关联规则Apriori

最新推荐文章于 2024-07-20 17:12:48 发布

敲代码的A强

最新推荐文章于 2024-07-20 17:12:48 发布

阅读量255

点赞数

文章标签： python 开发语言

本文链接：https://blog.csdn.net/szq207819993/article/details/128130662

版权

针对下列数据集找出所有频繁项集,并使用提升度找出所有关联规则。¶

item_list = [['牛奶','面包'],
['面包','尿布','啤酒','土豆'],
['牛奶','尿布','啤酒','可乐'],
['面包','牛奶','尿布','啤酒'],
['面包','牛奶','尿布','可乐']]

import pandas as pd
from mlxtend.frequent_patterns import apriori
from mlxtend.frequent_patterns import association_rules
from mlxtend.preprocessing import TransactionEncoder

item_list = [['牛奶','面包'],
['面包','尿布','啤酒','土豆'],
['牛奶','尿布','啤酒','可乐'],
['面包','牛奶','尿布','啤酒'],
['面包','牛奶','尿布','可乐']]

item_df = pd.DataFrame(item_list)
te = TransactionEncoder()
df_tf = te.fit_transform(item_list)
df = pd.DataFrame(df_tf,columns=te.columns_)
df_data = df[['可乐','啤酒','土豆','尿布','牛奶','面包']]
frequent_items = apriori(df_data,min_support=0.5,use_colnames=True)
display(frequent_items)

rules = association_rules(frequent_items,metric='lift',min_threshold=1)
display(rules)