def __init__(self, *, swow_archive_path: str = SWOW_ARCHIVE_PATH, **kwds):
_Pipeline.__init__(
self,
extractor=SwowExtractor(swow_archive_path=swow_archive_path),
id="swow",
transformer=SwowTransformer(),
**kwds
)
def __init__(self, **kwds):
_Pipeline.__init__(
self,
extractor=HasPartExtractor(),
id="has_part",
transformer=HasPartTransformer(),
**kwds
)
def __init__(self, **kwds):
_Pipeline.__init__(
self,
extractor=WebChildExtractor(**kwds),
id="web_child",
transformer=WebChildTransformer(),
**kwds
)
def __init__(self, xml_file_path: str = default_eat_file_path, **kwds):
_Pipeline.__init__(
self,
extractor=EatExtractor(xml_file_path=xml_file_path),
id="eat",
transformer=EatTransformer(),
**kwds
)
def __init__(self, loader: str, **kwds):
from mowgli_etl.pipeline.portal_test_data.portal_test_data_extractor import (
PortalTestDataExtractor, )
from mowgli_etl.pipeline.portal_test_data.portal_test_data_loader import (
PortalTestDataLoader, )
from mowgli_etl.pipeline.portal_test_data.portal_test_data_transformer import (
PortalTestDataTransformer, )
_Pipeline.__init__(self,
extractor=PortalTestDataExtractor(),
id=self.ID,
loader=PortalTestDataLoader(),
transformer=PortalTestDataTransformer(),
**kwds)
def __init__(self,
*,
sentic_zip_url=ONTOSENTICNET_ZIP_URL,
owl_filename=ONTOSENTICNET_OWL_FILENAME,
**kwds):
_Pipeline.__init__(
self,
extractor=SENTICExtractor(sentic_zip_url=sentic_zip_url,
owl_filename=owl_filename,
**kwds),
id="sentic",
transformer=SENTICTransformer(),
**kwds,
)
def __init__(self, product_type_classifier: str, **kwds):
# if product_type_classifier == "heuristic":
# product_type_classifier_inst = WdcHeuristicProductTypeClassifier()
# # elif product_type_classifier == "spacy":
# # product_type_classifier_inst = ...
# else:
# raise NotImplementedError(product_type_classifier)
_Pipeline.__init__(
self,
extractor=WdcExtractor(),
id=WDC_DATASOURCE_ID,
transformer=WdcTransformer(
), # product_type_classifier=product_type_classifier_inst),
**kwds)
def __init__(self, bzip: bool = True, **kwargs):
from mowgli_etl.pipeline.mcs_benchmark.mcs_benchmark_extractor import (
McsBenchmarkExtractor, )
from mowgli_etl.pipeline.mcs_benchmark.mcs_benchmark_loader import (
McsBenchmarkLoader, )
from mowgli_etl.pipeline.mcs_benchmark.mcs_benchmark_transformer import (
McsBenchmarkTransformer, )
_Pipeline.__init__(
self,
extractor=McsBenchmarkExtractor(),
id=self.ID,
loader=McsBenchmarkLoader(bzip=bzip),
transformer=McsBenchmarkTransformer(),
)
def __init__(self, **kwds):
_Pipeline.__init__(self,
extractor=AristoExtractor(),
id="aristo",
transformer=AristoTransformer(),
**kwds)
def __init__(self, node_edge_sequence: Tuple[Union[KgNode, KgEdge], ...]):
_Pipeline.__init__(self,
extractor=NopExtractor(),
id=DATASOURCE,
transformer=MockTransformer(node_edge_sequence))
def __init__(self, **kwds):
_Pipeline.__init__(self,
extractor=FoodOnExtractor(),
id="food_on",
transformer=FoodOnTransformer(),
**kwds)
def __init__(self, **kwds):
_Pipeline.__init__(self,
extractor=USFExtractor(**kwds),
id="usf",
transformer=USFTransformer(),
**kwds)