根据用户注册信息推荐 代码部分

代码1：

# coding=gbk
'''
数据集：
BX-Users.csv，包含用户的ID、位置和年龄。
BX-Books.csv，包含图书的ISBN、标题、作者、发表年代、出版社和缩略。
BX-Book-Ratings.csv， 包含用户对图书的评分信息。

比较两种p(f,i)两种定义方式，给[年龄<25]和[年龄>50]两类用户推荐的前10本书
'''
import pandas as pd
users=pd.read_csv('../data/BX-Users.csv',sep=';',dtype={'Age':float})
books=pd.read_csv('../data/BX-Books.csv',sep=';',escapechar='\')
rates=pd.read_csv('../data/BX-Book-Ratings.csv',sep=';',nrows=80000,dtype={'Book-Rating':float})

#分类用户,只保存用户ID
AgeL25=set(users[users.Age<25].ix[:,0])
AgeG50=set(users[users.Age>25].ix[:,0])

#以字典形式存储书的id和名称
books={a:b for a, b in books[[0,1]].itertuples(index=False)}
rates=rates[rates['ISBN'].isin(books)]

RateL25=rates[rates['User-ID'].isin(AgeL25)]
RateG50=rates[rates['User-ID'].isin(AgeG50)]

#第一种方式，使用 25岁以下用户最热门书籍作为给25岁以下用户的推荐，50岁以上亦同
#这种方式会将全年龄段都热门书籍推荐给25岁以下用户

rankL25=dict()

#按书籍分组
groups = RateL25.groupby(['ISBN'])
for book,group in groups:
    rankL25[book]=len(group)

recL25=[books[x[0]] for x in sorted(rankL25.items(),lambda x,y:cmp(x[1],y[1]),reverse=True)[0:5]]

rankG50=dict()

#按书籍分组
groups = RateG50.groupby(['ISBN'])
for book,group in groups:
    rankG50[book]=len(group)

recG50=[books[x[0]] for x in sorted(rankG50.items(),lambda x,y:cmp(x[1],y[1]),reverse=True)[0:5]]

print recL25
print recG50

'''
结果中有三本书是一样的，因为这三本书各年龄段都热门
['Wild Animus', 'The Lovely Bones: A Novel', 'The Da Vinci Code', "Harry Potter and the Sorcerer's Stone (Harry Potter (Paperback))", "She's Come Undone (Oprah's Book Club)"]
['Wild Animus', 'The Lovely Bones: A Novel', 'The Da Vinci Code', 'Life of Pi', 'Divine Secrets of the Ya-Ya Sisterhood: A Novel']
'''

#第2中方式，将读者中25岁以下用户占比最大的小说推荐给25岁以下用户，50岁以上亦同
#这种方式可以解决全年龄段热门读物会都被推荐的问题
#当有本书只有一个读者时，它的推荐比重就会是1，在分母中加上alpha，为了解决这个问题
alpha=10

groups = rates.groupby(['ISBN'])
bookrates={book:len(group) for book,group in groups}

for book,rank in rankL25.items():
    rankL25[book]=rank/(bookrates[book]+alpha)
recL25=[books[x[0]] for x in sorted(rankL25.items(),lambda x,y:cmp(x[1],y[1]),reverse=True)[0:5]]

for book,rank in rankG50.items():
    rankG50[book]=rank/(bookrates[book]+alpha)
recG50=[books[x[0]] for x in sorted(rankG50.items(),lambda x,y:cmp(x[1],y[1]),reverse=True)[0:5]]

print recL25
print recG50

代码2：

# coding=gbk
import pandas as pd
from sklearn import cross_validation

users=pd.read_csv('data/BX-Users.csv',sep=';',dtype={'Age':float})
rates=pd.read_csv('data/BX-Book-Ratings.csv',sep=';',dtype={'Book-Rating':float})

#排除年龄为空及小于3岁和大于110岁的用户信息，以及其评价信息
users=users[(pd.notnull(users['Age']))&(users['Age']>0)&(users['Age']<100)]#只取用户ID和年龄
rates=rates[rates['User-ID'].isin(users['User-ID'])]#排除年龄不对的用户的评价

#地址只取国籍
def dealLocation(x):
    z=x['Location'].split(',')
    if len(z)<3:
        return 'False'
    else:
        return z[len(z)-1].strip()
users['Location']=users.apply(dealLocation,axis=1)
userdict = {a:(b,c) for a, b, c in users.itertuples(index=False)}

#先按国籍分组，然后按年龄分组，年龄从1到99岁，划分为20个区间
groups=users.groupby(['Location'])
userclass=dict()
userclassRec=dict()
for loc,group in groups:
    userclass[loc]=dict()
    userclassRec[loc]=dict()
    for i in range(20):
        userclass[loc][i]=set(group[(group['Age']>(i*5))&(group['Age']<=((i+1)*5))]['User-ID'])
        userclassRec[loc][i]=dict()

#将评分分为测试组和训练组
train,test=cross_validation.train_test_split(rates,test_size=0.2)
train = pd.DataFrame(train,columns=['User-ID', 'ISBN', 'Book-Rating'])
test = pd.DataFrame(test,columns=['User-ID', 'ISBN', 'Book-Rating'])

#计算每类用户的推荐
groups=train.groupby(['ISBN'])
for book,group in groups:
    busers=set(group['User-ID'])
    for u in busers:
        uinfo = userdict[u]
        loc = uinfo[0]
        ageclass = int((uinfo[1]-1)/5)
        if book not in userclassRec[loc][ageclass]:
            userclassRec[loc][ageclass][book]=0
        userclassRec[loc][ageclass][book]+=1.0/(len(busers)+5)

#根据评分各个用户组里的书籍
for loc,ages in userclassRec.items():
    for age,books in ages.items():
        userclassRec[loc][age]=[i[0] for i in sorted(userclassRec[loc][age].items(),lambda x,y:cmp(x[1],y[1]),reverse=True)[0:20]]
        

groups=test.groupby(['User-ID'])
total=0
accurate=0
for u,group in groups:
    uinfo = userdict[u]
    loc = uinfo[0]
    ageclass = int((uinfo[1]-1)/5)
    
    total += len(userclassRec[loc][ageclass])
    for book in set(group['ISBN']):
        if book in userclassRec[loc][ageclass]:
            accurate +=1

print accurate*1.0/total