o tBhc@sdZddlZddlmZddlmZddlmZm Z ddl Z ddl m Z m Z dd l mZmZmZdd lmZGd d d eeeZGd ddeeeZdS)zNearest Neighbor ClassificationN)stats) weighted_mode) _is_arraylike _num_samples)_check_weights _get_weights) NeighborsBaseKNeighborsMixinRadiusNeighborsMixin)ClassifierMixinc sVeZdZdZ ddddddddd fd d Zd d ZddZddZddZZ S)KNeighborsClassifiera!Classifier implementing the k-nearest neighbors vote. Read more in the :ref:`User Guide `. Parameters ---------- n_neighbors : int, default=5 Number of neighbors to use by default for :meth:`kneighbors` queries. weights : {'uniform', 'distance'} or callable, default='uniform' Weight function used in prediction. Possible values: - 'uniform' : uniform weights. All points in each neighborhood are weighted equally. - 'distance' : weight points by the inverse of their distance. in this case, closer neighbors of a query point will have a greater influence than neighbors which are further away. - [callable] : a user-defined function which accepts an array of distances, and returns an array of the same shape containing the weights. algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto' Algorithm used to compute the nearest neighbors: - 'ball_tree' will use :class:`BallTree` - 'kd_tree' will use :class:`KDTree` - 'brute' will use a brute-force search. - 'auto' will attempt to decide the most appropriate algorithm based on the values passed to :meth:`fit` method. Note: fitting on sparse input will override the setting of this parameter, using brute force. leaf_size : int, default=30 Leaf size passed to BallTree or KDTree. This can affect the speed of the construction and query, as well as the memory required to store the tree. The optimal value depends on the nature of the problem. p : int, default=2 Power parameter for the Minkowski metric. When p = 1, this is equivalent to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used. metric : str or callable, default='minkowski' The distance metric to use for the tree. The default metric is minkowski, and with p=2 is equivalent to the standard Euclidean metric. For a list of available metrics, see the documentation of :class:`~sklearn.metrics.DistanceMetric` and the metrics listed in `sklearn.metrics.pairwise.PAIRWISE_DISTANCE_FUNCTIONS`. Note that the "cosine" metric uses :func:`~sklearn.metrics.pairwise.cosine_distances`. If metric is "precomputed", X is assumed to be a distance matrix and must be square during fit. X may be a :term:`sparse graph`, in which case only "nonzero" elements may be considered neighbors. metric_params : dict, default=None Additional keyword arguments for the metric function. n_jobs : int, default=None The number of parallel jobs to run for neighbors search. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. Doesn't affect :meth:`fit` method. Attributes ---------- classes_ : array of shape (n_classes,) Class labels known to the classifier effective_metric_ : str or callble The distance metric used. It will be same as the `metric` parameter or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to 'minkowski' and `p` parameter set to 2. effective_metric_params_ : dict Additional keyword arguments for the metric function. For most metrics will be same with `metric_params` parameter, but may also contain the `p` parameter value if the `effective_metric_` attribute is set to 'minkowski'. 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_samples_fit_ : int Number of samples in the fitted data. outputs_2d_ : bool False when `y`'s shape is (n_samples, ) or (n_samples, 1) during fit otherwise True. See Also -------- RadiusNeighborsClassifier: Classifier based on neighbors within a fixed radius. KNeighborsRegressor: Regression based on k-nearest neighbors. RadiusNeighborsRegressor: Regression based on neighbors within a fixed radius. NearestNeighbors: Unsupervised learner for implementing neighbor searches. Notes ----- See :ref:`Nearest Neighbors ` in the online documentation for a discussion of the choice of ``algorithm`` and ``leaf_size``. .. warning:: Regarding the Nearest Neighbors algorithms, if it is found that two neighbors, neighbor `k+1` and `k`, have identical distances but different labels, the results will depend on the ordering of the training data. https://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm Examples -------- >>> X = [[0], [1], [2], [3]] >>> y = [0, 0, 1, 1] >>> from sklearn.neighbors import KNeighborsClassifier >>> neigh = KNeighborsClassifier(n_neighbors=3) >>> neigh.fit(X, y) KNeighborsClassifier(...) >>> print(neigh.predict([[1.1]])) [0] >>> print(neigh.predict_proba([[0.9]])) [[0.666... 0.333...]] uniformautor minkowskiN)weights algorithm leaf_sizepmetric metric_paramsn_jobsc s$tj|||||||d||_dS)N) n_neighborsrrrrrr)super__init__r) selfrrrrrrrr __class__x/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/neighbors/_classification.pyrs  zKNeighborsClassifier.__init__cCst|j|_|||S)aFit the k-nearest neighbors classifier from the training dataset. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) or (n_samples, n_samples) if metric='precomputed' Training data. y : {array-like, sparse matrix} of shape (n_samples,) or (n_samples, n_outputs) Target values. Returns ------- self : KNeighborsClassifier The fitted k-nearest neighbors classifier. )rr_fit)rXyr!r!r"fits  zKNeighborsClassifier.fitcCs|jdkr|j|dd}d}n||\}}|j}|j}|js)|jd}|jg}t|}t|}t||j}t j ||f|dj d} t |D]8\} } |dur]t j||| fdd \} } n t||| f|dd \} } t j| t jd} | | | dd| f<qG|js| } | S) Predict the class labels for the provided data. Parameters ---------- X : array-like of shape (n_queries, n_features), or (n_queries, n_indexed) if metric == 'precomputed' Test samples. Returns ------- y : ndarray of shape (n_queries,) or (n_queries, n_outputs) Class labels for each data sample. rFreturn_distanceNrrdtyperaxis)r kneighborsclasses__y outputs_2d_reshapelenrr npemptyr- enumeratermoderasarrayravelintptake)rr$ neigh_ind neigh_distr1r2 n_outputs n_queriesry_predk classes_kr9_r!r!r"predicts,   zKNeighborsClassifier.predictcCs:|jdkr|j|dd}d}n||\}}|j}|j}|js)|jd}|jg}t|}t||j}|dur 1. The class probabilities of the input samples. Classes are ordered by lexicographic order. rFr(Nr*rr.?r)rr0r1r2r3r4rr r6 ones_likearanger8zerossizeTsumnewaxisappend)rr$r>r?r1r2rArall_rows probabilitiesrCrD pred_labelsproba_kiidx normalizerr!r!r" predict_probas6     "  z"KNeighborsClassifier.predict_probacCddiSN multilabelTr!rr!r!r" _more_tags3zKNeighborsClassifier._more_tags)r __name__ __module__ __qualname____doc__rr&rFrXr] __classcell__r!r!rr"rs" /:rc sXeZdZdZ dddddddddd fd d Zd d ZddZddZddZZ S)RadiusNeighborsClassifieraClassifier implementing a vote among neighbors within a given radius. Read more in the :ref:`User Guide `. Parameters ---------- radius : float, default=1.0 Range of parameter space to use by default for :meth:`radius_neighbors` queries. weights : {'uniform', 'distance'} or callable, default='uniform' Weight function used in prediction. Possible values: - 'uniform' : uniform weights. All points in each neighborhood are weighted equally. - 'distance' : weight points by the inverse of their distance. in this case, closer neighbors of a query point will have a greater influence than neighbors which are further away. - [callable] : a user-defined function which accepts an array of distances, and returns an array of the same shape containing the weights. Uniform weights are used by default. algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto' Algorithm used to compute the nearest neighbors: - 'ball_tree' will use :class:`BallTree` - 'kd_tree' will use :class:`KDTree` - 'brute' will use a brute-force search. - 'auto' will attempt to decide the most appropriate algorithm based on the values passed to :meth:`fit` method. Note: fitting on sparse input will override the setting of this parameter, using brute force. leaf_size : int, default=30 Leaf size passed to BallTree or KDTree. This can affect the speed of the construction and query, as well as the memory required to store the tree. The optimal value depends on the nature of the problem. p : int, default=2 Power parameter for the Minkowski metric. When p = 1, this is equivalent to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used. metric : str or callable, default='minkowski' Distance metric to use for the tree. The default metric is minkowski, and with p=2 is equivalent to the standard Euclidean metric. For a list of available metrics, see the documentation of :class:`~sklearn.metrics.DistanceMetric`. If metric is "precomputed", X is assumed to be a distance matrix and must be square during fit. X may be a :term:`sparse graph`, in which case only "nonzero" elements may be considered neighbors. outlier_label : {manual label, 'most_frequent'}, default=None Label for outlier samples (samples with no neighbors in given radius). - manual label: str or int label (should be the same type as y) or list of manual labels if multi-output is used. - 'most_frequent' : assign the most frequent label of y to outliers. - None : when any outlier is detected, ValueError will be raised. metric_params : dict, default=None Additional keyword arguments for the metric function. n_jobs : int, default=None The number of parallel jobs to run for neighbors search. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. **kwargs : dict Additional keyword arguments passed to the constructor. .. deprecated:: 1.0 The RadiusNeighborsClassifier class will not longer accept extra keyword parameters in 1.2 since they are unused. Attributes ---------- classes_ : ndarray of shape (n_classes,) Class labels known to the classifier. effective_metric_ : str or callable The distance metric used. It will be same as the `metric` parameter or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to 'minkowski' and `p` parameter set to 2. effective_metric_params_ : dict Additional keyword arguments for the metric function. For most metrics will be same with `metric_params` parameter, but may also contain the `p` parameter value if the `effective_metric_` attribute is set to 'minkowski'. 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_samples_fit_ : int Number of samples in the fitted data. outlier_label_ : int or array-like of shape (n_class,) Label which is given for outlier samples (samples with no neighbors on given radius). outputs_2d_ : bool False when `y`'s shape is (n_samples, ) or (n_samples, 1) during fit otherwise True. See Also -------- KNeighborsClassifier : Classifier implementing the k-nearest neighbors vote. RadiusNeighborsRegressor : Regression based on neighbors within a fixed radius. KNeighborsRegressor : Regression based on k-nearest neighbors. NearestNeighbors : Unsupervised learner for implementing neighbor searches. Notes ----- See :ref:`Nearest Neighbors ` in the online documentation for a discussion of the choice of ``algorithm`` and ``leaf_size``. https://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm Examples -------- >>> X = [[0], [1], [2], [3]] >>> y = [0, 0, 1, 1] >>> from sklearn.neighbors import RadiusNeighborsClassifier >>> neigh = RadiusNeighborsClassifier(radius=1.0) >>> neigh.fit(X, y) RadiusNeighborsClassifier(...) >>> print(neigh.predict([[1.5]])) [0] >>> print(neigh.predict_proba([[1.0]])) [[0.66666667 0.33333333]] rGrrrrrN)rrrrr outlier_labelrrc sNt| dkrtd| dttj||||||| d||_||_dS)NrzPassing additional keyword parameters has no effect and is deprecated in 1.0. An error will be raised from 1.2 and beyond. The ignored keyword parameter(s) are: .)radiusrrrrrr) r5warningswarnkeys FutureWarningrrrrf) rrhrrrrrrfrrkwargsrr!r"rs$  z"RadiusNeighborsClassifier.__init__c CsRt|j|_||||j}|j}|js|jd}|jg}|jdur'd}n}|jdkrLg}t|D]\}}t |dd|f}| || q2nXt |jrot|jtsot|jt|krktd|jt||j}n|jgt|}t||D]'\} } t | rt| tstd| | t | | j| jkrtd| | q|||_|S)aFit the radius neighbors classifier from the training dataset. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) or (n_samples, n_samples) if metric='precomputed' Training data. y : {array-like, sparse matrix} of shape (n_samples,) or (n_samples, n_outputs) Target values. Returns ------- self : RadiusNeighborsClassifier The fitted radius neighbors classifier. r*N most_frequentzJThe length of outlier_label: {} is inconsistent with the output length: {}zCThe outlier_label of classes {} is supposed to be a scalar, got {}.zCThe dtype of outlier_label {} is inconsistent with classes {} in y.)rrr#r1r2r3r4rfr8r6bincountrPargmaxr isinstancestrr5 ValueErrorformatzip TypeErrorr-outlier_label_) rr$r%r1r2rwrCrD label_countclasseslabelr!r!r"r&sN      zRadiusNeighborsClassifier.fitc Cs||}|j}|js|g}|jg}t|}|djd}tj||f|djd}t|D]1\}}|j dd} || | |dd|f<|dkj dd} | r^t | } |j||| |f<q-|jsf|}|S)r'rr,rr.N)rXr1r3r5shaper6r7r-r8rpr=allany flatnonzerorwr;) rr$probsr1r@rArBrCprobmax_prob_indexoutlier_zero_probszero_prob_indexr!r!r"rF9s&   z!RadiusNeighborsClassifier.predictcs>t|}||\}}tj|td}dd|D|dd<t|}t|}|j}|j|js;|j d|jg}|j durK|j dkrKt d|t ||j} | durY| |} g} t|D]\} tjt|td} fdd|D| dd<t|| j f} tt|| j f}| durt| |D]\}}tj|| j d ||ddf<qnt| |D]\}}tj|| || j d ||ddf<q|| |ddf<|j dkr|j }t| |k}|j d krd | ||df<n td |j | jd d ddtjf}d ||dk<| |} | | q_|js| d} | S)a Return probability estimates for the test data X. Parameters ---------- X : array-like of shape (n_queries, n_features), or (n_queries, n_indexed) if metric == 'precomputed' Test samples. Returns ------- p : ndarray of shape (n_queries, n_classes), or a list of n_outputs of such arrays if n_outputs > 1. The class probabilities of the input samples. Classes are ordered by lexicographic order. r,cSsg|]}t|dkqS)r)r5).0nindr!r!r" xz;RadiusNeighborsClassifier.predict_proba..Nr*rzNo neighbors found for test samples %r, you can try using larger radius, giving a label for outliers, or considering removing them from your dataset.csg|]}|fqSr!r!)rindr2rCr!r"rr) minlengthrrGziOutlier label {} is not in training classes. All class probabilities of outliers will be assigned with 0.r.rH)rradius_neighborsr6rKboolr~r1r2r3r4rwrLrsr rr8r5objectrorirjrtrNrOrP)rr$rAr?r> outlier_maskoutliersinliersr1rrRrDrSrT proba_inlrUrV_outlier_label label_indexrWr!rr"rXcsf           z'RadiusNeighborsClassifier.predict_probacCrYrZr!r\r!r!r"r]r^z$RadiusNeighborsClassifier._more_tags)rGr_r!r!rr"re7s$#I*Xre)rcnumpyr6scipyr utils.extmathrutils.validationrrri_baserr r r r baser rrer!r!r!r"s   #