def __init__(self,
input_config: Union[example_gen_pb2.Input, Dict[Text, Any]],
output_config: Optional[Union[example_gen_pb2.Output,
Dict[Text, Any]]] = None,
custom_config: Optional[Union[example_gen_pb2.CustomConfig,
Dict[Text, Any]]] = None,
output_data_format: Optional[int] = example_gen_pb2.
FORMAT_TF_EXAMPLE,
example_artifacts: Optional[types.Channel] = None,
instance_name: Optional[Text] = None):
"""Construct a QueryBasedExampleGen component.
Args:
input_config: An
[example_gen_pb2.Input](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing input configuration. If any field is provided as a
RuntimeParameter, input_config should be constructed as a dict with
the same field names as Input proto message. _required_
output_config: An
[example_gen_pb2.Output](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing output configuration. If unset, the default splits
will be labeled as 'train' and 'eval' with a distribution ratio of 2:1.
If any field is provided as a RuntimeParameter, output_config should
be constructed as a dict with the same field names as Output proto
message.
custom_config: An
[example_gen_pb2.CustomConfig](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing custom configuration for ExampleGen. If any field
is provided as a RuntimeParameter, output_config should be constructed
as a dict.
output_data_format: Payload format of generated data in output artifact,
one of example_gen_pb2.PayloadFormat enum.
example_artifacts: Channel of `standard_artifacts.Examples` for output
train and eval examples.
instance_name: Optional unique instance name. Required only if multiple
ExampleGen components are declared in the same pipeline.
Raises:
ValueError: The output_data_format value must be defined in the
example_gen_pb2.PayloadFormat proto.
"""
# Configure outputs.
output_config = output_config or utils.make_default_output_config(
input_config)
if not example_artifacts:
example_artifacts = types.Channel(type=standard_artifacts.Examples)
if output_data_format not in example_gen_pb2.PayloadFormat.values():
raise ValueError(
'The value of output_data_format must be defined in'
'the example_gen_pb2.PayloadFormat proto.')
spec = QueryBasedExampleGenSpec(input_config=input_config,
output_config=output_config,
output_data_format=output_data_format,
custom_config=custom_config,
examples=example_artifacts)
super(QueryBasedExampleGen, self).__init__(spec=spec,
instance_name=instance_name)
def __init__(self,
input_config: Union[example_gen_pb2.Input, Dict[Text, Any]],
output_config: Optional[Union[example_gen_pb2.Output,
Dict[Text, Any]]] = None,
custom_config: Optional[Union[example_gen_pb2.CustomConfig,
Dict[Text, Any]]] = None,
example_artifacts: Optional[types.Channel] = None,
instance_name: Optional[Text] = None,
enable_cache: Optional[bool] = None):
"""Construct an QueryBasedExampleGen component.
Args:
input_config: An
[example_gen_pb2.Input](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing input configuration. If any field is provided as a
RuntimeParameter, input_config should be constructed as a dict with the
same field names as Input proto message. _required_
output_config: An
[example_gen_pb2.Output](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing output configuration. If unset, the default splits
will be labeled as 'train' and 'eval' with a distribution ratio of 2:1.
If any field is provided as a RuntimeParameter, output_config should be
constructed as a dict with the same field names as Output proto message.
custom_config: An
[example_gen_pb2.CustomConfig](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing custom configuration for ExampleGen. If any field
is provided as a RuntimeParameter, output_config should be
constructed as a dict.
example_artifacts: Channel of `standard_artifacts.Examples` for output
train and eval examples.
instance_name: Optional unique instance name. Required only if multiple
ExampleGen components are declared in the same pipeline.
enable_cache: Optional boolean to indicate if cache is enabled for the
QueryBasedExampleGen component. If not specified, defaults to the value
specified for pipeline's enable_cache parameter.
"""
# Configure outputs.
output_config = output_config or utils.make_default_output_config(
input_config)
if not example_artifacts:
artifact = standard_artifacts.Examples()
artifact.split_names = artifact_utils.encode_split_names(
utils.generate_output_split_names(input_config, output_config))
example_artifacts = channel_utils.as_channel([artifact])
spec = QueryBasedExampleGenSpec(input_config=input_config,
output_config=output_config,
custom_config=custom_config,
examples=example_artifacts)
super(_QueryBasedExampleGen,
self).__init__(spec=spec,
instance_name=instance_name,
enable_cache=enable_cache)
def __init__(self,
input_config: example_gen_pb2.Input,
output_config: Optional[example_gen_pb2.Output] = None,
custom_config: Optional[example_gen_pb2.CustomConfig] = None,
example_artifacts: Optional[types.Channel] = None,
instance_name: Optional[Text] = None):
"""Construct an QueryBasedExampleGen component.
Args:
input_config: An
[example_gen_pb2.Input](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing input configuration. _required_
output_config: An
[example_gen_pb2.Output](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing output configuration. If unset, the default splits
will be labeled as 'train' and 'eval' with a distribution ratio of 2:1.
custom_config: An
[example_gen_pb2.CustomConfig](https://github.com/tensorflow/tfx/blob/master/tfx/proto/example_gen.proto)
instance, providing custom configuration for ExampleGen.
example_artifacts: Channel of 'ExamplesPath' for output train and
eval examples.
instance_name: Optional unique instance name. Required only if multiple
ExampleGen components are declared in the same pipeline.
"""
# Configure outputs.
output_config = output_config or utils.make_default_output_config(
input_config)
example_artifacts = example_artifacts or channel_utils.as_channel([
standard_artifacts.Examples(split=split_name)
for split_name in utils.generate_output_split_names(
input_config, output_config)
])
spec = QueryBasedExampleGenSpec(
input_config=input_config,
output_config=output_config,
custom_config=custom_config,
examples=example_artifacts)
super(_QueryBasedExampleGen, self).__init__(
spec=spec, instance_name=instance_name)
def __init__(self,
input_config: example_gen_pb2.Input,
output_config: Optional[example_gen_pb2.Output] = None,
custom_config: Optional[example_gen_pb2.CustomConfig] = None,
component_name: Optional[Text] = 'ExampleGen',
example_artifacts: Optional[types.Channel] = None,
name: Optional[Text] = None):
"""Construct an QueryBasedExampleGen component.
Args:
input_config: An example_gen_pb2.Input instance, providing input
configuration.
output_config: An example_gen_pb2.Output instance, providing output
configuration. If unset, default splits will be 'train' and 'eval' with
size 2:1.
custom_config: An optional example_gen_pb2.CustomConfig instance,
providing custom configuration for executor.
component_name: Name of the component, should be unique per component
class. Default to 'ExampleGen', can be overwritten by sub-classes.
example_artifacts: Optional channel of 'ExamplesPath' for output train and
eval examples.
name: Unique name for every component class instance.
"""
# Configure outputs.
output_config = output_config or utils.make_default_output_config(
input_config)
example_artifacts = example_artifacts or channel_utils.as_channel([
standard_artifacts.Examples(split=split_name)
for split_name in utils.generate_output_split_names(
input_config, output_config)
])
spec = QueryBasedExampleGenSpec(
input_config=input_config,
output_config=output_config,
custom_config=custom_config,
examples=example_artifacts)
super(_QueryBasedExampleGen, self).__init__(spec=spec, name=name)