o Rŀg@sdZddlZzddlZWneyddlmZeddwddlmZedeGdddZ d d Z dd d Z dd dZ dddZ dS)aCode for doing k-nearest-neighbors classification (DEPRECATED). k Nearest Neighbors is a supervised learning algorithm that classifies a new observation based the classes in its surrounding neighborhood. Glossary: - distance The distance between two points in the feature space. - weight The importance given to each point for classification. Classes: - kNN Holds information for a nearest neighbors classifier. Functions: - train Train a new kNN classifier. - calculate Calculate the probabilities of each class, given an observation. - classify Classify an observation into a class. Weighting Functions: - equal_weight Every example is given a weight of 1. This module has been deprecated, please consider an alternative like scikit-learn instead. N)MissingPythonDependencyErrorzJPlease install NumPy if you want to use Bio.kNN. See http://www.numpy.org/)BiopythonDeprecationWarningz}The 'Bio.kNN' module is deprecated and will be removed in a future release of Biopython. Consider using scikit-learn instead.c@seZdZdZddZdS)kNNaHolds information necessary to do nearest neighbors classification. Attributes: - classes Set of the possible classes. - xs List of the neighbors. - ys List of the classes that the neighbors belong to. - k Number of neighbors to look at. cCst|_g|_g|_d|_dS)zInitialize the class.N)setclassesxsysk)selfr ;/var/www/html/myenv/lib/python3.10/site-packages/Bio/kNN.py__init__?s z kNN.__init__N)__name__ __module__ __qualname____doc__r r r r r r5s rcCsdS)z8Return integer one (dummy method for equally weighting).r )xyr r r equal_weightGsrcCs.t}t||_t|||_||_||_|S)a(Train a k nearest neighbors classifier on a training set. xs is a list of observations and ys is a list of the class assignments. Thus, xs and ys should contain the same number of elements. k is the number of neighbors that should be examined when doing the classification. )rrrnpasarrayrrr )rrr typecodeknnr r r trainMs  rc Cs |durt}t|}g}|r)tt|jD]}|||j|}|||fqn,tt|}tt|jD]}||j||dd<tt ||}|||fq7| i}|j D]} d|| <q^|d|j D]\}}|j |} || |||j||| <ql|S)aCalculate the probability for each class. Arguments: - x is the observed data. - weight_fn is an optional function that takes x and a training example, and returns a weight. - distance_fn is an optional function that takes two points and returns the distance between them. If distance_fn is None (the default), the Euclidean distance is used. Returns a dictionary of the class to the weight given to the class. Ng)rrrrangelenrappendzerossqrtdotsortrr r) rr weight_fn distance_fnorderidisttempweightsr klassr r r calculate]s,     r*c CsR|durt}t||||d}d}d}|D]\}}|dus"||kr&|}|}q|S)a%Classify an observation into a class. If not specified, weight_fn will give all neighbors equal weight. distance_fn is an optional function that takes two points and returns the distance between them. If distance_fn is None (the default), the Euclidean distance is used. N)r"r#)rr*items) rrr"r#r( most_class most_weightr)weightr r r classifysr/)N)NN)rwarningsnumpyr ImportErrorBiorrwarnrrrr*r/r r r r s,      -