def execute(self, docs):
"""
@see parent
"""
clusters = []
# First cluster contains all of the docs.
cluster = dotdict()
cluster.docs = []
for doc in self.bible.docs:
doc.cluster = cluster
cluster.docs.append(doc)
cluster.centroid = self.centroid(cluster.docs)
# Append the first cluster to the cluster list.
clusters.append(cluster)
while len(clusters) != self.k:
# Use the abstract select cluster method.
cluster = self.select_cluster(clusters)
# Remove this cluster from the current set because it will be split.
clusters.remove(cluster)
max_sim = float("-inf")
max_bicluster = None
for i in range(self.iter):
# Free the docs from whatever cluster they are in.
for doc in cluster.docs:
doc.cluster = None
kmeans = KMeans(2)
kmeans.bible = self.bible
kmeans.execute(cluster.docs)
bicluster = kmeans.clusters
sim = kmeans.similarity()
if sim > max_sim:
max_sim = sim
max_bicluster = bicluster
# Re-assign the documents to their respective max bicluster.
for cluster in bicluster:
for doc in cluster.docs:
doc.cluster = cluster
# Add the new max bicluster to the current cluster set.
clusters.extend(bicluster)
self.clusters = clusters
def execute(self, docs):
"""
Overloads UPGMA's execute and runs the
results through K-Means.
Key arguments:
docs -- the docs to cluster.
"""
super(AgglomerativeUPGMAKMeans, self).execute(docs)
kmeans = KMeans(self.k)
kmeans.bible = self.bible
# Clusters will be changed within this method.
kmeans.execute(docs, self.clusters)
def execute(self, docs):
"""
Overloads UPGMA's execute and runs the
results through K-Means.
Key arguments:
docs -- the docs to cluster.
"""
super(AgglomerativeUPGMAKMeans, self).execute(docs)
kmeans = KMeans(self.k)
kmeans.bible = self.bible
# Clusters will be changed within this method.
kmeans.execute(docs, self.clusters)
def execute(self, docs):
"""
@see parent
"""
clusters = []
# First cluster contains all of the docs.
cluster = dotdict()
cluster.docs = []
for doc in self.bible.docs:
doc.cluster = cluster
cluster.docs.append(doc)
cluster.centroid = self.centroid(cluster.docs)
# Append the first cluster to the cluster list.
clusters.append(cluster)
while len(clusters) != self.k:
# Use the abstract select cluster method.
cluster = self.select_cluster(clusters)
# Remove this cluster from the current set because it will be split.
clusters.remove(cluster)
max_sim = float("-inf")
max_bicluster = None
for i in range(self.iter):
# Free the docs from whatever cluster they are in.
for doc in cluster.docs:
doc.cluster = None
kmeans = KMeans(2)
kmeans.bible = self.bible
kmeans.execute(cluster.docs)
bicluster = kmeans.clusters
sim = kmeans.similarity()
if sim > max_sim:
max_sim = sim
max_bicluster = bicluster
# Re-assign the documents to their respective max bicluster.
for cluster in bicluster:
for doc in cluster.docs:
doc.cluster = cluster
# Add the new max bicluster to the current cluster set.
clusters.extend(bicluster)
self.clusters = clusters