def main(database, table, smooth_func, lambda_, min_tag_freq):
with AnnotReader(database) as reader:
reader.change_table(table)
#Builds value calculator
estimator = SmoothEstimator(smooth_func, lambda_, reader.iterate())
calculator = ValueCalculator(estimator)
#Determine tags which will be considered
tags_to_consider = []
if min_tag_freq < 0: #All tags
tags_to_consider = range(estimator.num_tags())
else:
counter = Counter(annot['tag'] for annot in reader.iterate())
for tag, pop in counter.iteritems():
if pop >= min_tag_freq:
tags_to_consider.append(tag)
#Dumps probabilities
connection = None
database = None
try:
items = np.arange(estimator.num_items())
for tag in tags_to_consider:
v_prob_it = calculator.rnorm_prob_items_given_tag(tag, items)
for item in xrange(len(v_prob_it)):
prob = float(v_prob_it[item])
print({'tag':tag, 'item':item, 'prob_it':prob})
finally:
if connection:
connection.disconnect()
def compute_for_user(database, table, user, relevant, annotated,
smooth_func, lambda_, user_profile_size, out_folder):
with AnnotReader(database) as reader:
reader.change_table(table)
#Relevant items by user are left out with this query
query = {'$or' : [
{ 'user':{'$ne' : user} },
{ 'item':{'$nin' : relevant} }
]
}
#Probability estimator
est = SmoothEstimator(smooth_func, lambda_,
reader.iterate(query = query),
user_profile_size = user_profile_size)
value_calc = value_calculator.ValueCalculator(est)
fname = 'user_%d' % user
user_folder = os.path.join(out_folder, fname)
os.mkdir(user_folder)
#Initial information
with io.open(os.path.join(user_folder, 'info'), 'w') as info:
info.write(u'#UID: %d\n' %user)
relevant_str = ' '.join([str(i) for i in relevant])
annotated_str = ' '.join([str(i) for i in annotated])
info.write(u'# %d relevant items: %s\n' %(len(relevant),
str(relevant_str)))
info.write(u'# %d annotated items: %s\n' %(len(annotated),
str(annotated_str)))
#Create Graph
iterator = reader.iterate(query = query)
tag_to_item, item_to_tag = \
index_creator.create_double_occurrence_index(iterator,
'tag', 'item')
#Items to consider <-> Gamma items
items_to_consider = set(xrange(est.num_items()))
annotated_set = set(annotated)
items_to_consider.difference_update(annotated_set)
compute_tag_values(est, value_calc, tag_to_item, user,
user_folder,
np.array([i for i in items_to_consider]))
relevant_tags_fpath = os.path.join(user_folder, 'relevant_item.tags')
with io.open(relevant_tags_fpath, 'w') as rel:
rel.write(u'#ITEM TAG\n')
for item in relevant:
for tag in item_to_tag[item]:
rel.write(u'%d %d\n' %(item, tag))
def compute_for_user(database, table, user, relevant, annotated, smooth_func,
lambda_, user_profile_size, out_folder):
with AnnotReader(database) as reader:
reader.change_table(table)
#Relevant items by user are left out with this query
query = {
'$or': [{
'user': {
'$ne': user
}
}, {
'item': {
'$nin': relevant
}
}]
}
#Probability estimator
est = SmoothEstimator(smooth_func,
lambda_,
reader.iterate(query=query),
user_profile_size=user_profile_size)
value_calc = value_calculator.ValueCalculator(est)
fname = 'user_%d' % user
user_folder = os.path.join(out_folder, fname)
os.mkdir(user_folder)
#Initial information
with io.open(os.path.join(user_folder, 'info'), 'w') as info:
info.write(u'#UID: %d\n' % user)
relevant_str = ' '.join([str(i) for i in relevant])
annotated_str = ' '.join([str(i) for i in annotated])
info.write(u'# %d relevant items: %s\n' %
(len(relevant), str(relevant_str)))
info.write(u'# %d annotated items: %s\n' %
(len(annotated), str(annotated_str)))
#Create Graph
iterator = reader.iterate(query=query)
tag_to_item, item_to_tag = \
index_creator.create_double_occurrence_index(iterator,
'tag', 'item')
#Items to consider <-> Gamma items
items_to_consider = set(xrange(est.num_items()))
annotated_set = set(annotated)
items_to_consider.difference_update(annotated_set)
compute_tag_values(est, value_calc, tag_to_item, user, user_folder,
np.array([i for i in items_to_consider]))
relevant_tags_fpath = os.path.join(user_folder, 'relevant_item.tags')
with io.open(relevant_tags_fpath, 'w') as rel:
rel.write(u'#ITEM TAG\n')
for item in relevant:
for tag in item_to_tag[item]:
rel.write(u'%d %d\n' % (item, tag))
