ó ø-$Ic@sŠdZy eZWn!ek r3ddlmZnXddlZdd d„ƒYZd„Zdd„Z edd„Z edd „Z dS( s¼ This module provides code for doing k-nearest-neighbors classification. k Nearest Neighbors is a supervised learning algorithm that classifies a new observation based the classes in its surrounding neighborhood. Glossary: distance The distance between two points in the feature space. weight The importance given to each point for classification. Classes: kNN Holds information for a nearest neighbors classifier. Functions: train Train a new kNN classifier. calculate Calculate the probabilities of each class, given an observation. classify Classify an observation into a class. Weighting Functions: equal_weight Every example is given a weight of 1. iÿÿÿÿ(tSetNtkNNcBseZdZd„ZRS(sHolds information necessary to do nearest neighbors classification. Members: classes Set of the possible classes. xs List of the neighbors. ys List of the classes that the neighbors belong to. k Number of neighbors to look at. cCs+tƒ|_g|_g|_d|_dS(skNN()N(tsettclassestxstystNonetk(tself((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pyt__init__.s   (t__name__t __module__t__doc__R (((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pyR$s cCsdS(sequal_weight(x, y) -> 1i((txty((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pyt equal_weight5scCsCtƒ}t|ƒ|_tj||ƒ|_||_||_|S(sNtrain(xs, ys, k) -> kNN 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. (RRRtnumpytasarrayRRR(RRRttypecodetknn((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pyttrain:s   c Cs[tj|ƒ}g}|rgx¾tt|jƒƒD]/}|||j|ƒ}|j||fƒq1Wnutjt|ƒƒ}x]tt|jƒƒD]F}||j||(tjtj||ƒƒ}|j||fƒq’W|j ƒi}x|j D]} d|| weight dict Calculate the probability for each class. knn is a kNN object. 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. g( RRtrangetlenRtappendtzerostsqrttdottsortRRR( RR t weight_fnt distance_fntordertitdistttemptweightsRtklass((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pyt calculateKs&   &c Csot||d|d|ƒ}d}d}xA|jƒD]3\}}|dksX||kr4|}|}q4q4W|S(s]classify(knn, x[, weight_fn][, distance_fn]) -> class 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. RRN(R$Rtitems( RR RRR"t most_classt most_weightR#tweight((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pytclassifyss (( R Rt NameErrortsetsRRRRRRR$R)(((sz/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/kNN.pyts     (