&hdZddlZ ddlZddlmZejdeGddZ d Z d d Z dd Z dd Z y#e$rddlmZeddwxYw)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.ceZdZdZdZy)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. cLt|_g|_g|_d|_y)zInitialize the class.N)setclassesxsysk)selfs V/mounts/lovelace/software/anaconda3/envs/py312/lib/python3.12/site-packages/Bio/kNN.py__init__z kNN.__init__?s u N)__name__ __module__ __qualname____doc__rrrrr5s rrcy)z8Return integer one (dummy method for equally weighting).r)xys r equal_weightrGs rct}t||_tj|||_||_||_|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. )rrr npasarrayr r r )r r r typecodeknns rtrainr Ms; %Cb'CK ZZH %CF CF CE Jrc|t}tj|}g}|rMtt |j D]+}|||j |}|j ||f-ntjt |}tt |j D]S}||j |z |ddtjtj||}|j ||fU|ji}|jD]} d|| < |d|jD]3\}}|j|} || |||j |z|| <5|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)rrrrangelenr appendzerossqrtdotsortr r r ) rr weight_fn distance_fnorderidisttempweightsr klasss r calculater1]sV  1 A Es366{# $Aq#&&),D LL$ # $ xxAs366{# $A#&&)mDG77266$-.D LL$ # $ JJLG [[ 355>Baq  )Asvvay*AAB Nrc|t}t||||}d}d}|jD]\}}|||kDs|}|}|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*)rr1items) rrr)r*r/ most_class most_weightr0weights rclassifyr7sa Q)MGJK ! v  +!5J K! r)N)NN)rwarningsnumpyr ImportErrorBiorrwarnrrr r1r7rrrr=sz2,  A$  *ZK0 &T  s ?A