pipelines/components/gcp/automl/create_dataset_for_tables/component.yaml

description: |
  automl_create_dataset_for_tables creates an empty Dataset for AutoML tables  
implementation:
  container:
    args:
    - --gcp-project-id
    - inputValue: gcp_project_id
    - --gcp-region
    - inputValue: gcp_region
    - --display-name
    - inputValue: display_name
    - if:
        cond:
          isPresent: description
        then:
        - --description
        - inputValue: description
    - if:
        cond:
          isPresent: tables_dataset_metadata
        then:
        - --tables-dataset-metadata
        - inputValue: tables_dataset_metadata
    - if:
        cond:
          isPresent: retry
        then:
        - --retry
        - inputValue: retry
    - if:
        cond:
          isPresent: timeout
        then:
        - --timeout
        - inputValue: timeout
    - if:
        cond:
          isPresent: metadata
        then:
        - --metadata
        - inputValue: metadata
    - '----output-paths'
    - outputPath: dataset_path
    - outputPath: create_time
    - outputPath: dataset_id
    command:
    - python3
    - -u
    - -c
    - |
      from typing import NamedTuple

      def automl_create_dataset_for_tables(
          gcp_project_id: str,
          gcp_region: str,
          display_name: str,
          description: str = None,
          tables_dataset_metadata: dict = {},
          retry=None, #=google.api_core.gapic_v1.method.DEFAULT,
          timeout: float = None, #=google.api_core.gapic_v1.method.DEFAULT,
          metadata: dict = None,
      ) -> NamedTuple('Outputs', [('dataset_path', str), ('create_time', str), ('dataset_id', str)]):
          '''automl_create_dataset_for_tables creates an empty Dataset for AutoML tables
          '''
          import sys
          import subprocess
          subprocess.run([sys.executable, '-m', 'pip', 'install', 'google-cloud-automl==0.4.0', '--quiet', '--no-warn-script-location'], env={'PIP_DISABLE_PIP_VERSION_CHECK': '1'}, check=True)

          import google
          from google.cloud import automl
          client = automl.AutoMlClient()

          location_path = client.location_path(gcp_project_id, gcp_region)
          dataset_dict = {
              'display_name': display_name,
              'description': description,
              'tables_dataset_metadata': tables_dataset_metadata,
          }
          dataset = client.create_dataset(
              location_path,
              dataset_dict,
              retry or google.api_core.gapic_v1.method.DEFAULT,
              timeout or google.api_core.gapic_v1.method.DEFAULT,
              metadata,
          )
          print(dataset)
          dataset_id = dataset.name.rsplit('/', 1)[-1]
          return (dataset.name, dataset.create_time, dataset_id)

      import json
      import argparse
      _missing_arg = object()
      _parser = argparse.ArgumentParser(prog='Automl create dataset for tables', description='automl_create_dataset_for_tables creates an empty Dataset for AutoML tables\n')
      _parser.add_argument("--gcp-project-id", dest="gcp_project_id", type=str, required=True, default=_missing_arg)
      _parser.add_argument("--gcp-region", dest="gcp_region", type=str, required=True, default=_missing_arg)
      _parser.add_argument("--display-name", dest="display_name", type=str, required=True, default=_missing_arg)
      _parser.add_argument("--description", dest="description", type=str, required=False, default=_missing_arg)
      _parser.add_argument("--tables-dataset-metadata", dest="tables_dataset_metadata", type=json.loads, required=False, default=_missing_arg)
      _parser.add_argument("--retry", dest="retry", type=str, required=False, default=_missing_arg)
      _parser.add_argument("--timeout", dest="timeout", type=float, required=False, default=_missing_arg)
      _parser.add_argument("--metadata", dest="metadata", type=json.loads, required=False, default=_missing_arg)
      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=3)
      _parsed_args = {k: v for k, v in vars(_parser.parse_args()).items() if v is not _missing_arg}
      _output_files = _parsed_args.pop("_output_paths", [])

      _outputs = automl_create_dataset_for_tables(**_parsed_args)

      if not hasattr(_outputs, '__getitem__') or isinstance(_outputs, str):
          _outputs = [_outputs]

      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(str(_outputs[idx]))      
    image: python:3.7
inputs:
- name: gcp_project_id
  type: String
- name: gcp_region
  type: String
- name: display_name
  type: String
- name: description
  optional: true
  type: String
- default: '{}'
  name: tables_dataset_metadata
  optional: true
  type: JsonObject
- name: retry
  optional: true
- name: timeout
  optional: true
  type: Float
- name: metadata
  optional: true
  type: JsonObject
name: Automl create dataset for tables
outputs:
- name: dataset_path
  type: String
- name: create_time
  type: String
- name: dataset_id
  type: String