def test(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
batch_size=128,
maxlen=100):
# sample_io
sample_io = SampleIO(train_file,
test_file,
uid_voc,
mid_voc,
cat_voc,
batch_size,
maxlen,
embedding_dim=EMBEDDING_DIM,
light_embedding_dim=LIGHT_EMBEDDING_DIM)
model = Model_DIEN(EMBEDDING_DIM,
HIDDEN_SIZE,
ATTENTION_SIZE,
LIGHT_EMBEDDING_DIM,
LIGHT_HIDDEN_SIZE,
LIGHT_ATTENTION_SIZE,
use_rocket_training=use_rocket_training())
# test
datas = sample_io.next_test()
test_ops = tf_test_model(*model.xdl_embedding(
datas, EMBEDDING_DIM, LIGHT_EMBEDDING_DIM, *sample_io.get_n()))
eval_sess = xdl.TrainSession()
print(
'test_auc: %.4f ----test_loss: %.4f ---- test_accuracy: %.4f ---- test_aux_loss: %.4f'
% eval_model(eval_sess, test_ops))
def test(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
batch_size=128,
maxlen=100):
# sample_io
sample_io = SampleIO(train_file, test_file, uid_voc, mid_voc,
cat_voc, batch_size, maxlen, EMBEDDING_DIM)
if xdl.get_config('model') == 'din':
model = Model_DIN(
EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
elif xdl.get_config('model') == 'dien':
model = Model_DIEN(
EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
else:
raise Exception('only support din and dien model')
# test
datas = sample_io.next_test()
test_ops = tf_test_model(
*model.xdl_embedding(datas, EMBEDDING_DIM, *sample_io.get_n()))
eval_sess = xdl.TrainSession()
print('test_auc: %.4f ----test_loss: %.4f ---- test_accuracy: %.4f ---- test_aux_loss: %.4f' %
eval_model(eval_sess, test_ops))
def test(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
batch_size=128,
maxlen=100):
# sample_io
sample_io = SampleIO(train_file, test_file, uid_voc, mid_voc, cat_voc,
batch_size, maxlen, EMBEDDING_DIM)
if xdl.get_config('model') == 'din':
model = Model_DIN(EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
elif xdl.get_config('model') == 'dien':
model = Model_DIEN(EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
else:
raise Exception('only support din and dien model')
# test
# datas = sample_io.next_test()
# test_ops = tf_test_model(*model.xdl_embedding(datas, EMBEDDING_DIM, *sample_io.get_n()))
# print('='*10,'start test','='*10)
test_ops = model.build_final_net(EMBEDDING_DIM, sample_io, is_train=False)
print('=' * 10 + 'start test' + '=' * 10)
saver = xdl.Saver()
checkpoint_version = "ckpt-...............12000"
saver.restore(version=checkpoint_version)
eval_sess = xdl.TrainSession()
print(
'test_auc: %.4f ----test_loss: %.4f ---- test_accuracy: %.4f ---- test_aux_loss: %.4f'
% eval_model(eval_sess, test_ops))
def test(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
batch_size=128,
maxlen=100):
# sample_io
sample_io = SampleIO(train_file, test_file, uid_voc, mid_voc,
cat_voc, batch_size, maxlen,
embedding_dim=EMBEDDING_DIM,
light_embedding_dim=LIGHT_EMBEDDING_DIM)
model = Model_DIEN(
EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE, LIGHT_EMBEDDING_DIM,
LIGHT_HIDDEN_SIZE, LIGHT_ATTENTION_SIZE, use_rocket_training=use_rocket_training())
# test
datas = sample_io.next_test()
test_ops = tf_test_model(
*model.xdl_embedding(datas, EMBEDDING_DIM, LIGHT_EMBEDDING_DIM, *sample_io.get_n()))
eval_sess = xdl.TrainSession()
print('test_auc: %.4f ----test_loss: %.4f ---- test_accuracy: %.4f ---- test_aux_loss: %.4f' %
eval_model(eval_sess, test_ops))
def train(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
item_info=item_info,
reviews_info=reviews_info,
batch_size=128,
maxlen=100,
test_iter=700):
model = Model_DIEN(EMBEDDING_DIM,
HIDDEN_SIZE,
ATTENTION_SIZE,
LIGHT_EMBEDDING_DIM,
LIGHT_HIDDEN_SIZE,
LIGHT_ATTENTION_SIZE,
use_rocket_training=use_rocket_training())
sample_io = SampleIO(train_file,
test_file,
uid_voc,
mid_voc,
cat_voc,
item_info,
reviews_info,
batch_size,
maxlen,
embedding_dim=EMBEDDING_DIM,
light_embedding_dim=LIGHT_EMBEDDING_DIM)
with xdl.model_scope('train'):
train_ops = model.build_final_net(EMBEDDING_DIM, LIGHT_EMBEDDING_DIM,
sample_io)
lr = 0.001
# Adam Adagrad
train_ops.append(xdl.Adam(lr).optimize())
hooks = []
log_format = "[%(time)s] lstep[%(lstep)s] gstep[%(gstep)s] lqps[%(lqps)s] gqps[%(gqps)s] loss[%(loss)s]"
hooks = [QpsMetricsHook(), MetricsPrinterHook(log_format)]
if xdl.get_task_index() == 0:
hooks.append(
xdl.CheckpointHook(
xdl.get_config('checkpoint', 'save_interval')))
train_sess = xdl.TrainSession(hooks=hooks)
with xdl.model_scope('test'):
test_ops = model.build_final_net(EMBEDDING_DIM,
LIGHT_EMBEDDING_DIM,
sample_io,
is_train=False)
test_sess = xdl.TrainSession()
model.run(train_ops, train_sess, test_ops, test_sess, test_iter=test_iter)
def train(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
item_info=item_info,
reviews_info=reviews_info,
batch_size=128,
maxlen=100,
test_iter=700):
if xdl.get_config('model') == 'din':
model = Model_DIN(EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
elif xdl.get_config('model') == 'dien':
model = Model_DIEN(EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
else:
raise Exception('only support din and dien')
sample_io = SampleIO(train_file, test_file, uid_voc, mid_voc, cat_voc,
item_info, reviews_info, batch_size, maxlen,
EMBEDDING_DIM)
with xdl.model_scope('train'):
train_ops = model.build_final_net(EMBEDDING_DIM, sample_io)
lr = 0.001
# Adam Adagrad
train_ops.append(xdl.Adam(lr).optimize())
hooks = []
log_format = "[%(time)s] lstep[%(lstep)s] gstep[%(gstep)s] lqps[%(lqps)s] gqps[%(gqps)s] loss[%(loss)s]"
hooks = [QpsMetricsHook(), MetricsPrinterHook(log_format)]
if xdl.get_task_index() == 0:
hooks.append(
xdl.CheckpointHook(
xdl.get_config('checkpoint', 'save_interval')))
train_sess = xdl.TrainSession(hooks=hooks)
with xdl.model_scope('test'):
test_ops = model.build_final_net(EMBEDDING_DIM,
sample_io,
is_train=False)
test_sess = xdl.TrainSession()
print('=' * 10 + 'start train' + '=' * 10)
model.run(train_ops, train_sess, test_ops, test_sess, test_iter=test_iter)
def test(train_file=train_file,
test_file=test_file,
uid_voc=uid_voc,
mid_voc=mid_voc,
cat_voc=cat_voc,
item_info=item_info,
reviews_info=reviews_info,
batch_size=99,
maxlen=100):
if xdl.get_config('model') == 'din':
model = Model_DIN(EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
elif xdl.get_config('model') == 'dien':
model = Model_DIEN(EMBEDDING_DIM, HIDDEN_SIZE, ATTENTION_SIZE)
else:
raise Exception('only support din and dien model')
# create item cate dict
i_c = {}
for i in item_c:
ii = i.strip().split('\t')
i_c[ii[0]] = ii[1]
saver = xdl.Saver()
checkpoint_version = "ckpt-...............20000"
saver.restore(version=checkpoint_version)
last_hist = []
target_list = []
seq = []
test_set = pkl.load(open(test_file, 'rb'))
knn_table = pkl.load(
open('../data/ali_knn_table/knn' + str(test_file[-5]) + '_no_pro2.pkl',
'rb'))
print('length before deal with : ', len(test_set))
test_knn = open('../data/test_knn', 'w')
count22 = 0
for i in test_set:
# knn
ss = i.strip().split('\t')
last = ss[4].split('/')[-1]
# append last, target, and seq
last_hist.append(last)
target_list.append(ss[2])
seq.append((ss[1], ss[4])) # uid and hist
knn = knn_table[last]
for k in knn:
count22 += 1
if k in i_c:
tmp = '1\t' + ss[1] + '\t' + k + '\t' + i_c[k] + '\t' + ss[
4] + '\t' + ss[5]
else:
tmp = '1\t' + ss[1] + '\t' + k + '\t' + 'UNK' + '\t' + ss[
4] + '\t' + ss[5]
print >> test_knn, tmp
test_knn.close()
print('after last_hist :', len(last_hist))
print('all test_knn length :', count22)
# sample_io
test_knn_f = os.path.join(get_data_prefix(), 'test_knn')
sample_io = SampleIO(train_file, test_knn_f, uid_voc, mid_voc, cat_voc,
item_info, reviews_info, batch_size, maxlen,
EMBEDDING_DIM)
print('all length:', len(last_hist))
test_ops = model.build_final_net(EMBEDDING_DIM, sample_io, is_train=False)
print('=' * 10 + 'start test' + '=' * 10)
eval_sess = xdl.TrainSession()
pro_all, test_auc, loss_sum, accuracy_sum, aux_loss_sum = eval_model(
eval_sess, test_ops)
print(
'test_auc: %.4f ----test_loss: %.4f ---- test_accuracy: %.4f ---- test_aux_loss: %.4f'
% (test_auc, loss_sum, accuracy_sum, aux_loss_sum))
print('after pro length :', len(pro_all))
print('=' * 50)
# sort the knn with prob
rank_all_knn = {}
rank = []
for i in range(len(last_hist)):
knn = knn_table[last_hist[i]]
pro = pro_all[i]
c = list(zip(knn, pro))
c = sorted(c, key=lambda t: t[1], reverse=True)
rank_all = [sss[0] for sss in c]
rank_all_knn[seq[i][0]] = rank_all
if target_list[i] in rank_all:
rank.append(rank_all.index(target_list[i]) + 1)
else:
rank.append(100)
# print(rank_all_knn)
# save the result of re-rank
user = [i[0] for i in seq]
hist = [i[1] for i in seq]
assert len(last_hist) == len(user)
results = list(zip(user, hist, last_hist, target_list, rank))
# results = pd.DataFrame(results, columns = ['last','target','rank'])
# esults.to_csv('ali_dien_rank.csv',index=False)
with open('ali_dien_rank_4days' + test_file[-11:], 'wb') as d:
pkl.dump(results, d)