数据挖掘之Apriori算法详解和Python实现代码分享(3)
def loop(self):
"s级频繁项级的迭代"
s = 2
while True:
print '-'*80
print 'The' ,s - 1,'loop'
print 'location' , self.location
print 'support' , self.support
print 'num' , self.num
print '-'*80
# 生成下一级候选集
location = self.select(s)
support = self.sut(location)
support, location = self.del_location(support, location)
num = list(sorted(set([j for i in location for j in i])))
s += 1
if location and support and num:
self.pre_num = self.num
self.pre_location = self.location
self.pre_support = self.support
self.num = num
self.location = location
self.support = support
else:
break
def confidence_sup(self):
"计算confidence"
if sum(self.pre_support) == 0:
print 'min_support error' # 第一次迭代即失败
else:
for index_location,each_location in enumerate(self.location):
del_num = [each_location[:index] + each_location[index+1:] for index in range(len(each_location))] # 生成上一级频繁项级
del_num = [i for i in del_num if i in self.pre_location] # 删除不存在上一级频繁项级子集
del_support = [self.pre_support[self.pre_location.index(i)] for i in del_num if i in self.pre_location] # 从上一级支持度查找
# print del_num
# print self.support[index_location]
# print del_support
for index,i in enumerate(del_num): # 计算每个关联规则支持度和自信度
index_support = 0
if len(self.support) != 1:
index_support = index
support = float(self.support[index_location])/self.line_num * 100 # 支持度
s = [j for index_item,j in enumerate(self.item_name) if index_item in i]
if del_support[index]:
confidence = float(self.support[index_location])/del_support[index] * 100
if confidence > self.min_confidence:
print ','.join(s) , '->>' , self.item_name[each_location[index]] , ' min_support: ' , str(support) + '%' , ' min_confidence:' , str(confidence) + '%'
def main():
c = Apriori('basket.txt', 14, 3, 13)
d = Apriori('simple.txt', 50, 2, 6)
