def _suite_edit(suite, datasource, directory, jupyter, batch_kwargs, usage_event): batch_kwargs_json = batch_kwargs batch_kwargs = None context = load_data_context_with_error_handling(directory) try: suite = load_expectation_suite(context, suite) citations = suite.get_citations(require_batch_kwargs=True) if batch_kwargs_json: try: batch_kwargs = json.loads(batch_kwargs_json) if datasource: batch_kwargs["datasource"] = datasource _batch = toolkit.load_batch(context, suite, batch_kwargs) except json_parse_exception as je: cli_message( "<red>Please check that your batch_kwargs are valid JSON.\n{}</red>".format( je ) ) send_usage_message( data_context=context, event=usage_event, success=False ) sys.exit(1) except ge_exceptions.DataContextError: cli_message( "<red>Please check that your batch_kwargs are able to load a batch.</red>" ) send_usage_message( data_context=context, event=usage_event, success=False ) sys.exit(1) except ValueError as ve: cli_message( "<red>Please check that your batch_kwargs are able to load a batch.\n{}</red>".format( ve ) ) send_usage_message( data_context=context, event=usage_event, success=False ) sys.exit(1) elif citations: citation = citations[-1] batch_kwargs = citation.get("batch_kwargs") if not batch_kwargs: cli_message( """ A batch of data is required to edit the suite - let's help you to specify it.""" ) additional_batch_kwargs = None try: data_source = select_datasource(context, datasource_name=datasource) except ValueError as ve: cli_message("<red>{}</red>".format(ve)) send_usage_message( data_context=context, event=usage_event, success=False ) sys.exit(1) if not data_source: cli_message("<red>No datasources found in the context.</red>") send_usage_message( data_context=context, event=usage_event, success=False ) sys.exit(1) if batch_kwargs is None: ( datasource_name, batch_kwargs_generator, data_asset, batch_kwargs, ) = get_batch_kwargs(context, datasource_name=data_source.name, additional_batch_kwargs=additional_batch_kwargs) notebook_name = "edit_{}.ipynb".format(suite.expectation_suite_name) notebook_path = _get_notebook_path(context, notebook_name) SuiteEditNotebookRenderer().render_to_disk(suite, notebook_path, batch_kwargs) if not jupyter: cli_message( f"To continue editing this suite, run <green>jupyter notebook {notebook_path}</green>" ) payload = edit_expectation_suite_usage_statistics( data_context=context, expectation_suite_name=suite.expectation_suite_name ) send_usage_message( data_context=context, event=usage_event, event_payload=payload, success=True ) if jupyter: toolkit.launch_jupyter_notebook(notebook_path) except Exception as e: send_usage_message(data_context=context, event=usage_event, success=False) raise e
def _get_datasource(context, datasource): datasource = select_datasource(context, datasource_name=datasource) if not datasource: cli_message("<red>No datasources found in the context.</red>") sys.exit(1) return datasource
def create_expectation_suite( context, datasource_name=None, batch_kwargs_generator_name=None, generator_asset=None, batch_kwargs=None, expectation_suite_name=None, additional_batch_kwargs=None, empty_suite=False, show_intro_message=False, open_docs=False, profiler_configuration="demo", ): """ Create a new expectation suite. :return: a tuple: (success, suite name) """ if show_intro_message and not empty_suite: cli_message( "\n<cyan>========== Create sample Expectations ==========</cyan>\n\n" ) data_source = select_datasource(context, datasource_name=datasource_name) if data_source is None: # select_datasource takes care of displaying an error message, so all is left here is to exit. sys.exit(1) datasource_name = data_source.name if expectation_suite_name in context.list_expectation_suite_names(): tell_user_suite_exists(expectation_suite_name) sys.exit(1) if (batch_kwargs_generator_name is None or generator_asset is None or batch_kwargs is None): ( datasource_name, batch_kwargs_generator_name, generator_asset, batch_kwargs, ) = get_batch_kwargs( context, datasource_name=datasource_name, batch_kwargs_generator_name=batch_kwargs_generator_name, generator_asset=generator_asset, additional_batch_kwargs=additional_batch_kwargs, ) # In this case, we have "consumed" the additional_batch_kwargs additional_batch_kwargs = {} if expectation_suite_name is None: default_expectation_suite_name = _get_default_expectation_suite_name( batch_kwargs, generator_asset) while True: expectation_suite_name = click.prompt( "\nName the new expectation suite", default=default_expectation_suite_name) if expectation_suite_name in context.list_expectation_suite_names( ): tell_user_suite_exists(expectation_suite_name) else: break if empty_suite: create_empty_suite(context, expectation_suite_name, batch_kwargs) return True, expectation_suite_name profiling_results = _profile_to_create_a_suite( additional_batch_kwargs, batch_kwargs, batch_kwargs_generator_name, context, datasource_name, expectation_suite_name, generator_asset, profiler_configuration, ) build_docs(context, view=False) if open_docs: _attempt_to_open_validation_results_in_data_docs( context, profiling_results) return True, expectation_suite_name
def suite_edit(suite, datasource, directory, jupyter, batch_kwargs): """ Generate a Jupyter notebook for editing an existing expectation suite. The SUITE argument is required. This is the name you gave to the suite when you created it. A batch of data is required to edit the suite, which is used as a sample. The edit command will help you specify a batch interactively. Or you can specify them manually by providing --batch-kwargs in valid JSON format. Read more about specifying batches of data in the documentation: https://docs.greatexpectations.io/ """ try: context = DataContext(directory) except ge_exceptions.ConfigNotFoundError as err: cli_message("<red>{}</red>".format(err.message)) return except ge_exceptions.ZeroDotSevenConfigVersionError as err: _offer_to_install_new_template(err, context.root_directory) return suite = _load_suite(context, suite) if batch_kwargs: try: batch_kwargs = json.loads(batch_kwargs) if datasource: batch_kwargs["datasource"] = datasource _batch = context.get_batch(batch_kwargs, suite.expectation_suite_name) assert isinstance(_batch, DataAsset) except json_parse_exception as je: cli_message("<red>Please check that your batch_kwargs are valid JSON.\n{}</red>".format(je)) sys.exit(1) except ge_exceptions.DataContextError: cli_message("<red>Please check that your batch_kwargs are able to load a batch.</red>") sys.exit(1) except ValueError as ve: cli_message("<red>Please check that your batch_kwargs are able to load a batch.\n{}</red>".format(ve)) sys.exit(1) else: cli_message(""" A batch of data is required to edit the suite - let's help you to specify it.""" ) additional_batch_kwargs = None try: data_source = select_datasource(context, datasource_name=datasource) except ValueError as ve: cli_message("<red>{}</red>".format(ve)) sys.exit(1) if not data_source: cli_message("<red>No datasources found in the context.</red>") sys.exit(1) if batch_kwargs is None: datasource_name, batch_kwarg_generator, data_asset, batch_kwargs = get_batch_kwargs( context, datasource_name=data_source.name, generator_name=None, generator_asset=None, additional_batch_kwargs=additional_batch_kwargs ) notebook_name = "{}.ipynb".format(suite.expectation_suite_name) notebook_path = os.path.join(context.root_directory, context.GE_EDIT_NOTEBOOK_DIR, notebook_name) NotebookRenderer().render_to_disk(suite, batch_kwargs, notebook_path) cli_message( "To continue editing this suite, run <green>jupyter notebook {}</green>".format( notebook_path ) ) if jupyter: subprocess.call(["jupyter", "notebook", notebook_path])
def _suite_edit(suite, datasource, directory, jupyter, batch_kwargs): batch_kwargs_json = batch_kwargs batch_kwargs = None try: context = DataContext(directory) except ge_exceptions.ConfigNotFoundError as err: cli_message("<red>{}</red>".format(err.message)) return suite = _load_suite(context, suite) citations = suite.get_citations(sort=True, require_batch_kwargs=True) if batch_kwargs_json: try: batch_kwargs = json.loads(batch_kwargs_json) if datasource: batch_kwargs["datasource"] = datasource _batch = context.get_batch(batch_kwargs, suite.expectation_suite_name) assert isinstance(_batch, DataAsset) except json_parse_exception as je: cli_message( "<red>Please check that your batch_kwargs are valid JSON.\n{}</red>" .format(je)) sys.exit(1) except ge_exceptions.DataContextError: cli_message( "<red>Please check that your batch_kwargs are able to load a batch.</red>" ) sys.exit(1) except ValueError as ve: cli_message( "<red>Please check that your batch_kwargs are able to load a batch.\n{}</red>" .format(ve)) sys.exit(1) elif citations: citation = citations[-1] batch_kwargs = citation.get("batch_kwargs") if not batch_kwargs: cli_message(""" A batch of data is required to edit the suite - let's help you to specify it.""" ) additional_batch_kwargs = None try: data_source = select_datasource(context, datasource_name=datasource) except ValueError as ve: cli_message("<red>{}</red>".format(ve)) sys.exit(1) if not data_source: cli_message("<red>No datasources found in the context.</red>") sys.exit(1) if batch_kwargs is None: ( datasource_name, batch_kwarg_generator, data_asset, batch_kwargs, ) = get_batch_kwargs( context, datasource_name=data_source.name, generator_name=None, generator_asset=None, additional_batch_kwargs=additional_batch_kwargs, ) notebook_name = "{}.ipynb".format(suite.expectation_suite_name) notebook_path = os.path.join(context.root_directory, context.GE_EDIT_NOTEBOOK_DIR, notebook_name) NotebookRenderer().render_to_disk(suite, notebook_path, batch_kwargs) if not jupyter: cli_message("To continue editing this suite, run <green>jupyter " f"notebook {notebook_path}</green>") if jupyter: subprocess.call(["jupyter", "notebook", notebook_path])
def validation_operator_run(name, run_id, validation_config_file, suite, directory): # Note though the long lines here aren't pythonic, they look best if Click does the line wraps. """ Run a validation operator against some data. There are two modes to run this command: 1. Interactive (good for development): Specify the name of the validation operator using the --name argument and the name of the expectation suite using the --suite argument. The cli will help you specify the batch of data that you want to validate interactively. 2. Non-interactive (good for production): Use the `--validation_config_file` argument to specify the path of the validation configuration JSON file. This file can be used to instruct a validation operator to validate multiple batches of data and use multiple expectation suites to validate each batch. Learn how to create a validation config file here: https://great-expectations.readthedocs.io/en/latest/command_line.html#great-expectations-validation-operator-run-validation-config-file-validation-config-file-path This command exits with 0 if the validation operator ran and the "success" attribute in its return object is True. Otherwise, the command exits with 1. To learn more about validation operators, go here: https://great-expectations.readthedocs.io/en/latest/features/validation.html#validation-operators """ try: context = DataContext(directory) except ge_exceptions.ConfigNotFoundError as err: cli_message("Failed to process <red>{}</red>".format(err.message)) sys.exit(1) if validation_config_file is not None: try: with open(validation_config_file) as f: validation_config = json.load(f) except ( IOError, json_parse_exception ) as e: cli_message(f"Failed to process the --validation_config_file argument: <red>{e}</red>") sys.exit(1) validation_config_error_message = _validate_valdiation_config(validation_config) if validation_config_error_message is not None: cli_message("<red>The validation config in {0:s} is misconfigured: {1:s}</red>".format(validation_config_file, validation_config_error_message)) sys.exit(1) else: if suite is None: cli_message( """ Please use --suite argument to specify the name of the expectation suite. Call `great_expectation suite list` command to list the expectation suites in your project. """ ) sys.exit(0) suite = load_expectation_suite(context, suite) if name is None: cli_message( """ Please use --name argument to specify the name of the validation operator. Call `great_expectation validation-operator list` command to list the operators in your project. """ ) sys.exit(1) else: if name not in context.list_validation_operator_names(): cli_message( f""" Could not find a validation operator {name}. Call `great_expectation validation-operator list` command to list the operators in your project. """ ) sys.exit(1) batch_kwargs = None cli_message( """ Let's help you specify the batch of data your want the validation operator to validate.""" ) try: data_source = select_datasource(context) except ValueError as ve: cli_message("<red>{}</red>".format(ve)) sys.exit(1) if not data_source: cli_message("<red>No datasources found in the context.</red>") sys.exit(1) if batch_kwargs is None: ( datasource_name, batch_kwarg_generator, data_asset, batch_kwargs, ) = get_batch_kwargs( context, datasource_name=data_source.name, generator_name=None, generator_asset=None, additional_batch_kwargs=None, ) validation_config = { "validation_operator_name": name, "batches": [ { "batch_kwargs": batch_kwargs, "expectation_suite_names": [suite.expectation_suite_name] } ] } try: validation_operator_name = validation_config["validation_operator_name"] batches_to_validate = [] for entry in validation_config["batches"]: for expectation_suite_name in entry["expectation_suite_names"]: batch = context.get_batch(entry["batch_kwargs"], expectation_suite_name) batches_to_validate.append(batch) if run_id is None: run_id = datetime.utcnow().strftime("%Y%m%dT%H%M%S.%fZ") results = context.run_validation_operator( validation_operator_name, assets_to_validate=[batch], run_id=run_id) except ( ge_exceptions.DataContextError, IOError, SQLAlchemyError, ) as e: cli_message("<red>{}</red>".format(e)) sys.exit(1) if not results["success"]: cli_message("Validation Failed!") sys.exit(1) else: cli_message("Validation Succeeded!") sys.exit(0)