def __init__(self, data, config, params, *args, **kwargs):
"""
"""
self._random = np.random
self._random_p = random
self._ratings = self._data.train_dict
self._sampler = sp.Sampler(self._data.sp_i_train)
self._iteration = 0
if self._batch_size < 1:
self._batch_size = self._num_users
######################################
self._params_list = [
("_intermediate_dim", "intermediate_dim", "intermediate_dim", 600,
None, None),
("_latent_dim", "latent_dim", "latent_dim", 200, None, None),
("_lambda", "reg_lambda", "reg_lambda", 0.01, None, None),
("_learning_rate", "lr", "lr", 0.001, None, None),
("_dropout_rate", "dropout_pkeep", "dropout_pkeep", 1, None, None),
]
self.autoset_params()
self._dropout_rate = 1. - self._dropout_rate
self._model = DenoisingAutoEncoder(self._num_items,
self._intermediate_dim,
self._latent_dim,
self._learning_rate,
self._dropout_rate, self._lambda)
def __init__(self, data, config, params, *args, **kwargs):
"""
AutoRec: Autoencoders Meet Collaborative Filtering
Link: https://users.cecs.anu.edu.au/~akmenon/papers/autorec/autorec-paper.pdf
Args:
data:
config:
params:
*args:
**kwargs:
"""
self._random = np.random
self._params_list = [
("_lr", "lr", "lr", 0.0001, None, None),
("_hidden_neuron", "hidden_neuron", "hidden_neuron", 500, None,
None),
("_l_w", "l_w", "l_w", 0.001, None, None),
]
self.autoset_params()
if self._batch_size < 1:
self._batch_size = self._data.transactions
self._data.sp_u_train = self._data.sp_i_train.transpose(
) # transpose the Matrix
self._sampler = sp.Sampler(self._data.sp_u_train)
self._ratings = self._data.train_dict
self._sp_i_train = self._data.sp_i_train
self._i_items_set = list(range(self._num_items))
self._model = ItemAutoRecModel(self._data, self._num_users,
self._num_items, self._lr,
self._hidden_neuron, self._l_w)
def __init__(self, data, config, params, *args, **kwargs):
"""
"""
self._ratings = self._data.train_dict
self._sampler = sp.Sampler(self._data.sp_i_train)
if self._batch_size < 1:
self._batch_size = self._num_users
######################################
self._params_list = [
("_intermediate_dim", "intermediate_dim", "intermediate_dim", 600,
int, None),
("_latent_dim", "latent_dim", "latent_dim", 200, int, None),
("_lambda", "reg_lambda", "reg_lambda", 0.01, None, None),
("_learning_rate", "lr", "lr", 0.001, None, None),
("_dropout_rate", "dropout_pkeep", "dropout_pkeep", 1, None, None),
("_seed", "seed", "seed", 42, None, None)
]
self.autoset_params()
np.random.seed(self._seed)
random.seed(self._seed)
self._random = np.random
self._random_p = random
self._dropout_rate = 1. - self._dropout_rate
self._model = VariationalAutoEncoder(self._num_items,
self._intermediate_dim,
self._latent_dim,
self._learning_rate,
self._dropout_rate, self._lambda)
# the total number of gradient updates for annealing
self._total_anneal_steps = 200000
# largest annealing parameter
self._anneal_cap = 0.2
