def __init__(self, msg, size, active_unlearner, distance_opt, working_set=None, sort_first=True, separate=True):
self.clustroid = msg # seed of the cluster
if msg.train == 1 or msg.train == 3: # if ham set1 or ham set3
self.train = [1, 3]
elif msg.train == 0 or msg.train == 2: # if spam set1 or spam set3
self.train = [0, 2]
self.common_features = []
self.msg_index = {}
self.separate = separate
self.size = size # arbitrarily set to 100
self.active_unlearner = active_unlearner # point to calling au instance
self.sort_first = sort_first
self.opt = distance_opt
self.working_set = working_set
# if 'frequency' in self.opt:
# self.working_set = [train for train in working_set]
# else:
# self.working_set = working_set
self.ham = set()
self.spam = set()
if 'frequency' in self.opt:
self.cluster_word_frequency = helpers.get_word_frequencies(self.clustroid)
self.added = [] # keeps track of order emails are added
self.dist_list = self.distance_array(self.separate) # returns list containing dist from all emails in phantom space to center clustroid
self.cluster_set = self.make_cluster() # adds closest emails to cluster
self.divide() # adds cluster emails to ham and spam
def weighted_initial(self, working_set, mislabeled):
if mislabeled is None: # Note that mislabeled is sorted in descending order by fabs(.50-email.prob)
mislabeled = self.get_mislabeled()
t_e = self.driver.tester.train_examples
print "Total Cluster Centroids Chosen: ", len(self.mislabeled_chosen)
possible_centroids = list(mislabeled - self.mislabeled_chosen)
print len(possible_centroids), " mislabeled emails remaining as possible cluster centroids"
if len(possible_centroids) == 0: #No more centers to select
return NO_CENTROIDS
else:
possible_centroids.sort(key=lambda x: fabs(.50-x.prob), reverse=True)
mislabeled_point = possible_centroids[0] # Choose most potent mislabeled email
self.mislabeled_chosen.add(mislabeled_point)
print "Chose the mislabeled point: ", mislabeled_point.tag
print "Probability: ", mislabeled_point.prob
init_email = None
training = chain(t_e[0], t_e[1], t_e[2], t_e[3]) if working_set is None else working_set
if "frequency" in self.distance_opt:
min_distance = sys.maxint
mislabeled_point_frequencies = helpers.get_word_frequencies(mislabeled_point)
for email in training:
current_distance = distance(email, mislabeled_point_frequencies, self.distance_opt)
if current_distance < min_distance:
init_email = email
min_distance = current_distance
elif self.distance_opt == "intersection":
min_distance = -1
for email in training: # select closest email to randomly selected mislabeled test email
current_distance = distance(email, mislabeled_point, self.distance_opt)
if current_distance > min_distance:
init_email = email
min_distance = current_distance
else:
min_distance = sys.maxint
for email in training: # select closest email to randomly selected mislabeled test email
current_distance = distance(email, mislabeled_point, self.distance_opt)
if current_distance < min_distance:
init_email = email
min_distance = current_distance
print type(init_email)
if init_email is None:
print "Training emails remaining: ", training
else:
print "-> selected ", init_email.tag, " as cluster centroid with distance of ", min_distance, " from mislabeled point"
return init_email
def __init__(self,
msg,
size,
active_unlearner,
distance_opt,
working_set=None,
sort_first=True,
separate=True):
self.clustroid = msg # seed of the cluster
if msg.train == 1 or msg.train == 3: # if ham set1 or ham set3
self.train = [1, 3]
elif msg.train == 0 or msg.train == 2: # if spam set1 or spam set3
self.train = [0, 2]
self.common_features = []
self.msg_index = {}
self.separate = separate
self.size = size # arbitrarily set to 100
self.active_unlearner = active_unlearner # point to calling au instance
self.sort_first = sort_first
self.opt = distance_opt
self.working_set = working_set
# if 'frequency' in self.opt:
# self.working_set = [train for train in working_set]
# else:
# self.working_set = working_set
self.ham = set()
self.spam = set()
if 'frequency' in self.opt:
self.cluster_word_frequency = helpers.get_word_frequencies(
self.clustroid)
self.added = [] # keeps track of order emails are added
self.dist_list = self.distance_array(
self.separate
) # returns list containing dist from all emails in phantom space to center clustroid
self.cluster_set = self.make_cluster(
) # adds closest emails to cluster
self.divide() # adds cluster emails to ham and spam
def weighted_initial(self, working_set, mislabeled):
if mislabeled is None: # Note that mislabeled is sorted in descending order by fabs(.50-email.prob)
mislabeled = self.get_mislabeled()
t_e = self.driver.tester.train_examples
print "Total Cluster Centroids Chosen: ", len(self.mislabeled_chosen)
possible_centroids = list(mislabeled - self.mislabeled_chosen)
print len(
possible_centroids
), " mislabeled emails remaining as possible cluster centroids"
if len(possible_centroids) == 0: #No more centers to select
return NO_CENTROIDS
else:
possible_centroids.sort(key=lambda x: fabs(.50 - x.prob),
reverse=True)
mislabeled_point = possible_centroids[
0] # Choose most potent mislabeled email
self.mislabeled_chosen.add(mislabeled_point)
print "Chose the mislabeled point: ", mislabeled_point.tag
print "Probability: ", mislabeled_point.prob
init_email = None
training = chain(t_e[0], t_e[1], t_e[2],
t_e[3]) if working_set is None else working_set
if "frequency" in self.distance_opt:
min_distance = sys.maxint
mislabeled_point_frequencies = helpers.get_word_frequencies(
mislabeled_point)
for email in training:
current_distance = distance(email,
mislabeled_point_frequencies,
self.distance_opt)
if current_distance < min_distance:
init_email = email
min_distance = current_distance
elif self.distance_opt == "intersection":
min_distance = -1
for email in training: # select closest email to randomly selected mislabeled test email
current_distance = distance(email, mislabeled_point,
self.distance_opt)
if current_distance > min_distance:
init_email = email
min_distance = current_distance
else:
min_distance = sys.maxint
for email in training: # select closest email to randomly selected mislabeled test email
current_distance = distance(email, mislabeled_point,
self.distance_opt)
if current_distance < min_distance:
init_email = email
min_distance = current_distance
print type(init_email)
if init_email is None:
print "Training emails remaining: ", training
else:
print "-> selected ", init_email.tag, " as cluster centroid with distance of ", min_distance, " from mislabeled point"
return init_email
