def generate_Lk(min_sup_src, L_k1, C_k, k):
for key, hash_item_collection in L_k1.get_items():
for index in range(hash_item_collection.size() - 1):
new_key = ''
index_th_item = hash_item_collection.get_item(index)
if key == '':
new_key = index_th_item.last_item
else:
new_key = key +',' + index_th_item.last_item
new_hash_collection = HashItemCollection()
#check if it is infrequent item-set
for item in hash_item_collection.get_items_from(index + 1):
'''
Create new itemset and check its support
'''
new_item = HashItem(item.last_item)
inter_items = set(index_th_item.tids).intersection(item.tids)
if len(inter_items) >= min_sup_src:
new_item.add_tids(list(inter_items))
new_hash_collection.add_item(new_item)
'''
Add the new itemsets into next level if there's any.
'''
if new_hash_collection.size() > 0:
C_k.insert(new_key, new_hash_collection)
def deserialize(self, file_name, reset_table=True):
if reset_table == True:
self.table = {}
with open(file_name, "r") as text_file:
k = 0
collection_key = None
for line in text_file:
if k % 2 == 0:
collection_key = line.strip()
else:
collection = HashItemCollection()
collection.deserialize(line.strip())
self.table[collection_key] = collection
k = k + 1
def generate_Lk_vw(min_sup, L_k1, C_k_file, k):
print('generate candidates with ' + str(k) + ' items')
file_writer = open(C_k_file, 'w')
for key, hash_item_collection in L_k1.get_items():
for index in range(hash_item_collection.size() - 1):
index_th_item = hash_item_collection.get_item(index)
new_key = ''
if key == '':
new_key = index_th_item.last_item
else:
new_key = key +',' + index_th_item.last_item
new_hash_collection = HashItemCollection()
#check if it is infrequent item-set
for item in hash_item_collection.get_items_from(index + 1):
new_item = HashItem(item.last_item)
inter_items = set(index_th_item.tids).intersection(item.tids)
if len(inter_items) >= min_sup:
new_item.add_tids(list(inter_items))
new_hash_collection.add_item(new_item)
if new_hash_collection.size() > 0:
file_writer.write(new_key)
file_writer.write('\n')
file_writer.write(new_hash_collection.serialize())
file_writer.write('\n')
file_writer.close()
def generate_Lk_w(min_sup_src, L_k1, C_k_file, k, inclusive_items_dict):
#print('generate candidates with ' + str(k) + ' items')
file_writer = open(C_k_file, 'w')
for key, hash_item_collection in L_k1.get_items():
for index in range(hash_item_collection.size() - 1):
index_th_item = hash_item_collection.get_item(index)
new_key = ''
if key == '':
new_key = index_th_item.last_item
else:
new_key = key + ',' + index_th_item.last_item
new_hash_collection = HashItemCollection()
#check if it is infrequent item-set
previous_itemset = string_2_itemset(new_key)
for item in hash_item_collection.get_items_from(index + 1):
'''
Check if the itemset contains any inclusive pair of items.
'''
if Apriori.checkInclusiveItems(previous_itemset,
item.last_item,
inclusive_items_dict):
continue
'''
Create new itemset and check its support
'''
new_item = HashItem(item.last_item)
inter_items = set(index_th_item.tids).intersection(
item.tids)
if len(inter_items) >= min_sup_src:
new_item.add_tids(list(inter_items))
new_hash_collection.add_item(new_item)
'''
Write the new itemsets into file if there's any.
'''
if new_hash_collection.size() > 0:
file_writer.write(new_key)
file_writer.write('\n')
file_writer.write(new_hash_collection.serialize())
file_writer.write('\n')
file_writer.close()
def insert_key(self, key):
self.table[key] = HashItemCollection()