kmeansMapper.py

#!/usr/bin/env python
import sys
import math

fd = open('/home/project-49/centers.txt','r')
centers = []
for line in fd:
    line = line.strip()
    vals = line.split(' ')
    centers.extend([vals])
fd.close()

for line in sys.stdin:
    line = line.strip()
    vals = line.split(' ')

    clusterNum = None
    distance = None
    i = 0

    for center in centers:
        euclidDist = math.sqrt((int(vals[0]) - int(center[0]))**2 + (int(vals[1])-int(center[1]))**2)
        if clusterNum:
            if euclidDist < distance:
                clusterNum = i+1
                distance = euclidDist
            else:
                clusterNum = i+1
                distance = euclidDist
            i += 1
        print clusterNum,"\t",vals[0],"\t",vals[1]