Knearest

class KNearest:
    """k-nearest neighbour inferer"""
    def __init__(self, ds):
        #set the dataset
        self.ds = ds

    def predict(self, p1, k=1):
        """Given a test point p1, return the modal class of its knearest neighbours"""
        distances = []
        #calculate the distance between the test point and known data points.
        for i, clas in enumerate( self.ds.classes ):
            for p2 in clas.data:
                dist = self._calc_distance(p1, p2)
                distances.append( ( dist, i, p2 ) )
        #rank the distances
        distances = sorted( distances )
        #the following is a bit scruffy, I should really be using mean
        return int( stats.mode( [dist[1] for dist in distances[:k]] )[0] ) 
         
    def _calc_distance(self, p1, p2): 
        """ Calculate the Euclidean distance between the two points """
        return ( sum( [(p1[i] - p2[i])**2 for i in range( len(p1) )] ) )**0.5