def FP_growth(self,headnode,headtable):
a=self.a
if tree.checkTreeOneWay(headnode):
add=unit.generateCombination(headtable,a,self.support)
if len(add)>0:
tree.frequent+=add
#print('frequent')
#print('1',tree.frequent)
pass
else:
for item in headtable:
#datas为条件模式基
datas=unit.generateSubset(headtable,item,self.a,tree.frequent)
if datas:
#print('2',item)
if item:
x=a[:]
x.append(item)
f=FP_Grow_tree.FP_Grow_tree(datas,x,self.support)
#print('----------------ddddd-')
#print(item,f.f.pretable)
for jix in f.f.pretable:
xx=a[:]
xx.append(item)
xx.append(jix[0])
tree.frequent.append((",".join(str(i) for i in xx),jix[1]))
pass
pass
pass
pass
arr.append(list)
list = []
return arr
sample = [['milk', 'eggs', 'bread', 'chips'],
['eggs', 'popcorn', 'chips', 'beer'], ['eggs', 'bread', 'chips'],
['milk', 'eggs', 'bread', 'popcorn', 'chips', 'beer'],
['milk', 'bread', 'beer'], ['eggs', 'bread', 'beer'],
['milk', 'bread', 'chips'],
['milk', 'eggs', 'bread', 'butter', 'chips'],
['milk', 'eggs', 'butter', 'chips']]
sample2 = [['r', 'z', 'h', 'j', 'p'], ['z', 'y', 'x', 'w', 'v', 'u', 't', 's'],
['z'], ['r', 'x', 'n', 'o', 's'],
['y', 'r', 'x', 'z', 'q', 't', 'p'],
['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]
sample1 = [[u'牛奶', u'鸡蛋', u'面包', u'薯片'], [u'鸡蛋', u'爆米花', u'薯片', u'啤酒'],
[u'鸡蛋', u'面包', u'薯片'], [u'牛奶', u'鸡蛋', u'面包', u'爆米花', u'薯片', u'啤酒'],
[u'牛奶', u'面包', u'啤酒'], [u'鸡蛋', u'面包', u'啤酒'], [u'牛奶', u'面包', u'薯片'],
[u'牛奶', u'鸡蛋', u'面包', u'黄油', u'薯片'], [u'牛奶', u'鸡蛋', u'黄油', u'薯片']]
sample3 = add_matix()
#print(sample1)
##参数说明 sample为事务数据集 []为递归过程中的基,support为最小支持度
support = 200
ff = FP_Grow_tree.FP_Grow_tree(sample3, [], support)
##打印频繁集
ff.printfrequent()
ff.printconfident(0.9)
data.iloc[r,c]=data.iloc[0,c]
data.to_excel("./data666.xls")
"""
data = pd.read_excel("./data666.xls", encoding="utf-8")
# 将交易记录变成列表的形式
dataSet = []
for i in range(1, 748):
d1 = data.iloc[i, :].tolist()
d1 = [x for x in d1 if str(x) != 'nan']
dataSet.append(d1)
#print(dataSet)
# =========================================================================================
print(">>>>>>>>>>>>>>> 使用FP_Growth_tree >>>>>>>>>>>>>>>>>>>>>")
time1 = time.time()
support = 300 # 支持度设为300
ff = FP_Grow_tree.FP_Grow_tree(dataSet, [], support)
# 打印频繁集
ff.printfrequent()
time2 = time.time()
print('FP_Growth_tree耗时：', str(time2 - time1))
# =======================================================================================
print(">>>>>>>>>>>>>>> 使用Apriori >>>>>>>>>>>>>>>>>>>>>")
time1 = time.time()
l, suppdata = apri.apriori(dataSet) # 对数据集使用apriori算法
print(l)
rules = apri.generateRules(l, suppdata, minconf=0.7) # 生成关联规则，最小置信度设为0.7
print(rules)
time2 = time.time()
print('Apriori耗时：', time2 - time1)