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

109 lines
3.5 KiB
YAML

implementation:
container:
args:
- --dataset-path
- inputValue: dataset_path
- --input-uri
- inputValue: input_uri
- 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
command:
- python3
- -u
- -c
- |
from typing import NamedTuple
def automl_import_data_from_bigquery(
dataset_path,
input_uri: str,
retry=None, #=google.api_core.gapic_v1.method.DEFAULT,
timeout=None, #=google.api_core.gapic_v1.method.DEFAULT,
metadata: dict = None,
) -> NamedTuple('Outputs', [('dataset_path', str)]):
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()
input_config = {
'bigquery_source': {
'input_uri': input_uri,
},
}
response = client.import_data(
dataset_path,
input_config,
retry or google.api_core.gapic_v1.method.DEFAULT,
timeout or google.api_core.gapic_v1.method.DEFAULT,
metadata,
)
result = response.result()
print(result)
metadata = response.metadata
print(metadata)
return (dataset_path)
import json
import argparse
_missing_arg = object()
_parser = argparse.ArgumentParser(prog='Automl import data from bigquery', description='')
_parser.add_argument("--dataset-path", dest="dataset_path", type=str, required=True, default=_missing_arg)
_parser.add_argument("--input-uri", dest="input_uri", type=str, required=True, default=_missing_arg)
_parser.add_argument("--retry", dest="retry", type=str, required=False, default=_missing_arg)
_parser.add_argument("--timeout", dest="timeout", type=str, 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=1)
_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_import_data_from_bigquery(**_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: dataset_path
- name: input_uri
type: String
- name: retry
optional: true
- name: timeout
optional: true
- name: metadata
optional: true
type: JsonObject
name: Automl import data from bigquery
outputs:
- name: dataset_path
type: String