def __init__(self,
input_data: types.Channel = None,
output_data: types.Channel = None,
name: Optional[Text] = None):
"""Construct a HelloComponent.
Args:
input_data: A Channel of type `standard_artifacts.Examples`. This will
often contain two splits: 'train', and 'eval'.
output_data: A Channel of type `standard_artifacts.Examples`. This will
usually contain the same splits as input_data.
name: Optional unique name. Necessary if multiple Hello components are
declared in the same pipeline.
"""
# output_data will contain a list of Channels for each split of the data,
# by default a 'train' split and an 'eval' split. Since HelloComponent
# passes the input data through to output, the splits in output_data will
# be the same as the splits in input_data, which were generated by the
# upstream component.
if not output_data:
examples_artifact = standard_artifacts.Examples()
examples_artifact.split_names = input_data.get()[0].split_names
output_data = channel_utils.as_channel([examples_artifact])
spec = HelloComponentSpec(input_data=input_data,
output_data=output_data, name=name)
super(HelloComponent, self).__init__(spec=spec)
def __init__(self,
statistics: types.Channel = None,
schema: types.Channel = None,
exclude_splits: Optional[List[Text]] = None,
output: Optional[types.Channel] = None,
stats: Optional[types.Channel] = None,
instance_name: Optional[Text] = None):
"""Construct an ExampleValidator component.
Args:
statistics: A Channel of type `standard_artifacts.ExampleStatistics`. This
should contain at least 'eval' split. Other splits are currently
ignored.
schema: A Channel of type `standard_artifacts.Schema`. _required_
exclude_splits: Names of splits that the example validator should not
validate. Default behavior (when exclude_splits is set to None)
is excluding no splits.
output: Output channel of type `standard_artifacts.ExampleAnomalies`.
stats: Backwards compatibility alias for the 'statistics' argument.
instance_name: Optional name assigned to this specific instance of
ExampleValidator. Required only if multiple ExampleValidator components
are declared in the same pipeline. Either `stats` or `statistics` must
be present in the arguments.
"""
if stats:
logging.warning(
'The "stats" argument to the StatisticsGen component has '
'been renamed to "statistics" and is deprecated. Please update your '
'usage as support for this argument will be removed soon.')
statistics = stats
if exclude_splits is None:
exclude_splits = []
logging.info('Excluding no splits because exclude_splits is not set.')
anomalies = output
if not anomalies:
anomalies_artifact = standard_artifacts.ExampleAnomalies()
statistics_split_names = artifact_utils.decode_split_names(
artifact_utils.get_single_instance(list(
statistics.get())).split_names)
split_names = [
split for split in statistics_split_names
if split not in exclude_splits
]
anomalies_artifact.split_names = artifact_utils.encode_split_names(
split_names)
anomalies = types.Channel(
type=standard_artifacts.ExampleAnomalies,
artifacts=[anomalies_artifact])
spec = ExampleValidatorSpec(
statistics=statistics,
schema=schema,
exclude_splits=json_utils.dumps(exclude_splits),
anomalies=anomalies)
super(ExampleValidator, self).__init__(
spec=spec, instance_name=instance_name)
def __init__(self,
examples: types.Channel = None,
schema: Optional[types.Channel] = None,
stats_options: Optional[tfdv.StatsOptions] = None,
output: Optional[types.Channel] = None,
input_data: Optional[types.Channel] = None,
instance_name: Optional[Text] = None,
enable_cache: Optional[bool] = None):
"""Construct a StatisticsGen component.
Args:
examples: A Channel of `ExamplesPath` type, likely generated by the
[ExampleGen component](https://www.tensorflow.org/tfx/guide/examplegen).
This needs to contain two splits labeled `train` and `eval`. _required_
schema: A `Schema` channel to use for automatically configuring the value
of stats options passed to TFDV.
stats_options: The StatsOptions instance to configure optional TFDV
behavior. When stats_options.schema is set, it will be used instead of
the `schema` channel input. Due to the requirement that stats_options be
serialized, the slicer functions and custom stats generators are dropped
and are therefore not usable.
output: `ExampleStatisticsPath` channel for statistics of each split
provided in the input examples.
input_data: Backwards compatibility alias for the `examples` argument.
instance_name: Optional name assigned to this specific instance of
StatisticsGen. Required only if multiple StatisticsGen components are
declared in the same pipeline.
enable_cache: Optional boolean to indicate if cache is enabled for the
StatisticsGen component. If not specified, defaults to the value
specified for pipeline's enable_cache parameter.
"""
if input_data:
absl.logging.warning(
'The "input_data" argument to the StatisticsGen component has '
'been renamed to "examples" and is deprecated. Please update your '
'usage as support for this argument will be removed soon.')
examples = input_data
if not output:
statistics_artifact = standard_artifacts.ExampleStatistics()
statistics_artifact.split_names = artifact_utils.get_single_instance(
list(examples.get())).split_names
output = types.Channel(type=standard_artifacts.ExampleStatistics,
artifacts=[statistics_artifact])
# TODO(b/150802589): Move jsonable interface to tfx_bsl and use json_utils.
stats_options_json = stats_options.to_json() if stats_options else None
spec = StatisticsGenSpec(examples=examples,
schema=schema,
stats_options_json=stats_options_json,
statistics=output)
super(StatisticsGen, self).__init__(spec=spec,
instance_name=instance_name,
enable_cache=enable_cache)
def __init__(self,
input_examples: types.Channel,
data_view: types.Channel,
output_examples: Optional[types.Channel] = None,
instance_name: Optional[Text] = None):
if not output_examples:
output_artifact = standard_artifacts.Examples()
output_artifact.copy_from(
artifact_utils.get_single_instance(list(input_examples.get())))
output_examples = channel_utils.as_channel([output_artifact])
spec = _DataViewBinderComponentSpec(
input_examples=input_examples,
data_view=data_view,
output_examples=output_examples)
super().__init__(spec=spec, instance_name=instance_name)
