协同过滤主要是计算人与人之间的距离,Python缔造的recommendations函数如下
####数据集(用户,电影名字,评分)
critics={'Lisa Rose': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
'Just My Luck': 3.0, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5,
'The Night Listener': 3.0},
'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5,
'Just My Luck': 1.5, 'Superman Returns': 5.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 3.5},
'Michael Phillips': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.0,
'Superman Returns': 3.5, 'The Night Listener': 4.0},
'Claudia Puig': {'Snakes on a Plane': 3.5, 'Just My Luck': 3.0,
'The Night Listener': 4.5, 'Superman Returns': 4.0,
'You, Me and Dupree': 2.5},
'Mick LaSalle': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'Just My Luck': 2.0, 'Superman Returns': 3.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 2.0},
'Jack Matthews': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'The Night Listener': 3.0, 'Superman Returns': 5.0, 'You, Me and Dupree': 3.5},
'Toby': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0,'Superman Returns':4.0}}
###计算举例的函数(人与人之间相似度)
def sim_pearson(prefs,p1,p2):
# Get the list of mutually rated items
si={}
for item in prefs[p1]:
if item in prefs[p2]: si[item]=1
# if they are no ratings in common, return 0
if len(si)==0: return 0
# Sum calculations
n=len(si)
# Sums of all the preferences
sum1=sum([prefs[p1][it] for it in si])
sum2=sum([prefs[p2][it] for it in si])
# Sums of the squares
sum1Sq=sum([pow(prefs[p1][it],2) for it in si])
sum2Sq=sum([pow(prefs[p2][it],2) for it in si])
# Sum of the products
pSum=sum([prefs[p1][it]*prefs[p2][it] for it in si])
# Calculate r (Pearson score)
num=pSum-(sum1*sum2/n)
den=sqrt((sum1Sq-pow(sum1,2)/n)*(sum2Sq-pow(sum2,2)/n))
if den==0: return 0
r=num/den
return r
####推荐方法
def getRecommendations(prefs,person,similarity=sim_pearson):
totals={}
simSums={}
for other in prefs:
# don't compare me to myself
if other==person: continue
sim=similarity(prefs,person,other)
# ignore scores of zero or lower
if sim<=0: continue
for item in prefs[other]:
# only score movies I haven't seen yet
if item not in prefs[person] or prefs[person][item]==0:
# Similarity * Score
totals.setdefault(item,0)
totals[item]+=prefs[other][item]*sim
# Sum of similarities
simSums.setdefault(item,0)
simSums[item]+=sim
# Create the normalized list
rankings=[(total/simSums[item],item) for item,total in totals.items()]
# Return the sorted list
rankings.sort()
rankings.reverse()
return rankings
调用方法
import recommendations
t=recommendations.getRecommendations(recommendations.critics,'Toby')
print (t)