def test_train_regression_model(self):
user_vocab_size = 15
item_vocab_size = 20
embedding_dim = 5
page_size = 3
user_model = SVDPPUserModel(item_attrs=[])
regression_model = RegressionPredictionModel(
config={
'rating': {
'context': 'item',
'vocab_size': item_vocab_size,
'embedding_dim': embedding_dim
}
})
model_builder = RecommenderBuilder(
user_model,
regression_model,
page_size=page_size,
attr2config={
'rating': {
'is_numerical': True,
'level': 'item'
},
'item': {
'vocab_size': item_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'item'
},
'user': {
'vocab_size': user_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'user'
}
},
embedding_attrs=['user'],
target2config={
'rating': {
'weight': 1.0,
'MAE': {
'context': 'item',
},
'RMSE': {
'context': 'item',
},
}
},
eval_metrics='MAE RMSE',
)
batches = []
batch_size = 4
for i in range(10):
max_seq_len = random.randint(5, 10)
batch = {
'user_idx': [],
'item_idx': [],
'rating_val': [],
'sequence_length_val': []
}
for l in range(batch_size):
batch['user_idx'].append(
[random.randint(1, user_vocab_size - 1)])
batch['sequence_length_val'].append(
[random.randint(2, max_seq_len) * page_size])
batch['item_idx'].append([])
batch['rating_val'].append([])
for j in range(max_seq_len):
for k in range(page_size):
if j < batch['sequence_length_val'][l][0] / page_size:
idx = random.randint(1, item_vocab_size - 1)
act_dice = random.random()
if act_dice < 0.5:
batch['item_idx'][l].append(idx)
batch['rating_val'][l].append(
random.randint(1, 5) * 1.0)
else:
batch['item_idx'][l].append(0)
batch['rating_val'][l].append(0.0)
else:
batch['rating_val'][l].append(0.0)
batch['item_idx'][l].append(0)
batches.append(batch)
train_data = JsonListDataSet(batches)
run_name = 'test_regression_l2_model'
export_dir = self._export_dir + run_name
shutil.rmtree(export_dir, ignore_errors=True)
model_trainer = ModelTrainer(train_data,
builder=model_builder,
max_steps=10,
tensorboard_dir=self._test_path,
export_dir=export_dir)
model_trainer.train(run_name)
def test_train_sequence_sampled_bpr_model(self):
embedding_dim = 10
user_vocab_size = 15
item_vocab_size = 20
rnn_size = 5
page_size = 3
user_model = SequenceUserModel(rnn_size)
bpr_model = SampledBPRModel(config={
'item': {
'vocab_size': item_vocab_size,
'embedding_dim': rnn_size
}
})
model_builder = RecommenderBuilder(
user_model,
bpr_model,
page_size=page_size,
attr2config={
'item': {
'vocab_size': item_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'item'
},
'user': {
'vocab_size': user_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'user'
}
},
target2config={'item': {
'weight': 1.0
}},
)
batches = []
batch_size = 4
for i in range(10):
max_seq_len = random.randint(5, 10)
batch = {'user_idx': [], 'item_idx': [], 'sequence_length_val': []}
for l in range(batch_size):
batch['user_idx'].append(
[random.randint(1, user_vocab_size - 1)])
batch['sequence_length_val'].append(
[random.randint(2, max_seq_len) * page_size])
batch['item_idx'].append([])
for j in range(max_seq_len):
for k in range(page_size):
if j < batch['sequence_length_val'][l][0] / page_size:
batch['item_idx'][l].append(
random.randint(1, item_vocab_size - 1))
else:
batch['item_idx'][l].append(0)
batches.append(batch)
train_data = JsonListDataSet(batches)
run_name = 'test_sequence_sampled_bpr_model'
export_dir = self._export_dir + run_name
shutil.rmtree(export_dir, ignore_errors=True)
model_trainer = ModelTrainer(train_data,
builder=model_builder,
max_steps=10,
tensorboard_dir=self._test_path,
export_dir=export_dir)
model_trainer.train(run_name)
def test_train_ctr_model(self):
user_vocab_size = 15
item_vocab_size = 20
embedding_dim = 5
page_size = 3
user_model = SVDPPUserModel(item_attrs=[])
sigmoid_model = CTRPredictionModel('display',
config={
'item': {
'vocab_size':
item_vocab_size,
'embedding_dim':
embedding_dim,
'user_bias': 'user'
},
'user': {
'vocab_size':
user_vocab_size
}
})
model_builder = RecommenderBuilder(
user_model,
sigmoid_model,
page_size=page_size,
attr2config={
'display': {
'vocab_size': item_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'item'
},
'item': {
'vocab_size': item_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'item'
},
'user': {
'vocab_size': user_vocab_size,
'embedding_dim': embedding_dim,
'is_numerical': False,
'level': 'user'
}
},
embedding_attrs=['user'],
target2config={'item': {
'weight': 1.0
}},
)
batches = []
batch_size = 4
for i in range(10):
max_seq_len = random.randint(5, 10)
batch = {
'user_idx': [],
'item_idx': [],
'display_idx': [],
'sequence_length_val': []
}
for l in range(batch_size):
batch['user_idx'].append(
[random.randint(1, user_vocab_size - 1)])
batch['sequence_length_val'].append(
[random.randint(2, max_seq_len) * page_size])
batch['item_idx'].append([])
batch['display_idx'].append([])
for j in range(max_seq_len):
for k in range(page_size):
if j < batch['sequence_length_val'][l][0] / page_size:
idx = random.randint(1, item_vocab_size - 1)
batch['display_idx'][l].append(idx)
act_dice = random.random()
if act_dice < 0.5:
batch['item_idx'][l].append(idx)
else:
batch['item_idx'][l].append(0)
else:
batch['display_idx'][l].append(0)
batch['item_idx'][l].append(0)
batches.append(batch)
train_data = JsonListDataSet(batches)
run_name = 'test_ctr_sigmoid_model'
export_dir = self._export_dir + run_name
shutil.rmtree(export_dir, ignore_errors=True)
model_trainer = ModelTrainer(train_data,
builder=model_builder,
max_steps=10,
tensorboard_dir=self._test_path,
export_dir=export_dir)
model_trainer.train(run_name)