{Kg8ddlZddlmZmZddlZddlmZmZm Z m Z ddl m Z ddl mZmZmZddlmZddlmZdd lmZd gZd ZGd d eeeZy) N)IntegralReal) BaseEstimatorMetaEstimatorMixin _fit_contextclone) safe_mask) HasMethodsInterval StrOptions)_RoutingNotSupportedMixin) available_if)check_is_fittedSelfTrainingClassifiercfd}|S)a2Check if we can delegate a method to the underlying estimator. First, we check the fitted `base_estimator_` if available, otherwise we check the unfitted `base_estimator`. We raise the original `AttributeError` if `attr` does not exist. This function is used together with `available_if`. cxt|drt|jyt|jy)Nbase_estimator_T)hasattrgetattrrbase_estimator)selfattrs j/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/sklearn/semi_supervised/_self_training.pycheckz_estimator_has..checks8 4* + D(($ / D'' .)rrs` r_estimator_hasrs Lrc eZdZUdZdZedggeedddgedd hgee d d dgee d d dd gd gdZ e e d< ddZ eddZeeddZeeddZeeddZeeddZeeddZy )raCSelf-training classifier. This :term:`metaestimator` allows a given supervised classifier to function as a semi-supervised classifier, allowing it to learn from unlabeled data. It does this by iteratively predicting pseudo-labels for the unlabeled data and adding them to the training set. The classifier will continue iterating until either max_iter is reached, or no pseudo-labels were added to the training set in the previous iteration. Read more in the :ref:`User Guide `. Parameters ---------- base_estimator : estimator object An estimator object implementing `fit` and `predict_proba`. Invoking the `fit` method will fit a clone of the passed estimator, which will be stored in the `base_estimator_` attribute. threshold : float, default=0.75 The decision threshold for use with `criterion='threshold'`. Should be in [0, 1). When using the `'threshold'` criterion, a :ref:`well calibrated classifier ` should be used. criterion : {'threshold', 'k_best'}, default='threshold' The selection criterion used to select which labels to add to the training set. If `'threshold'`, pseudo-labels with prediction probabilities above `threshold` are added to the dataset. If `'k_best'`, the `k_best` pseudo-labels with highest prediction probabilities are added to the dataset. When using the 'threshold' criterion, a :ref:`well calibrated classifier ` should be used. k_best : int, default=10 The amount of samples to add in each iteration. Only used when `criterion='k_best'`. max_iter : int or None, default=10 Maximum number of iterations allowed. Should be greater than or equal to 0. If it is `None`, the classifier will continue to predict labels until no new pseudo-labels are added, or all unlabeled samples have been labeled. verbose : bool, default=False Enable verbose output. Attributes ---------- base_estimator_ : estimator object The fitted estimator. classes_ : ndarray or list of ndarray of shape (n_classes,) Class labels for each output. (Taken from the trained `base_estimator_`). transduction_ : ndarray of shape (n_samples,) The labels used for the final fit of the classifier, including pseudo-labels added during fit. labeled_iter_ : ndarray of shape (n_samples,) The iteration in which each sample was labeled. When a sample has iteration 0, the sample was already labeled in the original dataset. When a sample has iteration -1, the sample was not labeled in any iteration. n_features_in_ : int Number of features seen during :term:`fit`. .. versionadded:: 0.24 feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 1.0 n_iter_ : int The number of rounds of self-training, that is the number of times the base estimator is fitted on relabeled variants of the training set. termination_condition_ : {'max_iter', 'no_change', 'all_labeled'} The reason that fitting was stopped. - `'max_iter'`: `n_iter_` reached `max_iter`. - `'no_change'`: no new labels were predicted. - `'all_labeled'`: all unlabeled samples were labeled before `max_iter` was reached. See Also -------- LabelPropagation : Label propagation classifier. LabelSpreading : Label spreading model for semi-supervised learning. References ---------- :doi:`David Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd annual meeting on Association for Computational Linguistics (ACL '95). Association for Computational Linguistics, Stroudsburg, PA, USA, 189-196. <10.3115/981658.981684>` Examples -------- >>> import numpy as np >>> from sklearn import datasets >>> from sklearn.semi_supervised import SelfTrainingClassifier >>> from sklearn.svm import SVC >>> rng = np.random.RandomState(42) >>> iris = datasets.load_iris() >>> random_unlabeled_points = rng.rand(iris.target.shape[0]) < 0.3 >>> iris.target[random_unlabeled_points] = -1 >>> svc = SVC(probability=True, gamma="auto") >>> self_training_model = SelfTrainingClassifier(svc) >>> self_training_model.fit(iris.data, iris.target) SelfTrainingClassifier(...) classifierfitgg?left)closed thresholdk_bestNrverboserr$ criterionr%max_iterr'_parameter_constraintsFcX||_||_||_||_||_||_y)Nr()rrr$r)r%r*r's r__init__zSelfTrainingClassifier.__init__s/-""    r)prefer_skip_nested_validationc2|j||gdd\}}t|j|_|jj dvr t d|dk7}tj|rtjdt|jdk(rL|j|jd tj|z kDrtjd ttj ||_tj$|d|_d |j&|<d |_tj|sB|j*|j(|j*kr|xj(d z c_|jj-|t/|||j"||jj1|t/||}|jj2tj4|d }tj6|d }|jdk(r||j8kD}nkt;|j|jd }||jd k(rtj<|t>}ntj@| |d |}tjB|d |} |||j"| <d|| <|j(|j&| <| jd d k(rd|_"ns|jFr)tId|j(d| jd dtj|s)|j*|j(|j*kr|j(|j*k(rd|_"tj|rd|_"|jj-|t/|||j"||jj2|_|S)a Fit self-training classifier using `X`, `y` as training data. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Array representing the data. y : {array-like, sparse matrix} of shape (n_samples,) Array representing the labels. Unlabeled samples should have the label -1. Returns ------- self : object Fitted estimator. )csrcsclildokF) accept_sparseforce_all_finite)USz~y has dtype string. If you wish to predict on string targets, use dtype object, and use -1 as the label for unlabeled samples.zy contains no unlabeled samplesr%rzsk_best is larger than the amount of unlabeled samples. All unlabeled samples will be labeled in the first iterationNr&)axisr$)dtypeT no_changezEnd of iteration z, added z new labels.r* all_labeled)%_validate_datar rrr:kind ValueErrornpallwarningswarn UserWarningr)r%shapesumcopy transduction_ full_like labeled_iter_n_iter_r*r!r predict_probaclasses_argmaxmaxr$min ones_likebool argpartitionnonzerotermination_condition_r'print) rXy has_labelprobpred max_probaselected n_to_select selected_fulls rr!zSelfTrainingClassifier.fitsv0"" q >X % KK!''!*rvvi'88 8 MM*   WWQZ\\!R0()9% &&# MM !T\\DMM%A LLA L  $ $)Ay)*D,>,>y,I  ''55a !iZ8P6QRD''004a1HIDt!,I~~,$t~~5!$++yq/AB )//!"44!||ITBH " z;G UHJJ z215h?M15XD  } -'+Im $04 D  } -""1%*.9+||' ~6+11!45\CM&&# MM !T\\DMM%AT <<4== (*4D ' 66) *7D '   i9% &(:(:9(E ,,55  rpredictcxt||j|ddd}|jj|S)a1Predict the classes of `X`. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Array representing the data. Returns ------- y : ndarray of shape (n_samples,) Array with predicted labels. TFr4r5reset)rr=rr`rrWs rr`zSelfTrainingClassifier.predict-sF     "   ##++A..rrLcxt||j|ddd}|jj|S)aWPredict probability for each possible outcome. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Array representing the data. Returns ------- y : ndarray of shape (n_samples, n_features) Array with prediction probabilities. TFrb)rr=rrLrds rrLz$SelfTrainingClassifier.predict_probaDsF     "   ##11!44rdecision_functioncxt||j|ddd}|jj|S)alCall decision function of the `base_estimator`. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Array representing the data. Returns ------- y : ndarray of shape (n_samples, n_features) Result of the decision function of the `base_estimator`. TFrb)rr=rrfrds rrfz(SelfTrainingClassifier.decision_function[F     "   ##55a88rpredict_log_probacxt||j|ddd}|jj|S)a_Predict log probability for each possible outcome. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Array representing the data. Returns ------- y : ndarray of shape (n_samples, n_features) Array with log prediction probabilities. TFrb)rr=rrirds rriz(SelfTrainingClassifier.predict_log_probarrhrscoreczt||j|ddd}|jj||S)aCall score on the `base_estimator`. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Array representing the data. y : array-like of shape (n_samples,) Array representing the labels. Returns ------- score : float Result of calling score on the `base_estimator`. TFrb)rr=rrk)rrWrXs rrkzSelfTrainingClassifier.scoresH"     "   ##))!Q//r)g?r$ rmF)__name__ __module__ __qualname____doc___estimator_typer r rr rr+dict__annotations__r-rr!rrr`rLrfrirkrrrrr'sErh#O &ug./tS#f=> +x!89:Haf=>h4?F; $D  &+l l\.+,/-/,.12535,.!456979,.!456979,.)*0+0r)rBnumbersrrnumpyr@baserrrr utilsr utils._param_validationr r r utils.metadata_routingrutils.metaestimatorsrutils.validationr__all__rrrrrr~sG"IIFF>/. # $&z01=z0r