def cluster_more(self, n):
"""Expands the cluster to include n more emails and returns these additional emails.
If n more is not available, cluster size is simply truncated to include all remaining
emails."""
if 'frequency' in self.opt:
if n >= len(self.dist_list):
n = len(self.dist_list)
print "Adding ", n, " more emails to cluster of size ", self.size, " via ", self.opt, " method"
self.size += n
new_elements = []
added = 0
while added < n:
d,i = self.dist_list.pop(0) # get nearest email
new_elements.append(i) # add to new list
self.added.append(i)
self.cluster_set.add(i) # add to original cluster set
self.cluster_word_frequency = h.update_word_frequencies(self.cluster_word_frequency, self.data_x[i]) # update word frequencies
self.update_dist_list()
added += 1
if added % 10 == 0:
print added, "/", n
assert(len(new_elements) == n), str(len(new_elements)) + " " + str(n)
assert(len(self.cluster_set) == self.size), str(len(self.cluster_set)) + " " + str(self.size)
self.divide(new_elements)
return new_elements
def make_cluster(self):
"""Constructs the initial cluster of emails."""
# self.dist_list = [t for t in self.dist_list if t is not None]
if self.size > len(self.dist_list):
print "\nTruncating cluster size...\n"
self.size = len(self.dist_list)
if 'frequency' in self.opt:
emails = [self.clustroid] # list of added emails
current_size = 1
while current_size < self.size:
d, i = self.dist_list.pop(0) # get nearest email
emails.append(i) # add to list
self.added.append(i) # track order in which emails are added
self.cluster_word_frequency = h.update_word_frequencies(
self.cluster_word_frequency,
self.data_x[i]) # update word frequencies
self.update_dist_list()
if current_size % 10 == 0:
print current_size, "/", self.size
# new cluster_word_frequency, so need to resort closest emails
current_size += 1
print "-> cluster initialized with size", len(emails)
return set(emails)
def make_cluster(self):
"""Constructs the initial cluster of emails."""
# self.dist_list = [t for t in self.dist_list if t is not None]
if self.size > len(self.dist_list):
print "\nTruncating cluster size...\n"
self.size = len(self.dist_list)
if 'frequency' in self.opt:
emails = [self.clustroid] # list of added emails
current_size = 1
while current_size < self.size:
d,i = self.dist_list.pop(0) # get nearest email
emails.append(i) # add to list
self.added.append(i) # track order in which emails are added
self.cluster_word_frequency = h.update_word_frequencies(self.cluster_word_frequency, self.data_x[i]) # update word frequencies
self.update_dist_list()
if current_size % 10 == 0:
print current_size, "/", self.size
# new cluster_word_frequency, so need to resort closest emails
current_size += 1
print "-> cluster initialized with size", len(emails)
return set(emails)
def cluster_more(self, n):
"""Expands the cluster to include n more emails and returns these additional emails.
If n more is not available, cluster size is simply truncated to include all remaining
emails."""
if 'frequency' in self.opt:
if n >= len(self.dist_list):
n = len(self.dist_list)
print "Adding ", n, " more emails to cluster of size ", self.size, " via ", self.opt, " method"
self.size += n
new_elements = []
added = 0
while added < n:
d, i = self.dist_list.pop(0) # get nearest email
new_elements.append(i) # add to new list
self.added.append(i)
self.cluster_set.add(i) # add to original cluster set
self.cluster_word_frequency = h.update_word_frequencies(
self.cluster_word_frequency,
self.data_x[i]) # update word frequencies
self.update_dist_list()
added += 1
if added % 10 == 0:
print added, "/", n
assert (
len(new_elements) == n), str(len(new_elements)) + " " + str(n)
assert (len(self.cluster_set) == self.size), str(
len(self.cluster_set)) + " " + str(self.size)
self.divide(new_elements)
return new_elements
