def build_data_loader(self):
# ToDo: Please define the directory to store the adjacent matrix
self.sample_generator = DataLoaderBase(ratings=self.data.train)
self.config["model"]["num_batch"] = (
self.data.n_train // self.config["model"]["batch_size"] + 1)
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
class LightGCN_train(TrainEngine):
"""An instance class from the TrainEngine base class."""
def __init__(self, config):
"""Initialize LightGCN_train Class.
Args:
config (dict): All the parameters for the model.
"""
self.config = config
super(LightGCN_train, self).__init__(config)
self.load_dataset()
self.build_data_loader()
self.engine = LightGCNEngine(self.config)
def build_data_loader(self):
"""Missing Doc."""
# ToDo: Please define the directory to store the adjacent matrix
self.sample_generator = DataLoaderBase(ratings=self.data.train)
adj_mat, norm_adj_mat, mean_adj_mat = self.sample_generator.get_adj_mat(
self.config)
norm_adj = sparse_mx_to_torch_sparse_tensor(norm_adj_mat)
self.config["model"]["norm_adj"] = norm_adj
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
def train(self):
"""Train the model."""
self.monitor = Monitor(log_dir=self.config["system"]["run_dir"],
delay=1,
gpu_id=self.gpu_id)
self.model_save_dir = os.path.join(
self.config["system"]["model_save_dir"],
self.config["model"]["save_name"])
self.max_n_update = self.config["model"]["max_n_update"]
for epoch in range(self.config["model"]["max_epoch"]):
print(f"Epoch {epoch} starts !")
print("-" * 80)
if epoch > 0 and self.eval_engine.n_no_update == 0:
# previous epoch have already obtained better result
self.engine.save_checkpoint(model_dir=self.model_save_dir)
if self.eval_engine.n_no_update >= self.max_n_update:
print(
"Early stop criterion triggered, no performance update for {:} times"
.format(self.max_n_update))
break
train_loader = self.sample_generator.pairwise_negative_train_loader(
self.config["model"]["batch_size"],
self.config["model"]["device_str"])
self.engine.train_an_epoch(epoch_id=epoch,
train_loader=train_loader)
self.eval_engine.train_eval(self.data.valid[0], self.data.test[0],
self.engine.model, epoch)
self.config["run_time"] = self.monitor.stop()
def test(self):
"""Test the model."""
self.engine.resume_checkpoint(model_dir=self.model_save_dir)
super(LightGCN_train, self).test()
def build_data_loader(self):
"""Missing Doc."""
# ToDo: Please define the directory to store the adjacent matrix
self.sample_generator = DataLoaderBase(ratings=self.data.train)
adj_mat, norm_adj_mat, mean_adj_mat = self.sample_generator.get_adj_mat(
self.config)
norm_adj = sparse_mx_to_torch_sparse_tensor(norm_adj_mat)
self.config["model"]["norm_adj"] = norm_adj
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
def build_data_loader(self):
"""Missing Doc."""
# ToDo: Please define the directory to store the adjacent matrix
self.gpu_id, self.config["model"]["device_str"] = self.get_device()
self.sample_generator = DataLoaderBase(ratings=self.data.train)
graph_embeddings = self.sample_generator.get_graph_embeddings(
self.config)
self.config["model"]["graph_embeddings"] = graph_embeddings
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
class LCFN_train(TrainEngine):
"""An instance class from the TrainEngine base class."""
def __init__(self, config):
"""Initialize NGCF_train Class.
Args:
config (dict): All the parameters for the model.
"""
self.config = config
print(config)
super(LCFN_train, self).__init__(self.config)
self.load_dataset()
self.build_data_loader()
def build_data_loader(self):
"""Missing Doc."""
# ToDo: Please define the directory to store the adjacent matrix
self.gpu_id, self.config["model"]["device_str"] = self.get_device()
self.sample_generator = DataLoaderBase(ratings=self.data.train)
graph_embeddings = self.sample_generator.get_graph_embeddings(
self.config)
self.config["model"]["graph_embeddings"] = graph_embeddings
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
def train(self):
"""Train the model."""
self.monitor = Monitor(log_dir=self.config["system"]["run_dir"],
delay=1,
gpu_id=self.gpu_id)
self.model_save_dir = os.path.join(
self.config["system"]["model_save_dir"],
self.config["model"]["save_name"])
if self.config["model"]["loss"] == "bpr":
train_loader = self.data.instance_bpr_loader(
batch_size=self.config["model"]["batch_size"],
device=self.config["model"]["device_str"],
)
elif self.config["model"]["loss"] == "bce":
train_loader = self.data.instance_bce_loader(
num_negative=self.config["model"]["num_negative"],
batch_size=self.config["model"]["batch_size"],
device=self.config["model"]["device_str"],
)
else:
raise ValueError(
f"Unsupported loss type {self.config['loss']}, try other options: 'bpr' or 'bce'"
)
self.engine = LCFNEngine(self.config)
self._train(self.engine, train_loader, self.model_save_dir)
self.config["run_time"] = self.monitor.stop()
return self.eval_engine.best_valid_performance
class NCF_train(TrainEngine):
""" An instance class from the TrainEngine base class
"""
def __init__(self, config):
"""Constructor
Args:
config (dict): All the parameters for the model
"""
self.config = config
super(NCF_train, self).__init__(self.config)
self.load_dataset()
self.build_data_loader()
self.gpu_id, self.config["model"]["device_str"] = self.get_device()
def build_data_loader(self):
# ToDo: Please define the directory to store the adjacent matrix
self.sample_generator = DataLoaderBase(ratings=self.data.train)
self.config["model"]["num_batch"] = (
self.data.n_train // self.config["model"]["batch_size"] + 1)
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
def train(self):
""" Main training navigator
Returns:
"""
# Options are: 'mlp', 'gmf', 'ncf_end', and 'ncf_pre';
# Train NeuMF without pre-train
if self.config["model"]["model"] == "ncf_end":
self.train_ncf()
elif self.config["model"]["model"] == "gmf":
self.train_gmf()
elif self.config["model"]["model"] == "mlp":
self.train_mlp()
elif self.config["model"]["model"] == "ncf_pre":
self.train_gmf()
self.train_mlp()
self.train_ncf()
else:
raise ValueError(
"Model type error: Options are: 'mlp', 'gmf', 'ncf_end', and 'ncf_pre'."
)
def train_ncf(self):
""" Train NeuMF
Returns:
None
"""
self.monitor = Monitor(log_dir=self.config["system"]["run_dir"],
delay=1,
gpu_id=self.gpu_id)
train_loader = self.sample_generator.instance_a_train_loader(
self.config["model"]["num_negative"],
self.config["model"]["batch_size"])
self.engine = NeuMFEngine(self.config)
self.neumf_save_dir = os.path.join(
self.config["system"]["model_save_dir"],
self.config["model"]["neumf_config"]["save_name"],
)
self._train(self.engine, train_loader, self.neumf_save_dir)
self.config["run_time"] = self.monitor.stop()
self.eval_engine.test_eval(self.data.test, self.engine.model)
def train_gmf(self):
""" Train GMF
Returns:
None
"""
self.monitor = Monitor(log_dir=self.config["system"]["run_dir"],
delay=1,
gpu_id=self.gpu_id)
train_loader = self.sample_generator.instance_a_train_loader(
self.config["model"]["num_negative"],
self.config["model"]["batch_size"])
# Train GMF
self.engine = GMFEngine(self.config)
self.gmf_save_dir = os.path.join(
self.config["system"]["model_save_dir"],
self.config["model"]["gmf_config"]["save_name"],
)
self._train(self.engine, train_loader, self.gmf_save_dir)
while self.eval_engine.n_worker:
print("Wait 15s for the complete of eval_engine.n_worker")
time.sleep(15) # wait the
self.config["run_time"] = self.monitor.stop()
self.eval_engine.test_eval(self.data.test, self.engine.model)
def train_mlp(self):
""" Train MLP
Returns:
None
"""
# Train MLP
self.monitor = Monitor(log_dir=self.config["system"]["run_dir"],
delay=1,
gpu_id=self.gpu_id)
train_loader = self.sample_generator.instance_a_train_loader(
self.config["model"]["num_negative"],
self.config["model"]["batch_size"])
self.engine = MLPEngine(self.config)
self.mlp_save_dir = os.path.join(
self.config["system"]["model_save_dir"],
self.config["model"]["mlp_config"]["save_name"],
)
self._train(self.engine, train_loader, self.mlp_save_dir)
while self.eval_engine.n_worker:
print("Wait 15s for the complete of eval_engine.n_worker")
time.sleep(15) # wait the
self.config["run_time"] = self.monitor.stop()
self.eval_engine.test_eval(self.data.test, self.engine.model)
def build_data_loader(self):
"""Missing Doc."""
# ToDo: Please define the directory to store the adjacent matrix
self.sample_generator = DataLoaderBase(ratings=self.data.train)
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items