def __init__(self, config):
"""Init GroceryData Class.
Args:
config:
"""
self.config = config
self.n_users = 0
self.n_items = 0
self.sub_set = 0
self.random_dim = 512
# subset of the dataset. use a small set of users and items if >0, otherwise use full dataset
if "sub_set" in config:
self.sub_set = config["dataset"]["sub_set"]
if "random_dim" in config:
self.random_dim = config["model"]["random_dim"]
# data preprocessing for training and test data
# To be replaced with new data method
train, valid, test = load_split_dataset(config)
self.train = self._intersect_train_test(train, test[0])
self.n_train = len(self.train.index)
self.valid = self._reindex_list(valid)
self.test = self._reindex_list(test)
self.item_sampler = AliasTable(
self.train[DEFAULT_ITEM_COL].value_counts().to_dict())
self.user_sampler = AliasTable(
self.train[DEFAULT_USER_COL].value_counts().to_dict())
if ("item_fea_type" in self.config["dataset"]
or "user_fea_type" in self.config["dataset"]):
self.init_item_fea()
self.init_user_fea()
def load_dataset(self):
"""Load dataset."""
self.data = BaseData(load_split_dataset(self.config))
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items
def load_dataset(self):
"""Load dataset."""
split_data = load_split_dataset(self.config)
self.data = GroceryData(split_dataset=split_data, config=self.config)
self.config["model"]["n_users"] = self.data.n_users
self.config["model"]["n_items"] = self.data.n_items