ZPhdZddlZddlZddlmZddlmZmZddl m Z m Z ddl m Z mZddlmZd d lmZe eje Gd d eZdS)z,Class to perform over-sampling using ADASYN.N)sparse)_safe_indexingcheck_random_state) HasMethodsInterval) Substitutioncheck_neighbors_object)_random_state_docstring)BaseOverSampler)sampling_strategy random_stateceZdZUdZiejdeejddde ddggiZe e d <d dd d fd Z dZ dZdZfdZxZS)ADASYNa Oversample using Adaptive Synthetic (ADASYN) algorithm. This method is similar to SMOTE but it generates different number of samples depending on an estimate of the local distribution of the class to be oversampled. Read more in the :ref:`User Guide `. Parameters ---------- {sampling_strategy} {random_state} n_neighbors : int or estimator object, default=5 The nearest neighbors used to define the neighborhood of samples to use to generate the synthetic samples. You can pass: - an `int` corresponding to the number of neighbors to use. A `~sklearn.neighbors.NearestNeighbors` instance will be fitted in this case. - an instance of a compatible nearest neighbors algorithm that should implement both methods `kneighbors` and `kneighbors_graph`. For instance, it could correspond to a :class:`~sklearn.neighbors.NearestNeighbors` but could be extended to any compatible class. Attributes ---------- sampling_strategy_ : dict Dictionary containing the information to sample the dataset. The keys corresponds to the class labels from which to sample and the values are the number of samples to sample. nn_ : estimator object Validated K-nearest Neighbours estimator linked to the parameter `n_neighbors`. n_features_in_ : int Number of features in the input dataset. .. versionadded:: 0.9 feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during `fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 0.10 See Also -------- SMOTE : Over-sample using SMOTE. SMOTENC : Over-sample using SMOTE for continuous and categorical features. SMOTEN : Over-sample using the SMOTE variant specifically for categorical features only. SVMSMOTE : Over-sample using SVM-SMOTE variant. BorderlineSMOTE : Over-sample using Borderline-SMOTE variant. Notes ----- The implementation is based on [1]_. Supports multi-class resampling. A one-vs.-rest scheme is used. References ---------- .. [1] He, Haibo, Yang Bai, Edwardo A. Garcia, and Shutao Li. "ADASYN: Adaptive synthetic sampling approach for imbalanced learning," In IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 1322-1328, 2008. Examples -------- >>> from collections import Counter >>> from sklearn.datasets import make_classification >>> from imblearn.over_sampling import ADASYN >>> X, y = make_classification(n_classes=2, class_sep=2, ... weights=[0.1, 0.9], n_informative=3, n_redundant=1, flip_y=0, ... n_features=20, n_clusters_per_class=1, n_samples=1000, ... random_state=10) >>> print('Original dataset shape %s' % Counter(y)) Original dataset shape Counter({{1: 900, 0: 100}}) >>> ada = ADASYN(random_state=42) >>> X_res, y_res = ada.fit_resample(X, y) >>> print('Resampled dataset shape %s' % Counter(y_res)) Resampled dataset shape Counter({{0: 904, 1: 900}}) n_neighborsr Nleft)closed kneighborskneighbors_graph_parameter_constraintsauto)rrrcht|||_||_dS)N)r)super__init__rr)selfrrr __class__s ^/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/imblearn/over_sampling/_adasyn.pyrzADASYN.__init__{s7 +<===(&c>td|jd|_dS)z'Create the necessary objects for ADASYNrr )additional_neighborN)r rnn_rs r_validate_estimatorzADASYN._validate_estimators&) 4+   r c(|t|j}|g}|g}|jD]\}}|dkr t j||k}t||} |j ||j | dddddf} |j j dz } t j || |kd| z } t j | std| t j | z} t j| |zt"} t j | }|st%d|j | |j | dddddf} t jt)|}t j|| }|| |}| | ||f| |z }||df}t1j|rQt5|j}t9t0||}| |||z}n| |||zz}||j}t j|||j }| || |t1j|rt1j!||j" }nt j!|}t j#|}||fS) NrF)return_distancer )axiszNot any neigbours belong to the majority class. This case will induce a NaN case with a division by zero. ADASYN is not suited for this specific dataset. Use SMOTE instead.z>No samples will be generated with the provided ratio settings.)size) fill_valuedtype)format)$r%rrcopysampling_strategy_itemsnp flatnonzerorr#fitrrsum RuntimeErrorrintastypeint ValueErrorarangelenrepeatchoiceuniformrissparsetype__name__getattrmultiplyr+fullappendvstackr,hstack)rXyr X_resampled y_resampled class_sample n_samplestarget_class_indicesX_classnnsrratio_nnn_samples_generateenumerated_class_indicesrowscolsdiffssteps sparse_funcX_newy_news r _fit_resamplezADASYN._fit_resamples^   """)$*;<< vvxxj vvxxj '+'>'D'D'F'F3 &3 & #L)A~~#%>!|2C#D#D $Q(<==G HLLOOO(%%gu%EEaaaeLC(.2Kvaf 41=== KH6(## "* x(( (H!#I)=!>!>!E!Ec!J!J 122I  T HLL ! ! !(%%gu%EEaaaeLC')y5I1J1J'K'K $957IJJD&&{&CCDCd O,wt} > > J &89 : : $$D! ' ' ' ' ' ' '   B(B(B(H   r r)rerfnumpyr0scipyr sklearn.utilsrrsklearn.utils._param_validationrrutilsr r utils._docstringr baser _sampling_strategy_docstringrr^r rrss22 <<<<<<<<@@@@@@@@88888888666666!!!!!!%B(@@@@@_@@ @@@r