import?random
import?math
class?UserbasedCF:
????def?__init__（selfdatafile?=?None）:
????????self.datafile?=?datafile
????????self.readData（）
????????self.splitData（347）
????def?readData（selfdatafile?=?None）:
????????“““
????????read?the?data?from?the?data?file?which?is?a?data?set
????????“““
????????self.datafile?=?datafile?or?self.datafile
????????self.data?=?[]
????????for?line?in?open（self.datafile）:
????????????useriditemidrecordmtime?=?line.split（“\t“）
????????????self.data.append（（useriditemidint（record）））
????def?splitData（selfkseeddata?=?NoneM?=?8）:
????????“““
????????split?the?data?set
????????testdata?is?a?test?data?set
????????traindata?is?a?train?set
????????“““
????????self.testdata?=?{}
????????self.traindata?=?{}
????????data?=?data?or?self.data
????????random.seed（seed）
????????for?useritemrecord?in?self.data:
????????????if?random.randint（0M）?==?k:
????????????????self.testdata.setdefault（user{}）
????????????????self.testdata[user][item]?=?record
????????????else:
????????????????self.traindata.setdefault（user{}）
????????????????self.traindata[user][item]?=?record
????def?userSimilarity（selftrain?=?None）:
????????“““
????????one?method?of?getting?user?similarity?matrix
????????“““
????????train?=?train?or?self.traindata
????????self.userSim?=?dict（）
????????for?u?in?train.keys（）:
????????????for?v?in?train.keys（）:
????????????????if?u?==?v:
????????????????????continue
????????????????self.userSim.setdefault（u{}）
????????????????self.userSim[u][v]?=?len（set（train[u].keys（））?&?set（train[v].keys（）））
????????????????self.userSim[u][v]?/=?math.sqrt（len（train[u]）?*?len（train[v]）?*?1.0）

????def?userSimilarityBest（selftrain?=?None）:
????????“““
????????the?other?method?of?getting?user?similarity?which?is?better?than?above
????????you?can?get?the?method?on?page?46
????????In?this?experiment?we?use?this?method
????????“““
????????train?=?train?or?self.traindata
????????self.userSimBest?=?dict（）
????????item_users?=?dict（）
????????#build?inverse?table?for?item_users
????????for?uitem?in?train.items（）:
????????????for?i?in?item.keys（）:
????????????????item_users.setdefault（iset（））
????????????????item_users[i].add（u）
????????#calculate?co-rated?items?between?users
????????user_item_count?=?dict（）
????????count?=?dict（）
????????for?itemusers?in?item_users.items（）:
????????????for?u?in?users:
????????????????user_item_count.setdefault（u0）
????????????????user_item_count[u]?+=?1
????????????????for?v?in?users:
????????????????????if?u?==?v:
????????????????????????continue
????????????????????count.setdefault（u{}）
????????????????????count[u].setdefault（v0）
????????????????????count[u][v]?+=?1
????????#calculate?finial?similarity?matrix?W
????????for?urelated_users?in?count.items（）:
????????????self.userSimBest.setdefault（udict（））
????????????for?vcuv?in?related_users.items（）:
????????????????self.userSimBest[u][v]?=?cuv?/?math.sqrt（us

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件???????6527??2015-03-06?14:59??UserbasedCF\main.py

?????文件????????266??2015-03-06?15:50??UserbasedCF\Readme.txt

?????文件????1979173??2000-07-19?16:09??UserbasedCF\數據\u.data

?????目錄??????????0??2015-03-06?15:47??UserbasedCF\數據

?????目錄??????????0??2015-03-06?15:47??UserbasedCF

-----------?---------??----------?-----??----

??????????????1985966????????????????????5