def test_run(self):
ap = Apriori(self.tidList, 63)
result = ap.run()
sort_f = lambda x: (x.support, x.item)
result.sort(key=sort_f)
self.targetSet.sort(key=sort_f)
self.assertListEqual(result, self.targetSet)
restrict_items = ["Bagel", "Cheese", "Milk"]
ap_restrict = Apriori(self.tidList, 63, restrict_items=restrict_items)
result_restrict = ap_restrict.run()
result_restrict.sort(key=sort_f)
target_restrict = list(
filter(lambda x: x.contains(restrict_items), self.targetSet))
self.assertListEqual(result_restrict, target_restrict)
class AprioriTestCase(unittest.TestCase):
def setUp(self):
_list = [
[1, 2, 3],
[1, 4],
[4, 5],
[1, 2, 4],
[1, 2, 6, 4, 3],
[2, 6, 3],
[2, 3, 6],
]
#trans list to Collection
tem_list = Collection()
for l in _list:
tem = Collection()
tem_list.append(tem)
for m in l:
tem.append(m)
self.apri = Apriori(tem_list, 0.3, 0.8)
def testInit_pass(self):
test_console('init_pass')
self.apri.init_pass()
print '.. self.apri.C : '
print self.apri.C
def testCadidate_gen(self):
temF = [
[1, 2, 3],
[2, 3, 4],
[4, 5, 6],
[1, 2, 3, 4],
[6, 7, 8],
]
collections = self.apri.Cadidate_gen(temF)
print '.. temF'
print temF
print '.. Cadidate_gen'
print collections
def testRun(self):
test_console('run')
self.apri.run()
def run(database, type, min_support=0.05, min_confidence=0.5):
if type == 'basic':
if database == 'Acme-Supermarket':
preprocessing = AcmeSupermarket(acme_filepath)
preprocessing.load()
algorithm = Apriori(min_support, min_confidence, acme_filepath)
rules = algorithm.run()
preprocessing.save_rules(rules)
elif database == 'Movielens':
preprocessing = Movielens(movie_filepath)
preprocessing.load()
algorithm = Apriori(min_support, min_confidence, movie_filepath)
rules = algorithm.run()
# Print?
else:
preprocessing = Retails(retails_filepath)
preprocessing.load()
algorithm = Apriori(min_support, min_confidence, retails_filepath)
rules = algorithm.run()
# print?
else:
if database == 'Acme-Supermarket':
preprocessing = AcmeSupermarket(acme_filepath)
preprocessing.load()
algorithm = AprioriEnhanced(min_support, min_confidence,
acme_filepath)
rules = algorithm.run()
preprocessing.save_rules(rules)
elif database == 'Movielens':
preprocessing = Movielens(movie_filepath)
preprocessing.load()
algorithm = AprioriEnhanced(min_support, min_confidence,
movie_filepath)
rules = algorithm.run()
# Print?
else:
preprocessing = Retails(retails_filepath)
preprocessing.load()
algorithm = AprioriEnhanced(min_support, min_confidence,
retails_filepath)
rules = algorithm.run()
# -*- coding: utf-8 -*-
from apriori import Apriori, ImprovedApriori
with open('after.csv', 'r') as fp:
lines = fp.readlines()
dataSet3 = []
for line in lines:
line = line.rstrip()
dataSet3.append(line.split(","))
minsup = 0.005
minconf = 0.5
if __name__ == '__main__':
# test1
apriori = Apriori(dataSet3, minsup, minconf)
apriori.run()
apriori.print_frequent_itemset()
apriori.print_rule()
def apriori():
session.rollback()
users = session.query(User).all()
favs = list()
for user in users:
favIds = list()
favorites = session.query(Favorite).filter_by(
user_mail=user.mail).all()
for favorite in favorites:
favIds.append(str(favorite.recipe_id))
favs.append(favIds)
minsup = 0.4
minconf = 0.4
apriori = Apriori(favs, minsup, minconf)
apriori.run()
apriori.print_frequent_itemset()
result = apriori.print_rule()
# print(result)
apriori_advices = list()
for res in result:
x = res.split(' ==> ')
# print(len(x[0]))
if len(x[0]) <= 2:
# print(x[0])
apriori_advices.append(x[0])
apriori_advices.append(x[1])
# print(apriori_advices)
key = list()
value = list()
i = 0
while i < len(apriori_advices):
key.append(int(apriori_advices[i]))
value.append(int(apriori_advices[i + 1]))
i += 4
favorites = session.query(Favorite).filter_by(user_mail=g.user.mail).all()
print(favorites)
favoriteIds = list()
for favorite in favorites:
favoriteIds.append(favorite.recipe_id)
print(favoriteIds)
print(key)
adviceIds = list()
i = 0
if (len(favoriteIds) > 0):
while i < len(key):
if contains(fs, key[i]) != True:
adviceIds.append(value[i])
i += 1
print(adviceIds)
adviceIds = list(set(adviceIds))
print(adviceIds)
advices = session.query(Recipe).filter(Recipe.id.in_(adviceIds)).all()
return jsonify([advice.serialize for advice in advices]), 201
keys = set()
transactionData = list()
for line in f:
line = str(line).replace("\n", "")
transactionItems = str(line).split(",")
transactionData.append(transactionItems)
return transactionData
# dataset = [
# ['bread', 'milk'],
# ['bread', 'diaper', 'beer', 'egg'],
# ['milk', 'diaper', 'beer', 'cola'],
# ['bread', 'milk', 'diaper', 'beer'],
# ['bread', 'milk', 'diaper', 'cola'],
# ]
dataset = getDataset()
minsup = 0.01
minconf = 0.4
ap = Apriori(dataset, minsup, minconf)
# run algorithm
ap.run()
# print out frequent itemset
ap.print_frequent_itemset()
# print out rules
ap.print_rule()
