param_validationrrsklearn.utils.validationrrr!r$r>r"r rs$$ ''''''''""""""""""""""BBBBBBBBBB++++++111111,,,,,,A@@@@@@@CCCCCCCC   $wwwww, wwwwwwr"