def _ge_validation_fn(context, dataset):
data_context = context.resources.ge_data_context
validator_kwargs = {
"datasource_name": datasource_name,
"data_connector_name": data_connector_name,
"data_asset_name": datasource_name or data_asset_name,
"runtime_parameters": {
runtime_method_type: dataset
},
"batch_identifiers": batch_identifiers,
"expectation_suite_name": suite_name,
**extra_kwargs,
}
validator = data_context.get_validator(**validator_kwargs)
run_id = {
"run_name": datasource_name + " run",
"run_time": datetime.datetime.utcnow(),
}
results = validator.validate(run_id=run_id)
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=True)
rendered_document_content_list = validation_results_page_renderer.render(
validation_results=results)
md_str = "".join(
DefaultMarkdownPageView().render(rendered_document_content_list))
meta_stats = MetadataEntry("Expectation Results",
value=MetadataValue.md(md_str))
yield ExpectationResult(
success=bool(results["success"]),
metadata_entries=[meta_stats],
)
yield Output(results.to_json_dict())
def render_multiple_validation_result_pages_markdown(
validation_operator_result: ValidationOperatorResult,
run_info_at_end: bool = True,
):
"""
Loop through and render multiple validation results to markdown.
Args:
validation_operator_result: (ValidationOperatorResult) Result of validation operator run
run_info_at_end: move run info below expectation results
Returns:
string containing formatted markdown validation results
"""
md_str = ""
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=run_info_at_end)
for validation_result in validation_operator_result.list_validation_results(
):
rendered_document_content = validation_results_page_renderer.render(
validation_result)
md_str += DefaultMarkdownPageView().render(
rendered_document_content) + " "
return md_str
def test_smoke_render_validation_results_page_renderer(titanic_profiler_evrs):
rendered = ValidationResultsPageRenderer().render(titanic_profiler_evrs)
with open(
'./tests/render/output/test_render_validation_results_page_renderer.json',
'w') as outfile:
json.dump(rendered, outfile, indent=2)
assert len(rendered["sections"]) > 5
def test_smoke_render_validation_results_page_renderer(titanic_profiler_evrs):
rendered = ValidationResultsPageRenderer().render(titanic_profiler_evrs)
with open(
file_relative_path(
__file__,
"./output/test_render_validation_results_page_renderer.json"),
"w",
) as outfile:
json.dump(rendered.to_json_dict(), outfile, indent=2)
assert len(rendered.sections) > 5
def test_render_validation_results(titanic_profiled_evrs_1):
rendered_content = ValidationResultsPageRenderer().render(titanic_profiled_evrs_1)
rendered_page = DefaultJinjaPageView().render(rendered_content)
with open(file_relative_path(__file__, './output/test_render_validation_results.html'), 'wb') as f:
f.write(rendered_page.encode("utf-8"))
assert rendered_page[:15] == "<!DOCTYPE html>"
assert rendered_page[-7:] == "</html>"
assert "Table-Level Expectations" in rendered_page
assert 'Must have more than <span class="badge badge-secondary" >0</span> rows.' in rendered_page
def test_render_validation_results(titanic_profiled_evrs_1):
rendered_json = ValidationResultsPageRenderer().render(titanic_profiled_evrs_1)
rendered_page = DefaultJinjaPageView().render(rendered_json)
with open('./tests/render/output/test_render_validation_results.html', 'wb') as f:
f.write(rendered_page.encode("utf-8"))
assert rendered_page[:15] == "<!DOCTYPE html>"
assert rendered_page[-7:] == "</html>"
assert "Table-Level Expectations" in rendered_page
assert 'Must have more than <span class="badge badge-secondary" >0</span> rows.' in rendered_page
assert 'Must have between <span class="badge badge-secondary" >0</span> and <span class="badge badge-secondary" >23</span> columns.' in rendered_page
def test_snapshot_ValidationResultsPageRenderer_render_with_run_info_at_start(
titanic_profiled_evrs_1,
ValidationResultsPageRenderer_render_with_run_info_at_start,
):
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=False)
rendered_validation_results = validation_results_page_renderer.render(
titanic_profiled_evrs_1).to_json_dict()
print(rendered_validation_results)
# with open(file_relative_path(__file__, "./fixtures/ValidationResultsPageRenderer_render_with_run_info_at_start_nc.json"), "w") as f:
# json.dump(rendered_validation_results, f, indent=2)
assert (rendered_validation_results ==
ValidationResultsPageRenderer_render_with_run_info_at_start)
def test_snapshot_ValidationResultsPageRenderer_render_with_run_info_at_end(
titanic_profiled_evrs_1,
ValidationResultsPageRenderer_render_with_run_info_at_end,
):
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=True)
rendered_validation_results = validation_results_page_renderer.render(
titanic_profiled_evrs_1).to_json_dict()
# replace version of vega-lite in res to match snapshot test
content_block = rendered_validation_results["sections"][5][
"content_blocks"][1]["table"][10][2]["content_blocks"][1]
content_block["graph"]["$schema"] = re.sub(
r"v\d*\.\d*\.\d*", "v4.8.1", content_block["graph"]["$schema"])
assert (rendered_validation_results ==
ValidationResultsPageRenderer_render_with_run_info_at_end)
def test_snapshot_ValidationResultsPageRenderer_render_with_run_info_at_end(
titanic_profiled_evrs_1,
ValidationResultsPageRenderer_render_with_run_info_at_end,
):
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=True)
rendered_validation_results = validation_results_page_renderer.render(
titanic_profiled_evrs_1).to_json_dict()
import pprint
pprint.pprint(rendered_validation_results["sections"])
# with open(file_relative_path(__file__, "./fixtures/ValidationResultsPageRenderer_render_with_run_info_at_end_nc.json"), "w") as f:
# json.dump(rendered_validation_results, f, indent=2)
pprint.pprint(ValidationResultsPageRenderer_render_with_run_info_at_end)
assert (rendered_validation_results ==
ValidationResultsPageRenderer_render_with_run_info_at_end)
def _ge_validation_fn(context, dataset):
data_context = context.resources.ge_data_context
if validation_operator_name is not None:
validation_operator = validation_operator_name
else:
data_context.add_validation_operator(
"ephemeral_validation",
{
"class_name": "ActionListValidationOperator",
"action_list": []
},
)
validation_operator = "ephemeral_validation"
suite = data_context.get_expectation_suite(suite_name)
final_batch_kwargs = batch_kwargs or {"dataset": dataset}
if "datasource" in batch_kwargs:
context.log.warning(
"`datasource` field of `batch_kwargs` will be ignored; use the `datasource_name` "
f"parameter of the {decorator_name} factory instead.")
final_batch_kwargs["datasource"] = datasource_name
batch = data_context.get_batch(final_batch_kwargs, suite)
run_id = {
"run_name": datasource_name + " run",
"run_time": datetime.datetime.utcnow(),
}
results = data_context.run_validation_operator(
validation_operator, assets_to_validate=[batch], run_id=run_id)
res = convert_to_json_serializable(
results.list_validation_results())[0]
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=True)
rendered_document_content_list = (
validation_results_page_renderer.render_validation_operator_result(
results))
md_str = " ".join(
DefaultMarkdownPageView().render(rendered_document_content_list))
meta_stats = MetadataEntry("Expectation Results",
value=MetadataValue.md(md_str))
yield ExpectationResult(
success=res["success"],
metadata_entries=[
meta_stats,
],
)
yield Output(res)
def test_snapshot_ValidationResultsPageRenderer_render_with_run_info_at_start(
titanic_profiled_evrs_1,
ValidationResultsPageRenderer_render_with_run_info_at_start,
):
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=False)
rendered_validation_results = validation_results_page_renderer.render(
titanic_profiled_evrs_1).to_json_dict()
# replace version of vega-lite in res to match snapshot test
content_block = rendered_validation_results["sections"][5][
"content_blocks"][1]["table"][10][2]["content_blocks"][1]
content_block["graph"]["$schema"] = re.sub(
r"v\d*\.\d*\.\d*", "v4.8.1", content_block["graph"]["$schema"])
# with open(file_relative_path(__file__, "./fixtures/ValidationResultsPageRenderer_render_with_run_info_at_start_nc.json"), "w") as f:
# json.dump(rendered_validation_results, f, indent=2)
assert (rendered_validation_results ==
ValidationResultsPageRenderer_render_with_run_info_at_start)
def render_multiple_validation_result_pages_markdown(
validation_operator_result: ValidationOperatorResult,
run_info_at_end: bool = True,
) -> str:
"""
Loop through and render multiple validation results to markdown.
Args:
validation_operator_result: (ValidationOperatorResult) Result of validation operator run
run_info_at_end: move run info below expectation results
Returns:
string containing formatted markdown validation results
"""
# deprecated-v0.12.1
warnings.warn(
"This 'render_multiple_validation_result_pages_markdown' function is deprecated as of v0.12.1 and will be removed in v0.16."
"Please use ValidationResultsPageRenderer.render_validation_operator_result() instead."
"E.g. to replicate the functionality of rendering a ValidationOperatorResult to markdown:"
"validation_results_page_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=validation_operator_result"
")"
'return " ".join(DefaultMarkdownPageView().render(rendered_document_content_list))',
DeprecationWarning,
)
validation_results_page_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=validation_operator_result
)
)
return " ".join(DefaultMarkdownPageView().render(rendered_document_content_list))
def validate_csv_using_greatexpectations(
csv_path: InputPath(),
expectation_suite_path: InputPath(),
data_doc_path: OutputPath(),
):
"""Validate a CSV dataset against a Great Expectations suite and create
Data Doc (a validation report). This component fails if validation is not
successful.
Annotations:
authors: Yaroslav Beshta <*****@*****.**>, Anton Kiselev <*****@*****.**>
Args:
csv_path: Path to the CSV file with the dataset.
expectation_suite_path: Path to Great Expectations expectation suite (in JSON format)
"""
import json
import os
import sys
import great_expectations as ge
from great_expectations.render import DefaultJinjaPageView
from great_expectations.render.renderer import ValidationResultsPageRenderer
with open(expectation_suite_path, 'r') as json_file:
expectation_suite = json.load(json_file)
df = ge.read_csv(csv_path, expectation_suite=expectation_suite)
result = df.validate()
document_model = ValidationResultsPageRenderer().render(result)
os.makedirs(os.path.dirname(data_doc_path), exist_ok=True)
with open(data_doc_path, 'w') as writer:
writer.write(DefaultJinjaPageView().render(document_model))
print(f'Saved: {data_doc_path}')
if not result.success:
sys.exit(1)
def test_snapshot_render_section_page_with_fixture_data(
validation_operator_result):
"""
Make sure the appropriate markdown rendering is done for the applied fixture.
Args:
validation_operator_result: test fixture
Returns: None
"""
validation_operator_result = ValidationOperatorResult(
**validation_operator_result)
validation_results_page_renderer = ValidationResultsPageRenderer(
run_info_at_end=True)
rendered_document_content_list = validation_results_page_renderer.render_validation_operator_result(
validation_operator_result=validation_operator_result)
md_str_list = DefaultMarkdownPageView().render(
rendered_document_content_list)
md_str = " ".join(md_str_list)
md_str = md_str.replace(" ", "").replace("\t", "").replace("\n", "")
print(md_str)
assert (md_str == """
# Validation Results
## Overview
### **Expectation Suite:** **basic.warning**
**Data asset:** **None**
**Status:** **Failed**
### Statistics
| | |
| ------------ | ------------ |
Evaluated Expectations | 11
Successful Expectations | 9
Unsuccessful Expectations | 2
Success Percent | ≈81.82%
## Table-Level Expectations
| Status | Expectation | Observed Value |
| ------------ | ------------ | ------------ |
❌ | Must have greater than or equal to **27000** and less than or equal to **33000** rows. | 30
✅ | Must have exactly **3** columns. | 3
✅ | Must have these columns in this order: **Team**, ** "Payroll (millions)"**, ** "Wins"** | ['Team', ' "Payroll (millions)"', ' "Wins"']
## "Payroll (millions)"
| Status | Expectation | Observed Value |
| ------------ | ------------ | ------------ |
✅ | values must never be null. | 100% not null
✅ | minimum value must be greater than or equal to **54.24** and less than or equal to **56.24**. | 55.24
✅ | maximum value must be greater than or equal to **196.96** and less than or equal to **198.96**. | 197.96
✅ | mean must be greater than or equal to **97.01899999999998** and less than or equal to **99.01899999999998**. | ≈98.019
❌ | median must be greater than or equal to **84000.75** and less than or equal to **86000.75**. | 85.75
✅ | quantiles must be within the following value ranges.
| Quantile | Min Value | Max Value |
| ------------ | ------------ | ------------ |
0.05 | 54.37 | 56.37
Q1 | 74.48 | 76.48
Median | 82.31 | 84.31
Q3 | 116.62 | 118.62
0.95 | 173.54 | 175.54
|
| Quantile | Value |
| ------------ | ------------ |
0.05 | 55.37
Q1 | 75.48
Median | 83.31
Q3 | 117.62
0.95 | 174.54
## Team
| Status | Expectation | Observed Value |
| ------------ | ------------ | ------------ |
✅ | values must never be null. | 100% not null
✅ | values must always be greater than or equal to **1** characters long. | 0% unexpected
### Info
| | |
| ------------ | ------------ |
Great Expectations Version | 0.11.8+4.g4ab34df3.dirty
Run Name | getest run
Run Time | 2020-07-27T17:19:32.959193+00:00
### Batch Markers
| | |
| ------------ | ------------ |
**ge_load_time** | **20200727T171932.954810Z**
**pandas_data_fingerprint** | **8c46fdaf0bd356fd58b7bcd9b2e6012d**
### Batch Kwargs
| | |
| ------------ | ------------ |
**PandasInMemoryDF** | **True**
**datasource** | **getest**
**ge_batch_id** | **56615f40-d02d-11ea-b6ea-acde48001122**
-----------------------------------------------------------
Powered by [Great Expectations](https://greatexpectations.io/)
# Validation Results
## Overview
### **Expectation Suite:** **basic.warning**
**Data asset:** **None**
**Status:** **Failed**
### Statistics
| | |
| ------------ | ------------ |
Evaluated Expectations | 11
Successful Expectations | 9
Unsuccessful Expectations | 2
Success Percent | ≈81.82%
## Table-Level Expectations
| Status | Expectation | Observed Value |
| ------------ | ------------ | ------------ |
❌ | Must have greater than or equal to **27000** and less than or equal to **33000** rows. | 30
✅ | Must have exactly **3** columns. | 3
✅ | Must have these columns in this order: **Team**, ** "Payroll (millions)"**, ** "Wins"** | ['Team', ' "Payroll (millions)"', ' "Wins"']
## "Payroll (millions)"
| Status | Expectation | Observed Value |
| ------------ | ------------ | ------------ |
✅ | values must never be null. | 100% not null
✅ | minimum value must be greater than or equal to **54.24** and less than or equal to **56.24**. | 55.24
✅ | maximum value must be greater than or equal to **196.96** and less than or equal to **198.96**. | 197.96
✅ | mean must be greater than or equal to **97.01899999999998** and less than or equal to **99.01899999999998**. | ≈98.019
❌ | median must be greater than or equal to **84000.75** and less than or equal to **86000.75**. | 85.75
✅ | quantiles must be within the following value ranges.
| Quantile | Min Value | Max Value |
| ------------ | ------------ | ------------ |
0.05 | 54.37 | 56.37
Q1 | 74.48 | 76.48
Median | 82.31 | 84.31
Q3 | 116.62 | 118.62
0.95 | 173.54 | 175.54
|
| Quantile | Value |
| ------------ | ------------ |
0.05 | 55.37
Q1 | 75.48
Median | 83.31
Q3 | 117.62
0.95 | 174.54
## Team
| Status | Expectation | Observed Value |
| ------------ | ------------ | ------------ |
✅ | values must never be null. | 100% not null
✅ | values must always be greater than or equal to **1** characters long. | 0% unexpected
### Info
| | |
| ------------ | ------------ |
Great Expectations Version | 0.11.8+4.g4ab34df3.dirty
Run Name | getest run
Run Time | 2020-07-27T17:19:32.959193+00:00
### Batch Markers
| | |
| ------------ | ------------ |
**ge_load_time** | **20200727T171932.954810Z**
**pandas_data_fingerprint** | **8c46fdaf0bd356fd58b7bcd9b2e6012d**
### Batch Kwargs
| | |
| ------------ | ------------ |
**PandasInMemoryDF** | **True**
**datasource** | **getest**
**ge_batch_id** | **56615f40-d02d-11ea-b6ea-acde48001122**
-----------------------------------------------------------
Powered by [Great Expectations](https://greatexpectations.io/)
""".replace(" ", "").replace("\t", "").replace("\n", ""))