class TopN(BaseEstimator):
def __init__(self, n=5):
print 'topN begin'
self.n = n
def gen_items_popular(self, trainSamples, trainTargets, hasTimes=False):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
itempopular = np.zeros(self.dataModel.getItemsNum())
uids = self.dataModel.getData().nonzero()[0]
iids = self.dataModel.getData().nonzero()[1]
for i in range(len(iids)):
iid = iids[i]
itempopular[iid] += 1
self.popItems = itempopular
def predict(self, testSamples):
recommend_lists = []
for user_item in testSamples:
if self.dataModel.getIidByItem(user_item[1]) in self.topN[:self.n]:
recommend_lists.append(1)
else:
recommend_lists.append(0)
return recommend_lists
def fit(self, trainSamples, trainTargets):
#print trainSamples, trainTargets
#print len(trainSamples), len(trainTargets)
self.gen_items_popular(trainSamples, trainTargets)
self.topN = np.argsort(np.array(self.popItems))[-1::-1]
return self
def recommend(self, uid):
return [self.dataModel.getItemByIid(i) for i in self.topN[:self.n]]
def score(self, testSamples, trueLabels):
#print testSamples
#print len(testSamples)
trueList = []
recommendList = []
user_unique = list(set(np.array(testSamples)[:, 0]))
for u in user_unique:
uTrueIndex = np.argwhere(np.array(testSamples)[:, 0] == u)[:, 0]
#true = [self.dataModel.getIidByItem(i) for i in list(np.array(testSamples)[uTrueIndex][:,1])]
true = list(np.array(testSamples)[uTrueIndex][:, 1])
trueList.append(true)
pre = [self.dataModel.getItemByIid(i) for i in self.topN[:self.n]]
recommendList.append(pre)
e = Eval()
result = e.evalAll(recommendList, trueList)
print 'TopN result:' + '(' + str(self.get_params()) + ')' + str(
(result)['F1'])
return (result)['F1']
class TopN(BaseEstimator):
def __init__(self, n=5):
print 'topN begin'
self.n = n
def gen_items_popular(self, trainSamples, trainTargets, hasTimes=False):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
itempopular = np.zeros(self.dataModel.getItemsNum())
uids = self.dataModel.getData().nonzero()[0]
iids = self.dataModel.getData().nonzero()[1]
for i in range(len(iids)):
iid = iids[i]
itempopular[iid] += 1
self.popItems = itempopular
def predict(self, testSamples):
recommend_lists = []
for user_item in testSamples:
if self.dataModel.getIidByItem(user_item[1]) in self.topN[:self.n]:
recommend_lists.append(1)
else:
recommend_lists.append(0)
return recommend_lists
def fit(self, trainSamples, trainTargets):
#print trainSamples, trainTargets
#print len(trainSamples), len(trainTargets)
self.gen_items_popular(trainSamples, trainTargets)
self.topN = np.argsort(np.array(self.popItems))[-1::-1]
return self
def recommend(self, uid):
return [self.dataModel.getItemByIid(i) for i in self.topN[:self.n]]
def score(self, testSamples, trueLabels):
#print testSamples
#print len(testSamples)
trueList = []
recommendList= []
user_unique = list(set(np.array(testSamples)[:,0]))
for u in user_unique:
uTrueIndex = np.argwhere(np.array(testSamples)[:,0] == u)[:,0]
#true = [self.dataModel.getIidByItem(i) for i in list(np.array(testSamples)[uTrueIndex][:,1])]
true = list(np.array(testSamples)[uTrueIndex][:,1])
trueList.append(true)
pre = [self.dataModel.getItemByIid(i) for i in self.topN[:self.n]]
recommendList.append(pre)
e = Eval()
result = e.evalAll(recommendList, trueList)
print 'TopN result:'+'('+str(self.get_params())+')'+str((result)['F1'])
return (result)['F1']
class LFM(BaseEstimator):
def __init__(self, n=5, factors=25, learningrate=0.05, userregular=0.0001, itemregular=0.0001, iter = 10):
print 'lfm begin'
self.factors = factors
self.n = n
self.learningrate = learningrate
self.userregular = userregular
self.itemregular = itemregular
self.iter = iter
def predict(self, testSamples):
recList = []
for user_item in testSamples:
uid = self.dataModel.getUidByUser(user_item[0])
recList.append(self.recommend(uid))
return recList
def fit(self, trainSamples, trainTargets):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
self.mu = np.array(trainTargets).mean()
self.bu = np.zeros(self.dataModel.getUsersNum())
self.bi = np.zeros(self.dataModel.getItemsNum())
temp = math.sqrt(self.factors)
self.qi = [[(0.1 * random.random() / temp) for j in range(self.factors)] for i in range(self.dataModel.getItemsNum())]
self.pu = [[(0.1 * random.random() / temp) for j in range(self.factors)] for i in range(self.dataModel.getUsersNum())]
lineData = self.dataModel.getLineData()
lengthOfTrain = len(lineData)
for step in range(self.iter):
rmse_sum = 0.0
hash = np.random.permutation(lengthOfTrain)
for j in range(lengthOfTrain):
n = hash[j]
row = lineData[n]
uid = self.dataModel.getUidByUser(row[0])
iid = self.dataModel.getIidByItem(row[1])
rating = row[2]
#rating = 1
eui = rating - self.predict_single(uid, iid)
rmse_sum += eui**2
self.bu[uid] += self.learningrate*(eui-self.userregular*self.bu[uid])
self.bi[iid] += self.learningrate*(eui-self.itemregular*self.bi[iid])
temp = self.qi[iid]
self.qi[iid] += self.learningrate*(np.dot(eui, self.pu[uid]) - np.dot(self.itemregular, self.qi[iid]))
self.pu[uid] += self.learningrate*(np.dot(eui, temp) - np.dot(self.userregular, self.pu[uid]))
self.learningrate = self.learningrate * 0.93
def predict_single(self, uid, iid):
ans = self.mu + self.bi[iid] + self.bu[uid] + np.dot(self.qi[iid], self.pu[uid])
if ans > 5:
return 5
elif ans < 1:
return 1
return ans
def recommend(self, u):
uid = self.dataModel.getUidByUser(u)
if uid == -1:
print 'not in test'
return []
else:
predict_scores = []
for i in range(self.dataModel.getItemsNum()):
predict_scores.append(self.predict_single(uid, i))
topN = np.argsort(np.array(predict_scores))[-1:-self.n-1:-1]
return [self.dataModel.getItemByIid(i) for i in topN]
def score(self, testSamples, trueLabels):
print 'LFM scoring ...'
trueList = []
recommendList= []
user_unique = list(set(np.array(testSamples)[:,0]))
for u in user_unique:
uTrueIndex = np.argwhere(np.array(testSamples)[:,0] == u)[:,0]
#true = [self.dataModel.getIidByItem(i) for i in list(np.array(testSamples)[uTrueIndex][:,1])]
true = list(np.array(testSamples)[uTrueIndex][:,1])
trueList.append(true)
pre = self.recommend(u)
recommendList.append(pre)
e = Eval()
result = e.evalAll(recommendList, trueList)
print 'LFM result:'+ '('+str(self.get_params())+')'+str((result)['F1'])
return (result)['F1']
class LFM(BaseEstimator):
def __init__(self,
n=5,
factors=25,
learningrate=0.05,
userregular=0.0001,
itemregular=0.0001,
iter=10):
print 'lfm begin'
self.factors = factors
self.n = n
self.learningrate = learningrate
self.userregular = userregular
self.itemregular = itemregular
self.iter = iter
def predict(self, testSamples):
recList = []
for user_item in testSamples:
uid = self.dataModel.getUidByUser(user_item[0])
recList.append(self.recommend(uid))
return recList
def fit(self, trainSamples, trainTargets):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
self.mu = np.array(trainTargets).mean()
self.bu = np.zeros(self.dataModel.getUsersNum())
self.bi = np.zeros(self.dataModel.getItemsNum())
temp = math.sqrt(self.factors)
self.qi = [[(0.1 * random.random() / temp)
for j in range(self.factors)]
for i in range(self.dataModel.getItemsNum())]
self.pu = [[(0.1 * random.random() / temp)
for j in range(self.factors)]
for i in range(self.dataModel.getUsersNum())]
lineData = self.dataModel.getLineData()
lengthOfTrain = len(lineData)
for step in range(self.iter):
rmse_sum = 0.0
hash = np.random.permutation(lengthOfTrain)
for j in range(lengthOfTrain):
n = hash[j]
row = lineData[n]
uid = self.dataModel.getUidByUser(row[0])
iid = self.dataModel.getIidByItem(row[1])
rating = row[2]
#rating = 1
eui = rating - self.predict_single(uid, iid)
rmse_sum += eui**2
self.bu[uid] += self.learningrate * (
eui - self.userregular * self.bu[uid])
self.bi[iid] += self.learningrate * (
eui - self.itemregular * self.bi[iid])
temp = self.qi[iid]
self.qi[iid] += self.learningrate * (
np.dot(eui, self.pu[uid]) -
np.dot(self.itemregular, self.qi[iid]))
self.pu[uid] += self.learningrate * (
np.dot(eui, temp) - np.dot(self.userregular, self.pu[uid]))
self.learningrate = self.learningrate * 0.93
def predict_single(self, uid, iid):
ans = self.mu + self.bi[iid] + self.bu[uid] + np.dot(
self.qi[iid], self.pu[uid])
if ans > 5:
return 5
elif ans < 1:
return 1
return ans
def recommend(self, u):
uid = self.dataModel.getUidByUser(u)
if uid == -1:
print 'not in test'
return []
else:
predict_scores = []
for i in range(self.dataModel.getItemsNum()):
predict_scores.append(self.predict_single(uid, i))
topN = np.argsort(np.array(predict_scores))[-1:-self.n - 1:-1]
return [self.dataModel.getItemByIid(i) for i in topN]
def score(self, testSamples, trueLabels):
print 'LFM scoring ...'
trueList = []
recommendList = []
user_unique = list(set(np.array(testSamples)[:, 0]))
for u in user_unique:
uTrueIndex = np.argwhere(np.array(testSamples)[:, 0] == u)[:, 0]
#true = [self.dataModel.getIidByItem(i) for i in list(np.array(testSamples)[uTrueIndex][:,1])]
true = list(np.array(testSamples)[uTrueIndex][:, 1])
trueList.append(true)
pre = self.recommend(u)
recommendList.append(pre)
e = Eval()
result = e.evalAll(recommendList, trueList)
print 'LFM result:' + '(' + str(self.get_params()) + ')' + str(
(result)['F1'])
return (result)['F1']