name: StatisticsGen
description: |-
  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.

      Returns:
        statistics: `ExampleStatistics` channel for statistics of each split
          provided in the input examples.
inputs:
- {name: examples, type: Examples}
- name: stats_options
  type:
    JsonObject: {data_type: 'proto:tensorflow_data_validation.StatsOptions'}
  optional: true
- {name: schema, type: Schema, optional: true}
outputs:
- {name: statistics, type: ExampleStatistics}
implementation:
  container:
    image: tensorflow/tfx:0.21.4
    command:
    - python3
    - -u
    - -c
    - |
      def _make_parent_dirs_and_return_path(file_path: str):
          import os
          os.makedirs(os.path.dirname(file_path), exist_ok=True)
          return file_path

      def StatisticsGen(
          examples_path ,
          #examples_path: 'ExamplesUri',

          statistics_path ,
          #statistics_path: 'ExampleStatisticsUri',

          stats_options     = None,

          schema_path  = None,
          #schema_path: 'SchemaUri' = None,
      ):
      #) -> NamedTuple('Outputs', [
      #    ('statistics', 'ExampleStatisticsUri'),
      #]):
          """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.

          Returns:
            statistics: `ExampleStatistics` channel for statistics of each split
              provided in the input examples.
          """
          from tfx.components.statistics_gen.component import StatisticsGen as component_class

          #Generated code
          import json
          import os
          import tensorflow
          from google.protobuf import json_format, message
          from tfx.types import Artifact, channel_utils, artifact_utils

          arguments = locals().copy()

          component_class_args = {}

          for name, execution_parameter in component_class.SPEC_CLASS.PARAMETERS.items():
              argument_value_obj = argument_value = arguments.get(name, None)
              if argument_value is None:
                  continue
              parameter_type = execution_parameter.type
              if isinstance(parameter_type, type) and issubclass(parameter_type, message.Message): # Maybe FIX: execution_parameter.type can also be a tuple
                  argument_value_obj = parameter_type()
                  json_format.Parse(argument_value, argument_value_obj)
              component_class_args[name] = argument_value_obj

          for name, channel_parameter in component_class.SPEC_CLASS.INPUTS.items():
              artifact_path = arguments[name + '_path']
              if artifact_path:
                  artifact = channel_parameter.type()
                  artifact.uri = artifact_path + '/' # ?
                  if channel_parameter.type.PROPERTIES and 'split_names' in channel_parameter.type.PROPERTIES:
                      # Recovering splits
                      subdirs = tensorflow.io.gfile.listdir(artifact_path)
                      artifact.split_names = artifact_utils.encode_split_names(sorted(subdirs))
                  component_class_args[name] = channel_utils.as_channel([artifact])

          component_class_instance = component_class(**component_class_args)

          input_dict = {name: channel.get() for name, channel in component_class_instance.inputs.get_all().items()}
          output_dict = {name: channel.get() for name, channel in component_class_instance.outputs.get_all().items()}
          exec_properties = component_class_instance.exec_properties

          # Generating paths for output artifacts
          for name, artifacts in output_dict.items():
              base_artifact_path = arguments[name + '_path']
              # Are there still cases where output channel has multiple artifacts?
              for idx, artifact in enumerate(artifacts):
                  subdir = str(idx + 1) if idx > 0 else ''
                  artifact.uri = os.path.join(base_artifact_path, subdir)  # Ends with '/'

          print('component instance: ' + str(component_class_instance))

          #executor = component_class.EXECUTOR_SPEC.executor_class() # Same
          executor = component_class_instance.executor_spec.executor_class()
          executor.Do(
              input_dict=input_dict,
              output_dict=output_dict,
              exec_properties=exec_properties,
          )

      import argparse
      _parser = argparse.ArgumentParser(prog='StatisticsGen', description='Construct a StatisticsGen component.\n\n    Args:\n      examples: A Channel of `ExamplesPath` type, likely generated by the\n        [ExampleGen component](https://www.tensorflow.org/tfx/guide/examplegen).\n        This needs to contain two splits labeled `train` and `eval`. _required_\n      schema: A `Schema` channel to use for automatically configuring the value\n        of stats options passed to TFDV.\n\n    Returns:\n      statistics: `ExampleStatistics` channel for statistics of each split\n        provided in the input examples.')
      _parser.add_argument("--examples", dest="examples_path", type=str, required=True, default=argparse.SUPPRESS)
      _parser.add_argument("--stats-options", dest="stats_options", type=str, required=False, default=argparse.SUPPRESS)
      _parser.add_argument("--schema", dest="schema_path", type=str, required=False, default=argparse.SUPPRESS)
      _parser.add_argument("--statistics", dest="statistics_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
      _parsed_args = vars(_parser.parse_args())
      _output_files = _parsed_args.pop("_output_paths", [])

      _outputs = StatisticsGen(**_parsed_args)

      _output_serializers = [

      ]

      import os
      for idx, output_file in enumerate(_output_files):
          try:
              os.makedirs(os.path.dirname(output_file))
          except OSError:
              pass
          with open(output_file, 'w') as f:
              f.write(_output_serializers[idx](_outputs[idx]))
    args:
    - --examples
    - {inputPath: examples}
    - if:
        cond: {isPresent: stats_options}
        then:
        - --stats-options
        - {inputValue: stats_options}
    - if:
        cond: {isPresent: schema}
        then:
        - --schema
        - {inputPath: schema}
    - --statistics
    - {outputPath: statistics}