def make_plot(df):
"""Make a plot of the star counts and post it as an artifact"""
ax = df.plot.line(title="GitHub Stars")
ax.set(xlabel="Date", ylabel="Stars")
fil = BytesIO()
plt.savefig(fil, format="svg")
fig_body = fil.getvalue().decode("utf-8")
create_markdown(fig_body)
def test_create_markdown(client, running_with_backend):
with context(task_run_id="trid"):
artifact_id = artifacts.create_markdown(markdown="markdown_here")
assert artifact_id == "id"
assert client.create_task_run_artifact.called
assert client.create_task_run_artifact.call_args[1] == {
"data": {"markdown": "markdown_here"},
"kind": "markdown",
"task_run_id": "trid",
}
def make_markdown_artifact_dedent():
mkdown = textwrap.dedent("""
# This is markdown
[apparently](https://prefect.io)
Am I markdown?
-----
#### We'll find out
""")
artifact_id = artifacts.create_markdown(mkdown)
print(artifact_id)
def test_old_create_markdown(client, running_with_backend):
with context(task_run_id="trid"):
with pytest.warns(
UserWarning,
match="has been moved to `prefect.backend.create_markdown_artifact`",
):
artifact_id = artifacts.create_markdown(markdown="markdown_here")
assert artifact_id == "id"
assert client.create_task_run_artifact.called
assert client.create_task_run_artifact.call_args[1] == {
"data": {"markdown": "markdown_here"},
"kind": "markdown",
"task_run_id": "trid",
}
def create_df_artifact(df):
json_df = df.to_json()
create_markdown(f"Transformed Dataframe:\n{json_df}")
def test_create_markdown_not_using_backend(client):
with context(task_run_id="trid"):
artifact_id = artifacts.create_markdown(markdown="markdown_here")
assert artifact_id == None
assert not client.create_task_run_artifact.called
def run(
self,
checkpoint_name: str = None,
context: "ge.DataContext" = None,
assets_to_validate: list = None,
batch_kwargs: dict = None,
expectation_suite_name: str = None,
context_root_dir: str = None,
runtime_environment: Optional[dict] = None,
run_name: str = None,
run_info_at_end: bool = True,
disable_markdown_artifact: bool = False,
validation_operator: str = "action_list_operator",
evaluation_parameters: Optional[dict] = None,
):
"""
Task run method.
Args:
- checkpoint_name (str, optional): the name of the checkpoint; should match the filename of
the checkpoint without .py
- context (DataContext, optional): an in-memory GE DataContext object. e.g.
`ge.data_context.DataContext()` If not provided then `context_root_dir` will be used to
look for one.
- assets_to_validate (list, optional): A list of assets to validate when running the
validation operator.
- batch_kwargs (dict, optional): a dictionary of batch kwargs to be used when validating
assets.
- expectation_suite_name (str, optional): the name of an expectation suite to be used when
validating assets.
- context_root_dir (str, optional): the absolute or relative path to the directory holding
your `great_expectations.yml`
- runtime_environment (dict, optional): a dictionary of great expectation config key-value
pairs to overwrite your config in `great_expectations.yml`
- run_name (str, optional): the name of this Great Expectation validation run; defaults to
the task slug
- run_info_at_end (bool, optional): add run info to the end of the artifact generated by this
task. Defaults to `True`.
- disable_markdown_artifact (bool, optional): toggle the posting of a markdown artifact from
this tasks. Defaults to `False`.
- evaluation_parameters (Optional[dict], optional): the evaluation parameters to use when
running validation. For more information, see
[example](https://docs.prefect.io/api/latest/tasks/great_expectations.html#rungreatexpectationsvalidation)
and
[docs](https://docs.greatexpectations.io/en/latest/reference/core_concepts/evaluation_parameters.html).
- validation_operator (str, optional): configure the actions to be executed after running
validation. Defaults to `action_list_operator`.
Raises:
- 'signals.FAIL' if the validation was not a success
Returns:
- result
('great_expectations.validation_operators.types.validation_operator_result.ValidationOperatorResult'):
The Great Expectations metadata returned from the validation
"""
runtime_environment = runtime_environment or dict()
# Load context if not provided directly
if not context:
context = ge.DataContext(
context_root_dir=context_root_dir,
runtime_environment=runtime_environment,
)
# Check that the parameters are mutually exclusive
if (sum(
bool(x) for x in [
(expectation_suite_name and batch_kwargs),
assets_to_validate,
checkpoint_name,
]) != 1):
raise ValueError(
"Exactly one of expectation_suite_name + batch_kwargs, assets_to_validate, or "
"checkpoint_name is required to run validation.")
# If assets are not provided directly through `assets_to_validate` then they need be loaded
# if a checkpoint_name is supplied, then load suite and batch_kwargs from there
# otherwise get batch from `batch_kwargs` and `expectation_suite_name`
if not assets_to_validate:
assets_to_validate = []
if checkpoint_name:
ge_checkpoint = context.get_checkpoint(checkpoint_name)
for batch in ge_checkpoint["batches"]:
batch_kwargs = batch["batch_kwargs"]
for suite_name in batch["expectation_suite_names"]:
suite = context.get_expectation_suite(suite_name)
batch = context.get_batch(batch_kwargs, suite)
assets_to_validate.append(batch)
validation_operator = ge_checkpoint["validation_operator_name"]
else:
assets_to_validate.append(
context.get_batch(batch_kwargs, expectation_suite_name))
# Run validation operator
results = context.run_validation_operator(
validation_operator,
assets_to_validate=assets_to_validate,
run_id={"run_name": run_name or prefect.context.get("task_slug")},
evaluation_parameters=evaluation_parameters,
)
# Generate artifact markdown
if not disable_markdown_artifact:
run_info_at_end = True
validation_results_page_renderer = (
ge.render.renderer.ValidationResultsPageRenderer(
run_info_at_end=run_info_at_end))
rendered_document_content_list = (
validation_results_page_renderer.
render_validation_operator_result(
validation_operator_result=results))
markdown_artifact = " ".join(
ge.render.view.DefaultMarkdownPageView().render(
rendered_document_content_list))
create_markdown(markdown_artifact)
if results.success is False:
raise signals.FAIL(result=results)
return results
def run(self, readme, ref):
artifact_id = artifacts.create_markdown(readme)
return artifact_id
def run(
self,
checkpoint_name: str = None,
context: "ge.DataContext" = None,
assets_to_validate: list = None,
batch_kwargs: dict = None,
expectation_suite_name: str = None,
get_checkpoint_from_context: bool = False,
context_root_dir: str = None,
runtime_environment: Optional[dict] = None,
run_name: str = None,
run_info_at_end: bool = True,
disable_markdown_artifact: bool = False,
):
"""
Task run method.
Args:
- checkpoint_name (str, optional): the name of the checkpoint; should match the filename of
the checkpoint without .py
- context (DataContext, optional): an in-memory GE DataContext object. e.g.
`ge.data_context.DataContext()` If not provided then `context_root_dir` will be used to
look for one.
- assets_to_validate (list, optional): A list of assets to validate when running the
validation operator. If not provided then `batch_kwargs` and `expectation_suite_name`
will be used if context is provided. Also, if not provided and
`get_checkpoint_from_context` is True then the assets will be loaded from that context.
- batch_kwargs (dict, optional): a dictionary of batch kwargs to be used when validating
assets.
- expectation_suite_name (str, optional): the name of an expectation suite to be used when
validating assets.
- get_checkpoint_from_context (bool, optional): get the checkpoint from context. Defaults to
`False`
- context_root_dir (str, optional): the absolute or relative path to the directory holding
your `great_expectations.yml`
- runtime_environment (dict, optional): a dictionary of great expectation config key-value
pairs to overwrite your config in `great_expectations.yml`
- run_name (str, optional): the name of this Great Expectation validation run; defaults to
the task slug
- run_info_at_end (bool, optional): add run info to the end of the artifact generated by this
task. Defaults to `True`.
- disable_markdown_artifact (bool, optional): toggle the posting of a markdown artifact from
this tasks. Defaults to `False`.
Raises:
- 'signals.VALIDATIONFAIL' if the validation was not a success
Returns:
- result
('great_expectations.validation_operators.types.validation_operator_result.ValidationOperatorResult'):
The Great Expectations metadata returned from the validation
"""
if checkpoint_name is None:
raise ValueError("You must provide the checkpoint name.")
runtime_environment = runtime_environment or dict()
# Load context if not provided directly
if not context:
context = ge.DataContext(
context_root_dir=context_root_dir,
runtime_environment=runtime_environment,
)
# if assets are not provided directly through `assets_to_validate` then they need be loaded
# if the checkpoint is being loaded from the context then load suite and batch from there
# otherwise get batch from `batch_kwargs` and `expectation_suite_name`
if not assets_to_validate:
assets_to_validate = []
if get_checkpoint_from_context:
ge_checkpoint = context.get_checkpoint(checkpoint_name)
for batch in ge_checkpoint["batches"]:
batch_kwargs = batch["batch_kwargs"]
for suite_name in batch["expectation_suite_names"]:
suite = context.get_expectation_suite(suite_name)
batch = context.get_batch(batch_kwargs, suite)
assets_to_validate.append(batch)
else:
assets_to_validate.append(
context.get_batch(batch_kwargs, expectation_suite_name)
)
# Run validation operator
results = context.run_validation_operator(
checkpoint_name or ge_checkpoint["validation_operator_name"],
assets_to_validate=assets_to_validate,
run_id={"run_name": run_name or prefect.context.get("task_slug")},
)
if results.success is False:
raise signals.FAIL(result=results)
# Generate artifact markdown
if not disable_markdown_artifact:
run_info_at_end = True
validation_results_page_renderer = (
ge.render.renderer.ValidationResultsPageRenderer(
run_info_at_end=run_info_at_end
)
)
rendered_document_content_list = (
validation_results_page_renderer.render_validation_operator_result(
validation_operator_result=results
)
)
markdown_artifact = " ".join(
ge.render.view.DefaultMarkdownPageView().render(
rendered_document_content_list
)
)
create_markdown(markdown_artifact)
return results