def kmean(self,k,cutoff):
initials = random.sample(self.files,k)
clusters = []
# print 'Iteration ==> ',k
for p in initials:
clusters.append(Cluster(self.id,files=[p]))
while True:
lists = []
for c in clusters: lists.append([])
for p in self.files:
smallest_distance = utils.getDistance(p.vector,clusters[0].centroid)
index = 0
for i in range(len(clusters[1:])):
distance = utils.getDistance(p.vector, clusters[i+1].centroid)
if distance < smallest_distance:
smallest_distance = distance
index = i+1
# Add this Point to that Cluster's corresponding list
lists[index].append(p)
# Update each Cluster with the corresponding list
# Record the biggest centroid shift for any Cluster
biggest_shift = 0.0
for i in range(len(clusters)):
shift = clusters[i].addfiles(lists[i])
biggest_shift = max(biggest_shift, shift)
# If the biggest centroid shift is less than the cutoff, stop
if biggest_shift < cutoff: break
# Return the list of Clusters
# print 'Total clusters => ',len(clusters)
for cl in clusters:
cl.centroid = cl.calculateCentroid()
cl.calculateRadius()
#print '\n-------\n',cl,cl.files,cl.radius,len(cl.files)
return clusters
def calculateRadius(self):
max = -1
for p in self.files:
dist = utils.getDistance(self.centroid, p.vector)
if dist > max: max = dist
self.radius = max
return max
def calculateRadius(self):
max = -1
for p in self.files:
dist = utils.getDistance(self.centroid,p.vector)
if dist > max: max = dist
self.radius = max
return max
def getScore(self,vector,centroid,clusterdata,alldata):
dist = utils.getDistance(vector,centroid)
return clusterdata/(dist*alldata)
