def coverage(train,test,W, N):
recommend_items=set()
all_items=set()
for user in train.keys():
for item in train[user]:
all_items.add(item[1])
rank=user_cf(user,train,W,K) #getrecommendation(user,N)
rank = dict(sorted(rank.items(),key=itemgetter(1),reverse=True) [0:N])
for item in rank.keys():
recommend_items.add(item)
return len(recommend_items)/(len(all_items)*1.0)
def precision(train,test, W, N): hit=0 all=0 for user in train.keys(): if user not in test: continue tu=[x[1] for x in test[user]] rank=user_cf(user,train,W,K) #getrecommendation(user,N) rank = dict(sorted(rank.items(),key=itemgetter(1),reverse=True) [0:N]) for item,pui in rank.items(): if item in tu: hit+=1 all+=N return hit/(all*1.0)
def popularity(train,test, W, N):
item_popularity=dict()
for user,items in train.items():
for item in items:
if item[1] not in item_popularity:
item_popularity[item[1]]=0
item_popularity[item[1]]+=1
ret=0
n=0
for user in train.keys():
rank=user_cf(user,train,W,K) #getrecommendation(user,N)
for item in rank.keys():
ret+=math.log(1+item_popularity[item])
n+=1
ret/=n*1.0
return ret
ratings = load_data("ml-1m/ratings.dat")
movies = load_data("ml-1m/movies.dat")
k = 5
seed = time.time()
train, test = splitdata(ratings, M, k, seed)
def list_to_dict(rating):
return {"uid": rating[0], "movieid": rating[1], "rating": rating[2], "time": rating[3]}
def convert_train(train):
for k, ratings in train.iteritems():
train[k] = [list_to_dict(rating) for rating in ratings]
return train
print "improve_cos ..."
W = improve_cos(train)
print "user_cf ..."
for user in users:
rank = user_cf(user[0], train, W, K)
# print rank
print precision(train, test, W, N)
print recall(train, test, W, N)
print coverage(train, test, W, N)
print popularity(train, test, W, N)
