-i}hSSKJr SSKJrJr SSKrSSKJrJ r J r J r J r SSK Jr SSKJrJr SSKJrJr SS KJrJr SS KJrJrJrJr SS KJr SS KJ r J!r!J"r"J#r# SS K$J%r% SSK&J'r' SSK(J)r)J*r* SSK+J,r,J-r-J.r.J/r/J0r0 SSK1J2r2J3r3 Sr4"SS\ \ \5r5"SS\55r6Sr7Sr8"SS\55r9g))MutableMapping)IntegralRealN) BaseEstimatorClassifierMixinMetaEstimatorMixin _fit_contextclone)NotFittedError) check_scoringget_scorer_names) _CurveScorer!_threshold_scores_to_class_labels)_safe_indexingget_tags) HasMethodsInterval RealNotInt StrOptions)_get_response_values_binary)MetadataRouter MethodMapping_raise_for_paramsprocess_routing) available_if)type_of_target)Paralleldelayed)_check_method_params_estimator_has _num_samplescheck_is_fitted indexable)StratifiedShuffleSplitcheck_cvch[UR5 g![a [US5 gf=f)N estimator_)r# estimatorr )r*s d/var/www/html/venv/lib/python3.13/site-packages/sklearn/model_selection/_classification_threshold.py_check_is_fittedr,/s.1 ++, 1 <01s 11c,^\rSrSr%Sr\"SS/5\"SS/5/\"1Sk5/S.r\\ S'S S .S jr S r \ "S S9S5r \S5r\"\"S55S5r\"\"S55S5r\"\"S55S5rU4SjrSrU=r$)BaseThresholdClassifier6aBase class for binary classifiers that set a non-default decision threshold. In this base class, we define the following interface: - the validation of common parameters in `fit`; - the different prediction methods that can be used with the classifier. .. versionadded:: 1.5 Parameters ---------- estimator : estimator instance The binary classifier, fitted or not, for which we want to optimize the decision threshold used during `predict`. response_method : {"auto", "decision_function", "predict_proba"}, default="auto" Methods by the classifier `estimator` corresponding to the decision function for which we want to find a threshold. It can be: * if `"auto"`, it will try to invoke, for each classifier, `"predict_proba"` or `"decision_function"` in that order. * otherwise, one of `"predict_proba"` or `"decision_function"`. If the method is not implemented by the classifier, it will raise an error. fit predict_probadecision_function>autor1r2r*response_method_parameter_constraintsr3r5cXlX lgNr4)selfr*r5s r+__init__ BaseThresholdClassifier.__init__Ys ".cJURS:XaSS/nU$URnU$)zDefine the response method.r3r1r2r7)r:r5s r+_get_response_method,BaseThresholdClassifier._get_response_method]s6   6 ).0CDO#22Or=F)prefer_skip_nested_validationc r[X0S5 [X5up[USS9nUS:wa[SU35eUR"X40UD6 [ UR S5(aUR RUl[ UR S5(aUR RUlU$)VFit the classifier. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training data. y : array-like of shape (n_samples,) Target values. **params : dict Parameters to pass to the `fit` method of the underlying classifier. Returns ------- self : object Returns an instance of self. Ny) input_namebinaryz=Only binary classification is supported. Unknown label type: n_features_in_feature_names_in_) rr$r ValueError_fithasattrr)rGrH)r:XrDparamsy_types r+r0BaseThresholdClassifier.fites0 &-c2 X OPVxX  !!&! 4??$4 5 5"&//"@"@D  4??$7 8 8%)__%F%FD " r=c.URR$)zClasses labels.)r)classes_)r:s r+rQ BaseThresholdClassifier.classes_s'''r=ch[U5 [USUR5nURU5$)aPredict class probabilities for `X` using the fitted estimator. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training vectors, where `n_samples` is the number of samples and `n_features` is the number of features. Returns ------- probabilities : ndarray of shape (n_samples, n_classes) The class probabilities of the input samples. r))r,getattrr*r1r:rLr*s r+r1%BaseThresholdClassifier.predict_probas/ D,? &&q))r=predict_log_probach[U5 [USUR5nURU5$)aPredict logarithm class probabilities for `X` using the fitted estimator. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training vectors, where `n_samples` is the number of samples and `n_features` is the number of features. Returns ------- log_probabilities : ndarray of shape (n_samples, n_classes) The logarithm class probabilities of the input samples. r))r,rTr*rWrUs r+rW)BaseThresholdClassifier.predict_log_proba/ D,? **1--r=ch[U5 [USUR5nURU5$)a~Decision function for samples in `X` using the fitted estimator. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training vectors, where `n_samples` is the number of samples and `n_features` is the number of features. Returns ------- decisions : ndarray of shape (n_samples,) The decision function computed the fitted estimator. r))r,rTr*r2rUs r+r2)BaseThresholdClassifier.decision_functionrZr=c>[TU]5nSURl[ UR 5R RUR lU$)NF)super__sklearn_tags__classifier_tags multi_classrr* input_tagssparse)r:tags __class__s r+r_(BaseThresholdClassifier.__sklearn_tags__sDw')+0(!)$..!9!D!D!K!K r=)r*rHrGr5)__name__ __module__ __qualname____firstlineno____doc__rrr6dict__annotations__r;r?r r0propertyrQrr!r1rWr2r___static_attributes__ __classcell__res@r+r.r.6s8 / 0 23 4 ''UVW $D6</&+% %N((.12*3*$.!456.7.$.!456.7.$r=r.c^\rSrSr%Sr0\R E\"S15\/\\ SS/S.Er\ \ S'SSSS.U4S jjr \ S 5rS rS rS rSrU=r$)FixedThresholdClassifiera Binary classifier that manually sets the decision threshold. This classifier allows to change the default decision threshold used for converting posterior probability estimates (i.e. output of `predict_proba`) or decision scores (i.e. output of `decision_function`) into a class label. Here, the threshold is not optimized and is set to a constant value. Read more in the :ref:`User Guide `. .. versionadded:: 1.5 Parameters ---------- estimator : estimator instance The binary classifier, fitted or not, for which we want to optimize the decision threshold used during `predict`. threshold : {"auto"} or float, default="auto" The decision threshold to use when converting posterior probability estimates (i.e. output of `predict_proba`) or decision scores (i.e. output of `decision_function`) into a class label. When `"auto"`, the threshold is set to 0.5 if `predict_proba` is used as `response_method`, otherwise it is set to 0 (i.e. the default threshold for `decision_function`). pos_label : int, float, bool or str, default=None The label of the positive class. Used to process the output of the `response_method` method. When `pos_label=None`, if `y_true` is in `{-1, 1}` or `{0, 1}`, `pos_label` is set to 1, otherwise an error will be raised. response_method : {"auto", "decision_function", "predict_proba"}, default="auto" Methods by the classifier `estimator` corresponding to the decision function for which we want to find a threshold. It can be: * if `"auto"`, it will try to invoke `"predict_proba"` or `"decision_function"` in that order. * otherwise, one of `"predict_proba"` or `"decision_function"`. If the method is not implemented by the classifier, it will raise an error. Attributes ---------- estimator_ : estimator instance The fitted classifier used when predicting. classes_ : ndarray of shape (n_classes,) The class labels. n_features_in_ : int Number of features seen during :term:`fit`. Only defined if the underlying estimator exposes such an attribute when fit. feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Only defined if the underlying estimator exposes such an attribute when fit. See Also -------- sklearn.model_selection.TunedThresholdClassifierCV : Classifier that post-tunes the decision threshold based on some metrics and using cross-validation. sklearn.calibration.CalibratedClassifierCV : Estimator that calibrates probabilities. Examples -------- >>> from sklearn.datasets import make_classification >>> from sklearn.linear_model import LogisticRegression >>> from sklearn.metrics import confusion_matrix >>> from sklearn.model_selection import FixedThresholdClassifier, train_test_split >>> X, y = make_classification( ... n_samples=1_000, weights=[0.9, 0.1], class_sep=0.8, random_state=42 ... ) >>> X_train, X_test, y_train, y_test = train_test_split( ... X, y, stratify=y, random_state=42 ... ) >>> classifier = LogisticRegression(random_state=0).fit(X_train, y_train) >>> print(confusion_matrix(y_test, classifier.predict(X_test))) [[217 7] [ 19 7]] >>> classifier_other_threshold = FixedThresholdClassifier( ... classifier, threshold=0.1, response_method="predict_proba" ... ).fit(X_train, y_train) >>> print(confusion_matrix(y_test, classifier_other_threshold.predict(X_test))) [[184 40] [ 6 20]] r3booleanN) threshold pos_labelr6)rvrwr5c8>[TU]XS9 X0lX lgNr4)r^r;rwrv)r:r*rvrwr5res r+r;!FixedThresholdClassifier.__init__3s 9N""r=c[USS5=n(a UR$[UR5 URR$![a [ S5[ef=f)Nr)z+The underlying estimator is not fitted yet.)rTrQr#r*r AttributeError)r:r*s r+rQ!FixedThresholdClassifier.classes_?selD9 99 9%% % " DNN +>>** * " =! " "s *A A(c [US40UD6n[UR5R"X40URRD6UlU$)rCr0)rr r*r0r))r:rLrDrM routed_paramss r+rJFixedThresholdClassifier._fitKsF((e>v> /33AXM>V #(<(OUX !% 0   r=c[URRS9RUR[ 5RSSS9S9nU$) Get metadata routing of this object. Please check :ref:`User Guide ` on how the routing mechanism works. Returns ------- routing : MetadataRouter A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating routing information. ownerr0calleecallerr*method_mapping)rrergaddr*rr:routers r+get_metadata_routing-FixedThresholdClassifier.get_metadata_routingsL dnn&=&=>BBnn(?..eE.JC  r=)r)rwrv)rgrhrirjrkr.r6rrstrrlrmr;rnrQrJrrrorprqs@r+rsrssUn$ ! 8 8$ &*D1CD1$D # # " "0  Dr=rscUbR[X5[X5p[X$5[X%5p[XUS9n [XUS9n UR"X40U D6 OXUpn U"X U 40U D6$)a7Fit a classifier and compute the scores for different decision thresholds. Parameters ---------- classifier : estimator instance The classifier to fit and use for scoring. If `classifier` is already fitted, it will be used as is. X : {array-like, sparse matrix} of shape (n_samples, n_features) The entire dataset. y : array-like of shape (n_samples,) The entire target vector. fit_params : dict Parameters to pass to the `fit` method of the underlying classifier. train_idx : ndarray of shape (n_train_samples,) or None The indices of the training set. If `None`, `classifier` is expected to be already fitted. val_idx : ndarray of shape (n_val_samples,) The indices of the validation set used to score `classifier`. If `train_idx`, the entire set will be used. curve_scorer : scorer instance The scorer taking `classifier` and the validation set as input and outputting decision thresholds and scores as a curve. Note that this is different from the usual scorer that outputs a single score value as `curve_scorer` outputs a single score value for each threshold. score_params : dict Parameters to pass to the `score` method of the underlying scorer. Returns ------- scores : ndarray of shape (thresholds,) or tuple of such arrays The scores computed for each decision threshold. When TPR/TNR or precision/ recall are computed, `scores` is a tuple of two arrays. potential_thresholds : ndarray of shape (thresholds,) The decision thresholds used to compute the scores. They are returned in ascending order. indices)rr r0) classifierrLrD fit_params train_idxval_idx curve_scorer score_paramsX_trainX_valy_trainy_valfit_params_trainscore_params_vals r+_fit_and_score_over_thresholdsrsvp'5~a7Q'5~a7Q/yQ/Qw<+;<)*|&  5 E4D EEr=c [R"[X5VVs/sHup4[R"XU5PM snnSS9$s snnf)a8Compute the mean interpolated score across folds by defining common thresholds. Parameters ---------- target_thresholds : ndarray of shape (thresholds,) The thresholds to use to compute the mean score. cv_thresholds : ndarray of shape (n_folds, thresholds_fold) The thresholds used to compute the scores for each fold. cv_scores : ndarray of shape (n_folds, thresholds_fold) The scores computed for each threshold for each fold. Returns ------- mean_score : ndarray of shape (thresholds,) The mean score across all folds for each target threshold. r)axis)npmeanzipinterp)target_thresholds cv_thresholds cv_scoressplit_thresholds split_scores r+_mean_interpolated_scorersQ& 7725]1N 1N-  II'; G1N    s#A c ^\rSrSr%Sr0\R E\"\"\ "555\ \ /\ "\ SSSS9S/S\"S 15\ "\S S S S9/S /\ S/S/S /S.Er\\S'SSSSSSSSS.U4SjjrSrSrSrSrSrU=r$)TunedThresholdClassifierCViaxClassifier that post-tunes the decision threshold using cross-validation. This estimator post-tunes the decision threshold (cut-off point) that is used for converting posterior probability estimates (i.e. output of `predict_proba`) or decision scores (i.e. output of `decision_function`) into a class label. The tuning is done by optimizing a binary metric, potentially constrained by a another metric. Read more in the :ref:`User Guide `. .. versionadded:: 1.5 Parameters ---------- estimator : estimator instance The classifier, fitted or not, for which we want to optimize the decision threshold used during `predict`. scoring : str or callable, default="balanced_accuracy" The objective metric to be optimized. Can be one of: - str: string associated to a scoring function for binary classification, see :ref:`scoring_string_names` for options. - callable: a scorer callable object (e.g., function) with signature ``scorer(estimator, X, y)``. See :ref:`scoring_callable` for details. response_method : {"auto", "decision_function", "predict_proba"}, default="auto" Methods by the classifier `estimator` corresponding to the decision function for which we want to find a threshold. It can be: * if `"auto"`, it will try to invoke, for each classifier, `"predict_proba"` or `"decision_function"` in that order. * otherwise, one of `"predict_proba"` or `"decision_function"`. If the method is not implemented by the classifier, it will raise an error. thresholds : int or array-like, default=100 The number of decision threshold to use when discretizing the output of the classifier `method`. Pass an array-like to manually specify the thresholds to use. cv : int, float, cross-validation generator, iterable or "prefit", default=None Determines the cross-validation splitting strategy to train classifier. Possible inputs for cv are: * `None`, to use the default 5-fold stratified K-fold cross validation; * An integer number, to specify the number of folds in a stratified k-fold; * A float number, to specify a single shuffle split. The floating number should be in (0, 1) and represent the size of the validation set; * An object to be used as a cross-validation generator; * An iterable yielding train, test splits; * `"prefit"`, to bypass the cross-validation. Refer :ref:`User Guide ` for the various cross-validation strategies that can be used here. .. warning:: Using `cv="prefit"` and passing the same dataset for fitting `estimator` and tuning the cut-off point is subject to undesired overfitting. You can refer to :ref:`TunedThresholdClassifierCV_no_cv` for an example. This option should only be used when the set used to fit `estimator` is different from the one used to tune the cut-off point (by calling :meth:`TunedThresholdClassifierCV.fit`). refit : bool, default=True Whether or not to refit the classifier on the entire training set once the decision threshold has been found. Note that forcing `refit=False` on cross-validation having more than a single split will raise an error. Similarly, `refit=True` in conjunction with `cv="prefit"` will raise an error. n_jobs : int, default=None The number of jobs to run in parallel. When `cv` represents a cross-validation strategy, the fitting and scoring on each data split is done in parallel. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. random_state : int, RandomState instance or None, default=None Controls the randomness of cross-validation when `cv` is a float. See :term:`Glossary `. store_cv_results : bool, default=False Whether to store all scores and thresholds computed during the cross-validation process. Attributes ---------- estimator_ : estimator instance The fitted classifier used when predicting. best_threshold_ : float The new decision threshold. best_score_ : float or None The optimal score of the objective metric, evaluated at `best_threshold_`. cv_results_ : dict or None A dictionary containing the scores and thresholds computed during the cross-validation process. Only exist if `store_cv_results=True`. The keys are `"thresholds"` and `"scores"`. classes_ : ndarray of shape (n_classes,) The class labels. n_features_in_ : int Number of features seen during :term:`fit`. Only defined if the underlying estimator exposes such an attribute when fit. feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Only defined if the underlying estimator exposes such an attribute when fit. See Also -------- sklearn.model_selection.FixedThresholdClassifier : Classifier that uses a constant threshold. sklearn.calibration.CalibratedClassifierCV : Estimator that calibrates probabilities. Examples -------- >>> from sklearn.datasets import make_classification >>> from sklearn.ensemble import RandomForestClassifier >>> from sklearn.metrics import classification_report >>> from sklearn.model_selection import TunedThresholdClassifierCV, train_test_split >>> X, y = make_classification( ... n_samples=1_000, weights=[0.9, 0.1], class_sep=0.8, random_state=42 ... ) >>> X_train, X_test, y_train, y_test = train_test_split( ... X, y, stratify=y, random_state=42 ... ) >>> classifier = RandomForestClassifier(random_state=0).fit(X_train, y_train) >>> print(classification_report(y_test, classifier.predict(X_test))) precision recall f1-score support 0 0.94 0.99 0.96 224 1 0.80 0.46 0.59 26 accuracy 0.93 250 macro avg 0.87 0.72 0.77 250 weighted avg 0.93 0.93 0.92 250 >>> classifier_tuned = TunedThresholdClassifierCV( ... classifier, scoring="balanced_accuracy" ... ).fit(X_train, y_train) >>> print( ... f"Cut-off point found at {classifier_tuned.best_threshold_:.3f}" ... ) Cut-off point found at 0.342 >>> print(classification_report(y_test, classifier_tuned.predict(X_test))) precision recall f1-score support 0 0.96 0.95 0.96 224 1 0.61 0.65 0.63 26 accuracy 0.92 250 macro avg 0.78 0.80 0.79 250 weighted avg 0.92 0.92 0.92 250 r%Nleft)closedz array-like cv_objectprefitrg?neitherru random_state)scoring thresholdscvrefitn_jobsrstore_cv_resultsr6balanced_accuracyr3dTF)rr5rrrrrrct>[T U]XS9 X lX@lXPlX`lXplXlXlgry) r^r;rrrrrrr) r:r*rr5rrrrrrres r+r;#TunedThresholdClassifierCV.__init__s: 9N $  ( 0r=c 0^^^^^^[TR[5(a:STRs=:aS:a#O O [STRTRS9mOTRS:Xa>TR SLa [ S5e[TRS5 TRmOC[TRTSS 9mTR S LaTR5S:a [ S 5e[TS 40UD6mTR5TlTS:Xa6TRTlTRmS [![#T554/nGO [%TR5Tl[%TR5mTR&"TT40TR(R&D6nTR (aTTTRR*pnOj[-TR&"TT40TR(R&D65up[/TU 5n[/TU 5n[1TTRR*U S9nTRR*"Xg40UD6 [3[5TR6S9"UUUUUU4SjU556up[9SU 55(a [ S5e[;SU 55n [=SU 55n[TR>[@5(a [BRD"XTR>S9nO [BRF"TR>5n[IXU 5nURK5nUUTl&UUTl'TRP(a UUS.Tl)T$![an[S5UeS nAff=f)aFit the classifier and post-tune the decision threshold. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training data. y : array-like of shape (n_samples,) Target values. **params : dict Parameters to pass to the `fit` method of the underlying classifier and to the `scoring` scorer. Returns ------- self : object Returns an instance of self. rr%)n_splits test_sizerrTz'When cv='prefit', refit cannot be True.rQz-When cv='prefit', `estimator` must be fitted.N)rDrFz1When cv has several folds, refit cannot be False.r0r)rc 3># UHdup[[5"TS:wa [T5OTTTTRRUUTR TR RS9v Mf g7f)r)rrrrrN)rrr r*r0 _curve_scorerscorerscore) .0rrrLrrrr:rDs r+ 2TunedThresholdClassifierCV._fit.. sm *+1&I67)+xE*%Z,66::'#!%!3!3!.!5!5!;!; +1sA,A/c3\# UH"n[R"USUS5v M$ g7f)rN)risclose)rths r+rrs&A=Rrzz"Q%B((=s*,zrThe provided estimator makes constant predictions. Therefore, it is impossible to optimize the decision threshold.c3@# UHoR5v M g7fr9)minrrs r+rr! ;H'7 " "=c3@# UHoR5v M g7fr9)maxrs r+rr$rr)num)rscores)* isinstancerrr&rrrIr#r*r r' get_n_splitsr_get_curve_scorerrr)ranger"r splitsplitterr0nextrr rrranyrrrrrlinspaceasarrayrargmax best_score_best_threshold_r cv_results_)r:rLrDrMexcsplitsrrrrrrr min_threshold max_thresholddecision_thresholdsobjective_scoresbest_idxrrrs``` @@@r+rJTunedThresholdClassifierCV._fits5( dggt $ $TWWq'dggDv> !335 >"nnDOJU<?345F#DNN3DOt~~.JXXaCm&<&<&B&BCFzz56=;R;R;V;V"2"2 $BHHQ$R]5K5K5Q5Q$RS (I6(I6#7}..22I$  OO   E4D E#& T[[ ) * *+1 * $  A=A A AA   ;H   ;H   doox 0 0"$++$//# #%**T__"= 3   $**,+H528<  1* D   q" $G s M:: N NNc[US5 URR5n[URUUR 5US9up4[ X0RURU5$)rr))rw) r#r_get_pos_labelrr)r?rrrQ)r:rLrwrrs r+r"TunedThresholdClassifierCV.predict<sg l+&&557 0 OO  % % '  1 ))4==)  r=c\[URRS9RUR[ 5RSSS9S9RUR [ 5RSSS9S9RUR5[ 5RSSS9S9nU$) rrr0rrr)rrr)rr)rrergrr*rrrrs r+r/TunedThresholdClassifierCV.get_metadata_routingVs !8!8 9 S..,22%2NS,22'%2PS--/,22'%2P  r=c[URURS9n[R"XR 5UR 5nU$)z8Get the curve scorer based on the objective metric used.)r)r r*rr from_scorerr?r)r:rrs r+r,TunedThresholdClassifierCV._get_curve_scorerss@ E#// ..0$// r=) rrrrrr)rrrrrr)rgrhrirjrkr.r6rsetrcallablerrrrrlrmr;rJrrrrorprqs@r+rrsaF$ ! 8 8$ s+-. /    !T&A<P  z " Zc) < T"'(&K!$D.$ 11,un 4:r=r):collections.abcrnumbersrrnumpyrbaserrr r r exceptionsr metricsr rmetrics._scorerrrutilsrrutils._param_validationrrrrutils._responserutils.metadata_routingrrrrutils.metaestimatorsrutils.multiclassrutils.parallelrrutils.validationr r!r"r#r$_splitr&r'r,r.rsrrrr=r+rs+"(-RR9 0-.51\o/A=\~@6@FAFH8A!8Ar=