'''
Created on Sep 16, 2010
kNN: k Nearest Neighbors
Input:
inX: vector to compare to existing dataset (1xN)
dataSet: size m data set of known vectors (NxM)
labels: data set labels (1xM vector)
k: number of neighbors to use for comparison (should be an odd number)
Output:
the most popular class label
@author: pbharrin
'''
from numpy import *
import operator
from os import listdir
def classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort()
classCount={}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
def file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines())
#get the number of lines in the file
returnMat = zeros((numberOfLines,3))
#prepare matrix to return
classLabelVector = []
#prepare labels return
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat,classLabelVector