一、请知晓
本文是基于:
Event Recommendation Engine Challenge分步解析第一步
Event Recommendation Engine Challenge分步解析第二步
需要读者先阅读前两篇文章解析
二、用户社交关系信息处理
这一步需要user_friends.csv.gz文件,我们先来看看文件内容:
import pandas as pd df_user_friends = pd.read_csv('user_friends.csv.gz', compression='gzip') df_user_friends.head()
代码示例结果(发现该记录了用户的所有朋友信息):
1)变量解释
nusers:train.csv和test.csv文件涉及的所有用户数目,3391
self.numFriends:一维向量,每个元素记录了(3391个)每个用户的朋友数目,然后除以总的朋友数(sumNumFriends),得到每个用户的朋友占比
import scipy.io as sio import pandas as pd numFriends = sio.mmread('UF_numFriends') pd.DataFrame(numFriends)
代码示例结果:
self.userFriends:稀疏矩阵,shape为(3391,3391),记录每个用户与其朋友的score矩阵,最后归一化
import scipy.io as sio import pandas as pd userFriends = sio.mmread('UF_userFriends').todense() pd.DataFrame(userFriends)
代码示例结果:
userEventScores:临时变量,记录某个用户的某个朋友对每个event的兴趣分(1,0,or -1)
sumNumFriends:每个用户的朋友数相加之和
2)记录对user_friends.csv.gz文件操作
逐行读取user_friends.csv.gz文件
如果用户在第一步中userIndex中,获取该用户的朋友数目,并保存在self.numFriends中
对于该用户每一个朋友,只操作存在于第一步中userIndex中的朋友
获得该朋友的Index,利用该index去操作第一步中的userEventScores,这个userEventScores记录了每个用户对每个event的兴趣分(1,0,or -1),这样我们就获得了该用户的该朋友对每个event的兴趣分,
并求得该用户的该朋友的平均兴趣分(对每个event的兴趣分和除以总得event数-13481)
3)有了上面对user_friends.csv.gz文件操作说明,我们来看看完整代码
from collections import defaultdict import locale, pycountry import scipy.sparse as ss import scipy.io as sio import itertools #import cPickle #From python3, cPickle has beed replaced by _pickle import _pickle as cPickle import scipy.spatial.distance as ssd import datetime from sklearn.preprocessing import normalize import gzip import numpy as np #处理user和event关联数据 class ProgramEntities: """ 我们只关心train和test中出现的user和event,因此重点处理这部分关联数据, 经过统计:train和test中总共3391个users和13418个events """ def __init__(self): #统计训练集中有多少独立的用户的events uniqueUsers = set()#uniqueUsers保存总共多少个用户:3391个 uniqueEvents = set()#uniqueEvents保存总共多少个events:13418个 eventsForUser = defaultdict(set)#字典eventsForUser保存了每个user:所对应的event usersForEvent = defaultdict(set)#字典usersForEvent保存了每个event:哪些user点击 for filename in ['train.csv', 'test.csv']: f = open(filename) f.readline()#跳过第一行 for line in f: cols = line.strip().split(',') uniqueUsers.add( cols[0] ) uniqueEvents.add( cols[1] ) eventsForUser[cols[0]].add( cols[1] ) usersForEvent[cols[1]].add( cols[0] ) f.close() self.userEventScores = ss.dok_matrix( ( len(uniqueUsers), len(uniqueEvents) ) ) self.userIndex = dict() self.eventIndex = dict() for i, u in enumerate(uniqueUsers): self.userIndex[u] = i for i, e in enumerate(uniqueEvents): self.eventIndex[e] = i ftrain = open('train.csv') ftrain.readline() for line in ftrain: cols = line.strip().split(',') i = self.userIndex[ cols[0] ] j = self.eventIndex[ cols[1] ] self.userEventScores[i, j] = int( cols[4] ) - int( cols[5] ) ftrain.close() sio.mmwrite('PE_userEventScores', self.userEventScores) #为了防止不必要的计算,我们找出来所有关联的用户或者关联的event #所谓关联用户指的是至少在同一个event上有行为的用户user pair #关联的event指的是至少同一个user有行为的event pair self.uniqueUserPairs = set() self.uniqueEventPairs = set() for event in uniqueEvents: users = usersForEvent[event] if len(users) > 2: self.uniqueUserPairs.update( itertools.combinations(users, 2) ) for user in uniqueUsers: events = eventsForUser[user] if len(events) > 2: self.uniqueEventPairs.update( itertools.combinations(events, 2) ) #rint(self.userIndex) cPickle.dump( self.userIndex, open('PE_userIndex.pkl', 'wb')) cPickle.dump( self.eventIndex, open('PE_eventIndex.pkl', 'wb') ) #数据清洗类 class DataCleaner: def __init__(self): #一些字符串转数值的方法 #载入locale self.localeIdMap = defaultdict(int) for i, l in enumerate(locale.locale_alias.keys()): self.localeIdMap[l] = i + 1 #载入country self.countryIdMap = defaultdict(int) ctryIdx = defaultdict(int) for i, c in enumerate(pycountry.countries): self.countryIdMap[c.name.lower()] = i + 1 if c.name.lower() == 'usa': ctryIdx['US'] = i if c.name.lower() == 'canada': ctryIdx['CA'] = i for cc in ctryIdx.keys(): for s in pycountry.subdivisions.get(country_code=cc): self.countryIdMap[s.name.lower()] = ctryIdx[cc] + 1 self.genderIdMap = defaultdict(int, {'male':1, 'female':2}) #处理LocaleId def getLocaleId(self, locstr): #这样因为localeIdMap是defaultdict(int),如果key中没有locstr.lower(),就会返回默认int 0 return self.localeIdMap[ locstr.lower() ] #处理birthyear def getBirthYearInt(self, birthYear): try: return 0 if birthYear == 'None' else int(birthYear) except: return 0 #性别处理 def getGenderId(self, genderStr): return self.genderIdMap[genderStr] #joinedAt def getJoinedYearMonth(self, dateString): dttm = datetime.datetime.strptime(dateString, "%Y-%m-%dT%H:%M:%S.%fZ") return "".join( [str(dttm.year), str(dttm.month) ] ) #处理location def getCountryId(self, location): if (isinstance( location, str)) and len(location.strip()) > 0 and location.rfind(' ') > -1: return self.countryIdMap[ location[location.rindex(' ') + 2: ].lower() ] else: return 0 #处理timezone def getTimezoneInt(self, timezone): try: return int(timezone) except: return 0 #用户与用户相似度矩阵 class Users: """ 构建user/user相似度矩阵 """ def __init__(self, programEntities, sim=ssd.correlation):#spatial.distance.correlation(u, v) #计算向量u和v之间的相关系数 cleaner = DataCleaner() nusers = len(programEntities.userIndex.keys())#3391 #print(nusers) fin = open('users.csv') colnames = fin.readline().strip().split(',') #7列特征 self.userMatrix = ss.dok_matrix( (nusers, len(colnames)-1 ) )#构建稀疏矩阵 for line in fin: cols = line.strip().split(',') #只考虑train.csv中出现的用户,这一行是作者注释上的,但是我不是很理解 #userIndex包含了train和test的所有用户,为何说只考虑train.csv中出现的用户 if cols[0] in programEntities.userIndex: i = programEntities.userIndex[ cols[0] ]#获取user:对应的index self.userMatrix[i, 0] = cleaner.getLocaleId( cols[1] )#locale self.userMatrix[i, 1] = cleaner.getBirthYearInt( cols[2] )#birthyear,空值0填充 self.userMatrix[i, 2] = cleaner.getGenderId( cols[3] )#处理性别 self.userMatrix[i, 3] = cleaner.getJoinedYearMonth( cols[4] )#处理joinedAt列 self.userMatrix[i, 4] = cleaner.getCountryId( cols[5] )#处理location self.userMatrix[i, 5] = cleaner.getTimezoneInt( cols[6] )#处理timezone fin.close() #归一化矩阵 self.userMatrix = normalize(self.userMatrix, norm='l1', axis=0, copy=False) sio.mmwrite('US_userMatrix', self.userMatrix) #计算用户相似度矩阵,之后会用到 self.userSimMatrix = ss.dok_matrix( (nusers, nusers) )#(3391,3391) for i in range(0, nusers): self.userSimMatrix[i, i] = 1.0 for u1, u2 in programEntities.uniqueUserPairs: i = programEntities.userIndex[u1] j = programEntities.userIndex[u2] if (i, j) not in self.userSimMatrix: #print(self.userMatrix.getrow(i).todense()) 如[[0.00028123,0.00029847,0.00043592,0.00035208,0,0.00032346]] #print(self.userMatrix.getrow(j).todense()) 如[[0.00028123,0.00029742,0.00043592,0.00035208,0,-0.00032346]] usim = sim(self.userMatrix.getrow(i).todense(),self.userMatrix.getrow(j).todense()) self.userSimMatrix[i, j] = usim self.userSimMatrix[j, i] = usim sio.mmwrite('US_userSimMatrix', self.userSimMatrix) #用户社交关系挖掘 class UserFriends: """ 找出某用户的那些朋友,想法非常简单 1)如果你有更多的朋友,可能你性格外向,更容易参加各种活动 2)如果你朋友会参加某个活动,可能你也会跟随去参加一下 """ def __init__(self, programEntities): nusers = len(programEntities.userIndex.keys())#3391 self.numFriends = np.zeros( (nusers) )#array([0., 0., 0., ..., 0., 0., 0.]),保存每一个用户的朋友数 self.userFriends = ss.dok_matrix( (nusers, nusers) ) fin = gzip.open('user_friends.csv.gz') print( 'Header In User_friends.csv.gz:',fin.readline() ) ln = 0 #逐行打开user_friends.csv.gz文件 #判断第一列的user是否在userIndex中,只有user在userIndex中才是我们关心的user #获取该用户的Index,和朋友数目 #对于该用户的每一个朋友,如果朋友也在userIndex中,获取其朋友的userIndex,然后去userEventScores中获取该朋友对每个events的反应 #score即为该朋友对所有events的平均分 #userFriends矩阵记录了用户和朋友之间的score #如851286067:1750用户出现在test.csv中,该用户在User_friends.csv.gz中一共2151个朋友 #那么其朋友占比应该是2151 / 总的朋友数sumNumFriends=3731377.0 = 2151 / 3731377 = 0.0005764627910822198 for line in fin: if ln % 200 == 0: print( 'Loading line:', ln ) cols = line.decode().strip().split(',') user = cols[0] if user in programEntities.userIndex: friends = cols[1].split(' ')#获得该用户的朋友列表 i = programEntities.userIndex[user] self.numFriends[i] = len(friends) for friend in friends: if friend in programEntities.userIndex: j = programEntities.userIndex[friend] #the objective of this score is to infer the degree to #and direction in which this friend will influence the #user's decision, so we sum the user/event score for #this user across all training events eventsForUser = programEntities.userEventScores.getrow(j).todense()#获取朋友对每个events的反应:0, 1, or -1 #print(eventsForUser.sum(), np.shape(eventsForUser)[1] ) #socre即是用户朋友在13418个events上的平均分 score = eventsForUser.sum() / np.shape(eventsForUser)[1]#eventsForUser = 13418, #print(score) self.userFriends[i, j] += score self.userFriends[j, i] += score ln += 1 fin.close() #归一化数组 sumNumFriends = self.numFriends.sum(axis=0)#每个用户的朋友数相加 print(sumNumFriends) self.numFriends = self.numFriends / sumNumFriends#每个user的朋友数目比例 sio.mmwrite('UF_numFriends', np.matrix(self.numFriends) ) self.userFriends = normalize(self.userFriends, norm='l1', axis=0, copy=False) sio.mmwrite('UF_userFriends', self.userFriends) print('第1步:统计user和event相关信息...') pe = ProgramEntities() print('第1步完成... ') print('第2步:计算用户相似度信息,并用矩阵形式存储...') #Users(pe) print('第2步完成... ') print('第3步:计算用户社交关系信息,并存储...') UserFriends(pe) print('第3步完成... ')
至此,第三步完成,哪里有不明白的请留言