def updatedist(self, c):
"""
Cluster c has changed, re-compute all intercluster distances
"""
self.removedist(c)
for x in self.clusters:
if x==c: continue
d=kernel_dist(x.center,c.center)
t=Dist(x,c,d)
heapq.heappush(self.dist,t)
def updatedist(self, c):
"""
Cluster c has changed, re-compute all intercluster distances
"""
self.removedist(c)
for x in self.clusters:
if x == c: continue
d = kernel_dist(x.center, c.center)
t = Dist(x, c, d)
heapq.heappush(self.dist, t)
def cluster(self, document):
'''
Performs clustering for a new document. It takes as input
a document object from the db and finds the closer cluster for it.
'''
doc_index = self.add_document(document)
doc_id = str(document.id)
doc_content = document.content
self.construct_term_doc_matrix(index=doc_index, document=doc_content)
print 'N', len(self.clusters)
print 'clustering', doc_index
if doc_index > 0: #ignore the first document
#e = doc_index
e = self.td_matrix
newc=OnlineCluster(a=e, cluster_id=self.cluster_id_counter, doc_id=doc_id, doc_content=doc_content, term_vector=self.attributes)
#If the new term vector is larger then change all the cluster centers
#However, if the new term vector is smaller then pad the new cluster's center
if len(self.clusters) > 0:
if len(newc.term_vector) > len(self.clusters[0].term_vector):
self.resize()
else:
newc.resize(self.clusters[0].term_vector)
e = newc.center
if len(self.clusters)>0:
# Compare the new document to each existing cluster
c=[ ( i, kernel_dist(x.center, e) ) for i,x in enumerate(self.clusters)]
closest_cluster = min( c , key=operator.itemgetter(1))
if closest_cluster[1] < 1.0:
closest=self.clusters[closest_cluster[0]]
closest.add(e, doc_id, doc_content)
# invalidate dist-cache for this cluster
self.updatedist(closest)
else:
# make a new cluster for this point
self.clusters.append(newc)
self.updatedist(newc)
if len(self.clusters)>=self.N and len(self.clusters)>1:
# merge closest two clusters. It doesn't matter which ones, Only the closest
m=heapq.heappop(self.dist)
m.x.merge(m.y)
self.clusters.remove(m.y)
self.removedist(m.y)
self.updatedist(m.x)
self.cluster_id_counter += 1
else:
newc=OnlineCluster(a=self.td_matrix, cluster_id=self.cluster_id_counter, doc_id=doc_id, doc_content=doc_content, term_vector=self.attributes)
self.clusters.append(newc)
self.updatedist(newc)
def cluster(self, document):
'''
Performs clustering for a new document. It takes as input
a document object from the db and finds the closer cluster for it.
'''
doc_index = self.add_document(document)
doc_id = str(document.id)
doc_content = document.content
self.construct_term_doc_matrix(index=doc_index, document=doc_content)
print 'N', len(self.clusters)
print 'clustering', doc_index
if doc_index > 0: #ignore the first document
#e = doc_index
e = self.td_matrix
newc = OnlineCluster(a=e,
cluster_id=self.cluster_id_counter,
doc_id=doc_id,
doc_content=doc_content,
term_vector=self.attributes)
#If the new term vector is larger then change all the cluster centers
#However, if the new term vector is smaller then pad the new cluster's center
if len(self.clusters) > 0:
if len(newc.term_vector) > len(self.clusters[0].term_vector):
self.resize()
else:
newc.resize(self.clusters[0].term_vector)
e = newc.center
if len(self.clusters) > 0:
# Compare the new document to each existing cluster
c = [(i, kernel_dist(x.center, e))
for i, x in enumerate(self.clusters)]
closest_cluster = min(c, key=operator.itemgetter(1))
if closest_cluster[1] < 1.0:
closest = self.clusters[closest_cluster[0]]
closest.add(e, doc_id, doc_content)
# invalidate dist-cache for this cluster
self.updatedist(closest)
else:
# make a new cluster for this point
self.clusters.append(newc)
self.updatedist(newc)
if len(self.clusters) >= self.N and len(self.clusters) > 1:
# merge closest two clusters. It doesn't matter which ones, Only the closest
m = heapq.heappop(self.dist)
m.x.merge(m.y)
self.clusters.remove(m.y)
self.removedist(m.y)
self.updatedist(m.x)
self.cluster_id_counter += 1
else:
newc = OnlineCluster(a=self.td_matrix,
cluster_id=self.cluster_id_counter,
doc_id=doc_id,
doc_content=doc_content,
term_vector=self.attributes)
self.clusters.append(newc)
self.updatedist(newc)
