def __init__(self, records):
Cluster.__init__(self, records)
vote = dict()
count = dict()
for r in records:
if r.test != 0: continue
basic.AddToDict(vote, r.item, r.vote)
basic.AddToDict(count, r.item, 1)
k = 0
for item, v in vote.items():
ave = v / (count[item] * 1.0)
c = int(ave * 2)
self.group[item] = c
def UserSimilarity(records):
item_users = dict()
ave_vote = dict()
activity = dict()
for r in records:
if r.test != 0: continue
basic.AddToMat(item_users, r.item, r.user, r.vote)
basic.AddToDict(ave_vote, r.user, r.vote)
basic.AddToDict(activity, r.user, 1)
ave_vote = {x:y/activity[x] for x,y in ave_vote.items()}
nu = dict()
W = dict()
for i,ri in item_users.items():
for u,rui in ri.items():
basic.AddToDict(nu, u, (rui - ave_vote[u])*(rui - ave_vote[u]))
for v,rvi in ri.items():
if u == v: continue
basic.AddToMat(W, u, v, (rui - ave_vote[u])*(rvi - ave_vote[v]))
for u in W:
W[u]= {x:y/math.sqrt(nu[x]*nu[u]) for x,y in W[u].items()}
return W,ave_vote
def __init__(self, records):
Cluster.__init__(self, records)
popularity = dict()
for r in records:
if r.test != 0: continue
basic.AddToDict(popularity, r.item, 1)
k = 0
for item, n in sorted(popularity.items(),
key=itemgetter(1),
reverse=False):
c = int((k * 5) / (1.0 * len(popularity)))
self.group[item] = c
k += 1
def __init__(self, records):
Cluster.__init__(self, records)
activity = dict()
for r in records:
if r.test != 0: continue
basic.AddToDict(activity, r.user, 1)
k = 0
for user, n in sorted(activity.items(),
key=itemgetter(1),
reverse=False):
c = int((k * 5) / (1.0 * len(activity)))
self.group[user] = c
k += 1