def test_get_batch_kwargs_for_specific_dataasset(empty_data_context,
filesystem_csv):
project_root_dir = empty_data_context.root_directory
context = DataContext(project_root_dir)
base_directory = str(filesystem_csv)
context.add_datasource(
"wow_a_datasource",
module_name="great_expectations.datasource",
class_name="PandasDatasource",
batch_kwargs_generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": base_directory,
}
},
)
batch = get_batch_kwargs(
context,
datasource_name=None,
batch_kwargs_generator_name=None,
data_asset_name="f1",
additional_batch_kwargs={},
)
expected_batch = {
"data_asset_name": "f1",
"datasource": "wow_a_datasource",
"path": os.path.join(filesystem_csv, "f1.csv"),
}
assert batch == expected_batch
def _suite_scaffold(suite: str, directory: str, jupyter: bool) -> None:
usage_event = "cli.suite.scaffold"
suite_name = suite
context = toolkit.load_data_context_with_error_handling(directory)
notebook_filename = f"scaffold_{suite_name}.ipynb"
notebook_path = _get_notebook_path(context, notebook_filename)
if suite_name in context.list_expectation_suite_names():
toolkit.tell_user_suite_exists(suite_name)
if os.path.isfile(notebook_path):
cli_message(
f" - If you wish to adjust your scaffolding, you can open this notebook with jupyter: `{notebook_path}` <red>(Please note that if you run that notebook, you will overwrite your existing suite.)</red>"
)
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
sys.exit(1)
datasource = toolkit.select_datasource(context)
if datasource is None:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
sys.exit(1)
_suite = context.create_expectation_suite(suite_name)
_, _, _, batch_kwargs = get_batch_kwargs(context,
datasource_name=datasource.name)
renderer = SuiteScaffoldNotebookRenderer(context, _suite, batch_kwargs)
renderer.render_to_disk(notebook_path)
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=True,
)
if jupyter:
toolkit.launch_jupyter_notebook(notebook_path)
else:
cli_message(
f"To continue scaffolding this suite, run `jupyter notebook {notebook_path}`"
)
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,
flag_build_docs=True,
open_docs=False,
profiler_configuration="demo",
data_asset_name=None,
):
"""
Create a new expectation suite.
WARNING: the flow and name of this method and its interaction with _profile_to_create_a_suite
require a serious revisiting.
:return: a tuple: (success, suite name, profiling_results)
"""
if generator_asset:
warnings.warn(
"The 'generator_asset' argument will be deprecated and renamed to 'data_asset_name'. "
"Please update code accordingly.",
DeprecationWarning,
)
data_asset_name = generator_asset
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 data_asset_name is None
or batch_kwargs is None
):
(
datasource_name,
batch_kwargs_generator_name,
data_asset_name,
batch_kwargs,
) = get_batch_kwargs(
context,
datasource_name=datasource_name,
batch_kwargs_generator_name=batch_kwargs_generator_name,
data_asset_name=data_asset_name,
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, data_asset_name
)
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, None
profiling_results = _profile_to_create_a_suite(
additional_batch_kwargs,
batch_kwargs,
batch_kwargs_generator_name,
context,
datasource_name,
expectation_suite_name,
data_asset_name,
profiler_configuration,
)
if flag_build_docs:
build_docs(context, view=False)
if open_docs:
attempt_to_open_validation_results_in_data_docs(context, profiling_results)
return True, expectation_suite_name, profiling_results
def validation_operator_run(name, run_name, 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(f"Failed to process <red>{err.message}</red>")
sys.exit(1)
try:
if validation_config_file is not None:
try:
with open(validation_config_file) as f:
validation_config = json.load(f)
except (OSError, json_parse_exception) as e:
cli_message(
f"Failed to process the --validation_config_file argument: <red>{e}</red>"
)
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
success=False,
)
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 {:s} is misconfigured: {:s}</red>".format(
validation_config_file, validation_config_error_message
)
)
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
success=False,
)
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.
"""
)
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
success=False,
)
sys.exit(0)
suite = toolkit.load_expectation_suite(
context, suite, "cli.validation_operator.run"
)
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.
"""
)
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
success=False,
)
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.
"""
)
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
success=False,
)
sys.exit(1)
batch_kwargs = None
cli_message(
"""
Let us help you specify the batch of data your want the validation operator to validate."""
)
try:
data_source = toolkit.select_datasource(context)
except ValueError as ve:
cli_message(f"<red>{ve}</red>")
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
success=False,
)
sys.exit(1)
if not data_source:
cli_message("<red>No datasources found in the context.</red>")
toolkit.send_usage_message(
data_context=context,
event="cli.validation_operator.run",
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,
batch_kwargs_generator_name=None,
data_asset_name=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_name is None:
run_name = datetime.datetime.now(datetime.timezone.utc).strftime(
"%Y%m%dT%H%M%S.%fZ"
)
run_id = RunIdentifier(run_name=run_name)
if suite is None:
results = context.run_validation_operator(
validation_operator_name,
assets_to_validate=batches_to_validate,
run_id=run_id,
)
else:
if suite.evaluation_parameters is None:
results = context.run_validation_operator(
validation_operator_name,
assets_to_validate=batches_to_validate,
run_id=run_id,
)
else:
results = context.run_validation_operator(
validation_operator_name,
assets_to_validate=batches_to_validate,
run_id=run_id,
evaluation_parameters=suite.evaluation_parameters,
)
except (ge_exceptions.DataContextError, OSError, SQLAlchemyError) as e:
cli_message(f"<red>{e}</red>")
toolkit.send_usage_message(
data_context=context, event="cli.validation_operator.run", success=False
)
sys.exit(1)
if not results["success"]:
cli_message("Validation failed!")
toolkit.send_usage_message(
data_context=context, event="cli.validation_operator.run", success=True
)
sys.exit(1)
else:
cli_message("Validation succeeded!")
toolkit.send_usage_message(
data_context=context, event="cli.validation_operator.run", success=True
)
sys.exit(0)
except Exception as e:
toolkit.send_usage_message(
data_context=context, event="cli.validation_operator.run", success=False
)
raise e
def _suite_edit(
suite,
datasource,
directory,
jupyter,
batch_kwargs,
usage_event,
suppress_usage_message=False,
):
# suppress_usage_message flag is for the situation where _suite_edit is called by _suite_new().
# when called by _suite_new(), the flag will be set to False, otherwise it will default to True
batch_kwargs_json = batch_kwargs
batch_kwargs = None
context = toolkit.load_data_context_with_error_handling(directory)
try:
suite = toolkit.load_expectation_suite(context, suite, usage_event)
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
)
)
if not suppress_usage_message:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=True,
)
sys.exit(1)
except ge_exceptions.DataContextError:
cli_message(
"<red>Please check that your batch_kwargs are able to load a batch.</red>"
)
if not suppress_usage_message:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
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
)
)
if not suppress_usage_message:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
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 = toolkit.select_datasource(
context, datasource_name=datasource
)
except ValueError as ve:
cli_message(f"<red>{ve}</red>")
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
sys.exit(1)
if not data_source:
cli_message("<red>No datasources found in the context.</red>")
if not suppress_usage_message:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
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,
batch_kwargs_generator_name=None,
data_asset_name=None,
additional_batch_kwargs=additional_batch_kwargs,
)
notebook_name = f"edit_{suite.expectation_suite_name}.ipynb"
notebook_path = _get_notebook_path(context, notebook_name)
SuiteEditNotebookRenderer.from_data_context(context).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
)
if not suppress_usage_message:
send_usage_message(
data_context=context,
event=usage_event,
event_payload=payload,
api_version="v2",
success=True,
)
if jupyter:
toolkit.launch_jupyter_notebook(notebook_path)
except Exception as e:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
raise e