def _validate_preprocessed_dataset(user_features: FeatureDataset,
item_features: FeatureDataset):
if user_features is not None and any(
user_features.df.duplicated(subset=user_features.ids.name)):
ErrorMapping.throw(DuplicateFeatureDefinitionError())
if item_features is not None and any(
item_features.df.duplicated(subset=item_features.ids.name)):
ErrorMapping.throw(DuplicateFeatureDefinitionError())
def _validate_features_type(dataset: FeatureDataset):
for col in dataset.columns:
if dataset.get_column_type(col) == ColumnTypeName.NAN:
ErrorMapping.throw(
InvalidColumnTypeError(
col_type=dataset.get_column_type(col),
col_name=col,
arg_name=dataset.name))
def _check_features(self, features: FeatureDataset):
"""Check compatibility between recorded features and the given features.
The two feature dataset are compatibility if:
1. The new feature dataset contains all feature names in the old feature dataset
2. The same feature in two dataset is of same type
"""
common_logger.info(f"Check features compatibility with existing feature metas")
for _, feature_meta in self.feature_metas.items():
name = feature_meta.name
if name not in features.features:
ErrorMapping.throw(ColumnNotFoundError(column_id=name, arg_name_missing_column=features.name))
column_type = features.get_column_type(name)
if features.get_column_type(name) != feature_meta.type_:
ErrorMapping.verify_element_type(type_=column_type, expected_type=feature_meta.type_, column_name=name,
arg_name=features.name)
def _validate_preprocessed_dataset(transactions: TransactionDataset, user_features: FeatureDataset,
item_features: FeatureDataset):
if transactions.row_size <= 0:
ErrorMapping.throw(
InvalidDatasetError(dataset1=transactions.name, reason=f"dataset does not have any valid samples"))
if transactions.df.duplicated(
subset=transactions.columns[[TRANSACTIONS_USER_COL, TRANSACTIONS_ITEM_COL]]).any():
ErrorMapping.throw(MoreThanOneRatingError())
if user_features is not None and any(user_features.df.duplicated(subset=user_features.ids.name)):
ErrorMapping.throw(DuplicateFeatureDefinitionError())
if item_features is not None and any(item_features.df.duplicated(subset=item_features.ids.name)):
ErrorMapping.throw(DuplicateFeatureDefinitionError())