def cal_rec(p,cut):
R_true = read_user('cf-test-1-users.dat')
dir_save = 'cdl'+str(p)
U = np.mat(np.loadtxt(dir_save+'/final-U.dat'))
V = np.mat(np.loadtxt(dir_save+'/final-V.dat'))
R = U*V.T
num_u = R.shape[0]
num_hit = 0
fp = open(dir_save+'/rec-list.dat','w')
for i in range(num_u):
if i!=0 and i%100==0:
print 'Iter '+str(i)
l_score = R[i,:].A1.tolist()
pl = sorted(enumerate(l_score),key=lambda d:d[1],reverse=True)
l_rec = list(zip(*pl)[0])[:cut]
s_rec = set(l_rec)
s_true = set(np.where(R_true[i,:]>0)[1].A1)
cnt_hit = len(s_rec.intersection(s_true))
fp.write('%d:' % cnt_hit)
fp.write(' '.join(map(str,l_rec)))
fp.write('\n')
fp.close()
cnt_hit = len(s_rec.intersection(s_true))
fp.write('%d:' % cnt_hit)
fp.write(' '.join(map(str, l_rec)))
fp.write('\n')
fp.close()
if __name__ == '__main__':
# give the same p as given in cdl.py
p = 1
M_low = 50
M_high = 300
cal_rec(p, M_high)
dir_save = 'cdl%d' % p
R_test = read_user('cf-test-1-users.dat')
fp = open('rec-list.dat')
lines = fp.readlines()
total = 0
correct = 0
users = 0
total_items_liked = 0
num_users = len(range(R_test.shape[0]))
# recall@M is calculated for M = 50 to 300
recall_levels = M_high-M_low + 1
recallArray = np.zeros(shape=(num_users,recall_levels))
for user_id in range(num_users):
cnt_hit = len(s_rec.intersection(s_true))
fp.write('%d:' % cnt_hit)
fp.write(' '.join(map(str, l_rec)))
fp.write('\n')
fp.close()
if __name__ == '__main__':
# give the same p as given in cdl.py
p = 1
M_low = 50
M_high = 300
cal_rec(p, M_high)
dir_save = 'cdl%d' % p
R_test = read_user('data/cf-test-1-users.dat')
fp = open(dir_save + '/rec-list.dat')
lines = fp.readlines()
total = 0
correct = 0
users = 0
total_items_liked = 0
num_users = len(range(R_test.shape[0]))
# recall@M is calculated for M = 50 to 300
recall_levels = M_high - M_low + 1
recallArray = np.zeros(shape=(num_users, recall_levels))
for user_id in range(num_users):
lv = 1e-2 # lambda_v/lambda_n in CDL
dir_save = 'cdl%d' % p
if not os.path.isdir(dir_save):
os.system('mkdir %s' % dir_save)
fp = open(dir_save + '/cdl.log', 'w')
print 'p%d: lambda_v/lambda_u/ratio/K: %f/%f/%f/%d' % (p, lambda_v,
lambda_u, lv, K)
fp.write('p%d: lambda_v/lambda_u/ratio/K: %f/%f/%f/%d\n' % \
(p,lambda_v,lambda_u,lv,K))
fp.close()
if is_dummy:
X = data.get_dummy_mult()
R = data.read_dummy_user()
else:
X = data.get_mult()
R = data.read_user()
# set to INFO to see less information during training
logging.basicConfig(level=logging.DEBUG)
#ae_model = AutoEncoderModel(mx.gpu(0), [784,500,500,2000,10], pt_dropout=0.2,
# internal_act='relu', output_act='relu')
ae_model = AutoEncoderModel(mx.cpu(2), [X.shape[1], 100, K],
pt_dropout=0.2,
internal_act='relu',
output_act='relu')
train_X = X
#ae_model.layerwise_pretrain(train_X, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
# lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
#V = np.zeros((train_X.shape[0],10))
V = np.random.rand(train_X.shape[0], K) / 10
s_true = set(np.where(R_true[i, :] > 0)[1])
cnt_hit = len(s_rec.intersection(s_true))
fp.write("%d:" % cnt_hit)
fp.write(" ".join(map(str, l_rec)))
fp.write("\n")
fp.close()
if __name__ == "__main__":
# give the same p as given in cdl.py
p = 4
cal_rec(p, 300)
dir_save = "cdl%d" % p
R_test = read_user("cf-test-1-users.dat")
fp = open(dir_save + "/rec-list.dat")
lines = fp.readlines()
total = 0
correct = 0
users = 0
total_items_liked = 0
num_users = len(range(R_test.shape[0]))
# recall@M is calculated for M = 50 to 300
M_low = 50
M_high = 300
recall_levels = M_high - M_low + 1
recallArray = np.zeros(shape=(num_users, recall_levels))
np.random.seed(1234) # set seed
lv = 1e-2 # lambda_v/lambda_n in CDL
dir_save = 'cdl%d' % p
if not os.path.isdir(dir_save):
os.system('mkdir %s' % dir_save)
fp = open(dir_save+'/cdl.log','w')
print 'p%d: lambda_v/lambda_u/ratio/K: %f/%f/%f/%d' % (p,lambda_v,lambda_u,lv,K)
fp.write('p%d: lambda_v/lambda_u/ratio/K: %f/%f/%f/%d\n' % \
(p,lambda_v,lambda_u,lv,K))
fp.close()
if is_dummy:
X = data.get_dummy_mult()
R = data.read_dummy_user()
else:
X = data.get_mult()
R = data.read_user()
# set to INFO to see less information during training
logging.basicConfig(level=logging.DEBUG)
#ae_model = AutoEncoderModel(mx.gpu(0), [784,500,500,2000,10], pt_dropout=0.2,
# internal_act='relu', output_act='relu')
#mx.cpu() no param needed for cpu.
ae_model = AutoEncoderModel(mx.cpu(), [X.shape[1],100,K],
pt_dropout=0.2, internal_act='relu', output_act='relu')
train_X = X
#ae_model.layerwise_pretrain(train_X, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
# lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
#V = np.zeros((train_X.shape[0],10))
V = np.random.rand(train_X.shape[0],K)/10
import csv
from data import read_user
import numpy as np
p = 2
user_id = 1
# read predicted results
dir_save = 'cdl%d' % p
csvReader = csv.reader(open('raw-data.csv', 'rb'))
d_id_title = dict()
for i, row in enumerate(csvReader):
if i == 0:
continue
d_id_title[i - 1] = row[3]
R_test = read_user('cf-test-1-users.dat')
R_train = read_user('cf-train-1-users.dat')
fp = open(dir_save + '/rec-list.dat')
lines = fp.readlines()
s_test = set(np.where(R_test[user_id, :] > 0)[1].A1)
l_train = np.where(R_train[user_id, :] > 0)[1].A1.tolist()
l_pred = map(int, lines[user_id].strip().split(':')[1].split(' '))
print '##### Articles in the Training Sets #####'
for i in l_train:
print d_id_title[i]
print '\n##### Articles Recommended (Correct Ones Marked by Stars) #####'
for i in l_pred:
if i in s_test:
print '* ' + d_id_title[i]
else:
print d_id_title[i]
fp.close()
import csv
from data import read_user
import numpy as np
p = 2
user_id = 1
# read predicted results
dir_save = 'cdl%d' % p
csvReader = csv.reader(open('raw-data.csv','rb'))
d_id_title = dict()
for i,row in enumerate(csvReader):
if i==0:
continue
d_id_title[i-1] = row[3]
R_test = read_user('cf-test-1-users.dat')
R_train = read_user('cf-train-1-users.dat')
fp = open(dir_save+'/rec-list.dat')
lines = fp.readlines()
s_test = set(np.where(R_test[user_id,:]>0)[1].A1)
l_train = np.where(R_train[user_id,:]>0)[1].A1.tolist()
l_pred = map(int,lines[user_id].strip().split(':')[1].split(' '))
print '##### Articles in the Training Sets #####'
for i in l_train:
print d_id_title[i]
print '\n##### Articles Recommended (Correct Ones Marked by Stars) #####'
for i in l_pred:
if i in s_test:
print '* '+d_id_title[i]
else:
print d_id_title[i]
fp.close()
cnt_hit = len(s_rec.intersection(s_true))
fp.write('%d:' % cnt_hit)
fp.write(' '.join(map(str, l_rec)))
fp.write('\n')
fp.close()
if __name__ == '__main__':
# give the same p as given in cdl.py
p = 1
M_low = 50
M_high = 300
cal_rec(p, M_high)
dir_save = 'cdl%d' % p
R_test = read_user('data/test_P1_3.dat')
fp = open(dir_save + '/rec-list.dat')
lines = fp.readlines()
total = 0
correct = 0
users = 0
total_items_liked = 0
num_users = len(range(R_test.shape[0]))
# recall@M is calculated for M = 50 to 300
recall_levels = M_high - M_low + 1
recallArray = np.zeros(shape=(num_users, recall_levels))
for user_id in range(num_users):
def main():
logging.info('reading data')
item_mat = data.get_mult()
trainM = sparse.csr_matrix(
data.read_user(f_in='data/dummy/cf-train-10-users.dat',
num_u=50,
num_v=1929))
testM = sparse.csr_matrix(
data.read_user(f_in='data/dummy/cf-test-10-users.dat',
num_u=50,
num_v=1929))
trainList = list()
testList = list()
for user in range(trainM.shape[0]):
negative = 0
for item in range(trainM.shape[1]):
if trainM[user, item] == 1:
trainList.append([user, item, 1])
else:
if negative < 20:
trainList.append([user, item, 0])
negative += 1
train = np.array(trainList).astype('float32')
testList = list()
for user in range(testM.shape[0]):
negative = 0
for item in range(testM.shape[1]):
if testM[user, item] == 1:
testList.append([user, item, 1])
# else:
# if negative < 10:
# testList.append( [user, item, 0] )
# negative+=1
test = np.array(testList).astype('float32')
num_item_feat = item_mat.shape[1]
model = CollaborativeDeepLearning(item_mat, [num_item_feat, 50, 10])
model.pretrain(lamda_w=0.001, encoder_noise=0.3, epochs=10)
model_history = model.fineture(train,
test,
lamda_u=0.01,
lamda_v=0.1,
lamda_n=0.1,
lr=0.01,
epochs=500)
testing_rmse = model.getRMSE(test)
print('Testing RMSE = {}'.format(testing_rmse))
import metrics
print('AUC %s' % metrics.full_auc(model.cdl_model, testM))
import matplotlib.pyplot as plt
M_low = 50
M_high = 300
recall_levels = M_high - M_low + 1
recallArray = np.zeros(6)
x = 0
for n in [50, 100, 150, 200, 250, 300]:
test_recall = metrics.recall_at_k(model.cdl_model, testM, k=n)
recallArray[x] = test_recall
print('Recall: %.2f.' % (test_recall))
x += 1
plt.plot([50, 100, 150, 200, 250, 300], recallArray)
plt.ylabel("Recall")
plt.xlabel("M")
plt.title("Proposed: Recall@M")
plt.show()
