U ]ß<`½ã@sDdZddlZGdd„dƒZdd„Zd dd„Zdd d „Zdd d „ZdS)aµCode for doing k-nearest-neighbors classification. 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. éNc@seZdZdZdd„ZdS)ÚkNNaHolds information necessary to do nearest neighbors classification. Attribues: - 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. cCstƒ|_g|_g|_d|_dS)z Initialize.N)ÚsetÚclassesÚxsÚysÚk)Úself©r ú&lib/python3.8/site-packages/Bio/kNN.pyÚ__init__,sz kNN.__init__N)Ú__name__Ú __module__Ú __qualname__Ú__doc__r r r r r r"s rcCsdS)z8Return integer one (dummy method for equally weighting).ér )ÚxÚyr r r Ú equal_weight4srcCs.tƒ}t|ƒ|_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. )rrrÚnumpyÚasarrayrrr)rrrÚtypecodeÚknnr r r Útrain:s  rc Cs |dkr t}t |¡}g}|rRtt|jƒƒD]"}|||j|ƒ}| ||f¡q,nXt t|ƒ¡}tt|jƒƒD]:}||j||dd…<t t  ||¡¡}| ||f¡qn|  ¡i}|j D] } d|| <q¼|d|j …D].\}}|j |} || |||j|ƒ|| <qØ|S)aÎCalculate 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)rrrÚrangeÚlenrÚappendZzerosZsqrtÚdotÚsortrrr) rrÚ weight_fnÚ distance_fnÚorderÚiZdistZtempÚweightsrÚklassr r r Ú calculateJs*     r$c CsR|dkr t}t||||d}d}d}| ¡D] \}}|dksD||kr,|}|}q,|S)a%Classify an observation into a class. If not specified, weight_fn will give all neighbors equal weight. distance_fn is an optional function that takes two points and returns the distance between them. If distance_fn is None (the default), the Euclidean distance is used. N)rr)rr$Úitems) rrrrr"Z most_classZ most_weightr#Zweightr r r Úclassifywsr&)N)NN)NN)rrrrrr$r&r r r r Ús   -