def test_sort():
show_news_create_time()
global x
local_news = x.get_all_info()
news = Documents.sort_news_by_time(local_news);
print '____________________________________________________'
for i in news:
print i.get_create_time()#do not new.get here
def test_cbr(target_reader_list = []):
input_target_len = len(target_reader_list)
#use training data to build user vector
testing = Documents('user_click_data.txt',True)
test_news = testing.get_AllNews()
user_read_dict = dict()
target_reader = []
#you can specify the target_reader number here!!!!
target_num = 5
if input_target_len != 0:
target_num = input_target_len
get = 0
while len(target_reader)<(target_num):
utemp = test_news[get].get_userid()
get += 1
if not utemp in target_reader:
target_reader.append(utemp)
if input_target_len != 0:
target_reader = target_reader_list
training = Documents('user_click_data.txt',True)
train_news = training.get_AllNews()
cbr = CBR(train_news)
cbr.build_user_vector(target_reader)
cbr.transform_user_vector()
for i in test_news:
uid = i.get_userid()
nid = i.get_newsid()
if uid in target_reader:
pass
else:
#print uid
target_reader.append(uid)
if uid in user_read_dict:
user_read_dict[uid].append(nid)
else:
user_read_dict[uid] = []
user_read_dict[uid].append(nid)
#if you want to specify the target_readerlist, you can uncomment the folllwing line
#target_reader = target_reader_list
#print target_reader
for i in range(target_num):
recommend = cbr.get_recommendation_list(target_reader[i],test_news)
#print 'recommend: ',recommend
#print 'real: ',user_read_dict[target_reader[i]]
temp = []
for item in recommend:
temp.append(item[0])
count_read = 0
count = 0
for t in user_read_dict[target_reader[i]]:
count_read += 1
if t in temp:
count += 1
print 'reader ',target_reader[i],' read:',len(user_read_dict[target_reader[i]]),' accept: ',count
def recommend(self):
if self.type == 0:
mtrain_path = '/root/git/python/rs_system/rs/rs/CBR/user_click_data.txt'
mtest_path = '/root/git/python/rs_system/rs/rs/CBR/user_click_data.txt'
mtrain_path = self.train_path
mtest_path = self.test_path
if self.user:
start_cbr.test_cbr([self.user], mtrain_path, mtest_path)
else:
start_cbr.test_cbr([], mtrain_path, mtest_path)
if self.type == 1:
results = dict()
news = Documents(self.train_path, is_tfidf=False, type=1)
m = news.get_user_item_matrix()
# item_news_m = news.get_item_user_m() #item_news_m[newsid] represents users who saw newsid
item_news_m = news.get_item_user_m()
test = Documents(self.test_path, is_tfidf=False, type=1)
test_user_item = test.get_user_item_matrix()
recom_items = test.get_items()
if self.user:
users = [self.user]
else:
users = self.get_sample_users(m, 30)
for i_user in users:
if i_user not in test_user_item:
continue
test_user_seen = test_user_item[i_user].keys()
for it in recom_items:
seen_items = m[self.user].keys()
if it in seen_items:
seen_items.remove(it)
rating = 0
user_id = item_news_m[it].keys()
for id in user_id:
count = self.user_sim(m[id].keys(), seen_items)
similarity = count / math.sqrt(
len(m[id].keys()) * len(m[self.user].keys()))
rating += m[id][it] * similarity
results[it] = rating
res = sorted(results.items(), key=lambda k: k[1],
reverse=True)[0:10]
predict_seen = [it[0] for it in res]
# for (key,val) in res:
# print "item %d rating is %f" % (key, val)
acc, hit_items = self.cal_accuracy(test_user_seen,
predict_seen)
print "%d %f " % (i_user, acc), hit_items
if self.type == 2:
news = Documents(self.train_path, is_tfidf=False, type=2)
user_item_m = news.get_user_item_matrix()
item_news_m = news.get_item_user_m(
) #item_news_m[newsid] represents users who saw newsid
test = Documents(self.test_path, is_tfidf=False, type=2)
test_user_item = test.get_user_item_matrix()
recom_items = test.get_items()
if self.user:
users = [self.user]
else:
users = self.get_sample_users(user_item_m, 30)
for i_user in users:
if i_user not in test_user_item:
continue
test_user_seen = test_user_item[i_user].keys()
user_seen = user_item_m[i_user].keys(
) #items that specified user has seen
results = {}
for it in recom_items:
if it in user_seen:
user_seen.remove(it)
rating = 0
for seen in user_seen:
similarity = self.sim(item_news_m[it],
item_news_m[seen])
rating += user_item_m[i_user][seen] * similarity
results[it] = rating
# print "item %d rating is %f" % (it, rating)
res = sorted(results.items(), key=lambda k: k[1],
reverse=True)[0:10]
predict_seen = [it[0] for it in res]
# print "predict user %d will see " %i_user, predict_seen
# for (key,val) in res:
# print "item %d rating is %f" % (key, val)
acc, hit_items = self.cal_accuracy(test_user_seen,
predict_seen)
# print "mark user %d see news in test " %i_user , test_user_seen
# print "prediction accuracy is %f" % acc
# print "hit news are", hit_items
print "%d %f " % (i_user, acc), hit_items
def recommend(self):
if self.type == 0:
mtrain_path = '/root/git/python/rs_system/rs/rs/CBR/user_click_data.txt'
mtest_path = '/root/git/python/rs_system/rs/rs/CBR/user_click_data.txt'
mtrain_path = self.train_path
mtest_path = self.test_path
if self.user:
start_cbr.test_cbr([self.user],mtrain_path,mtest_path)
else:
start_cbr.test_cbr([],mtrain_path,mtest_path)
if self.type == 1:
results=dict()
news = Documents(self.train_path, is_tfidf=False,type=1)
m = news.get_user_item_matrix()
# item_news_m = news.get_item_user_m() #item_news_m[newsid] represents users who saw newsid
item_news_m = news.get_item_user_m()
test = Documents(self.test_path, is_tfidf=False, type=1)
test_user_item = test.get_user_item_matrix()
recom_items = test.get_items()
if self.user:
users = [self.user]
else:
users = self.get_sample_users(m,30)
for i_user in users:
if i_user not in test_user_item:
continue
test_user_seen = test_user_item[i_user].keys()
for it in recom_items:
seen_items = m[self.user].keys()
if it in seen_items:
seen_items.remove(it)
rating=0
user_id=item_news_m[it].keys()
for id in user_id:
count=self.user_sim(m[id].keys(),seen_items)
similarity=count/math.sqrt(len(m[id].keys())*len(m[self.user].keys()))
rating+=m[id][it]*similarity
results[it]=rating
res = sorted(results.items(),key = lambda k:k[1],reverse=True)[0:10]
predict_seen = [it[0] for it in res]
# for (key,val) in res:
# print "item %d rating is %f" % (key, val)
acc,hit_items = self.cal_accuracy(test_user_seen,predict_seen)
print "%d %f "% (i_user,acc),hit_items
if self.type == 2:
news = Documents(self.train_path, is_tfidf=False, type=2)
user_item_m = news.get_user_item_matrix()
item_news_m = news.get_item_user_m() #item_news_m[newsid] represents users who saw newsid
test = Documents(self.test_path, is_tfidf=False, type=2)
test_user_item = test.get_user_item_matrix()
recom_items = test.get_items()
if self.user:
users = [self.user]
else:
users = self.get_sample_users(user_item_m,30)
for i_user in users:
if i_user not in test_user_item:
continue
test_user_seen = test_user_item[i_user].keys()
user_seen = user_item_m[i_user].keys() #items that specified user has seen
results = {}
for it in recom_items:
if it in user_seen:
user_seen.remove(it)
rating = 0
for seen in user_seen:
similarity = self.sim(item_news_m[it],item_news_m[seen])
rating += user_item_m[i_user][seen] * similarity
results[it] = rating
# print "item %d rating is %f" % (it, rating)
res = sorted(results.items(),key = lambda k:k[1],reverse=True)[0:10]
predict_seen = [it[0] for it in res]
# print "predict user %d will see " %i_user, predict_seen
# for (key,val) in res:
# print "item %d rating is %f" % (key, val)
acc,hit_items = self.cal_accuracy(test_user_seen,predict_seen)
# print "mark user %d see news in test " %i_user , test_user_seen
# print "prediction accuracy is %f" % acc
# print "hit news are", hit_items
print "%d %f "% (i_user,acc),hit_items
