Hi, has anyone experienced similar issues with an empty S3 docs bucket in Section 7? I am able to pass the assignment with a score of 80/100, but would like to know why there were errors in validations. Details on the location and outputs with traceback:
7 - Checkpoints and Computing Validations over the Dataset
Validation error after running this:
checkpoint_result = checkpoint.run()
Cell outputs are as below.
Calculating Metrics: 0%| | 0/25 [00:00<?, ?it/s]
Instantiating class from config without an explicit class_name is dangerous. Consider adding an explicit class_name for None
Error running action with name update_data_docs
Traceback (most recent call last):
File “/home/coder/miniconda/lib/python3.12/site-packages/great_expectations/data_context/util.py”, line 90, in instantiate_class_from_config
class_instance = class_(**config_with_defaults)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: SiteBuilder._init_() missing 1 required positional argument: ‘store_backend’During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File “/home/coder/miniconda/lib/python3.12/site-packages/great_expectations/validation_operators/validation_operators.py”, line 476, in _run_actions
action_result = self.actions[name].run(
^^^^^^^^^^^^^^^^^^^^^^^
File “/home/coder/miniconda/lib/python3.12/site-packages/great_expectations/checkpoint/actions.py”, line 101, in run
return self._run(
^^^^^^^^^^
File “/home/coder/miniconda/lib/python3.12/site-packages/great_expectations/checkpoint/actions.py”, line 1190, in _run
self.data_context.build_data_docs(
File “/home/coder/miniconda/lib/python3.12/site-packages/great_expectations/core/usage_statistics/usage_statistics.py”, line 266, in usage_statistics_wrapped_method
result = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File “/home/coder/miniconda/lib/python3.12/site-packages/great_expectations/data_context/data_context/abstract_data_context.py”, line 5318, in build_data_docs
return self._build_data_docs(
^^^^^^^^^^^^^^^^^^^^^^…
“validations_store_name”: “validations_store”
}, ‘root_directory’: ‘/home/coder/project/gx’, ‘site_name’: ‘local_site’}SiteBuilder._init_() missing 1 required positional argument: ‘store_backend’
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings…
TypeError Traceback (most recent call last)
File ~/miniconda/lib/python3.12/site-packages/great_expectations/data_context/util.py:90, in instantiate_class_from_config(config, runtime_environment, config_defaults)
89 try:
—> 90 class_instance = class_(**config_with_defaults)
91 except TypeError as e:TypeError: SiteBuilder.init() missing 1 required positional argument: ‘store_backend’
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
Cell In[27], line 1
----> 1 checkpoint_result = checkpoint.run()File ~/miniconda/lib/python3.12/site-packages/great_expectations/core/usage_statistics/usage_statistics.py:266, in usage_statistics_enabled_method..usage_statistics_wrapped_method(*args, **kwargs)
263 args_payload = args_payload_fn(*args, **kwargs) or {}
264 nested_update(event_payload, args_payload)
→ 266 result = func(*args, **kwargs)
267 message[“success”] = True
268 except Exception:File ~/miniconda/lib/python3.12/site-packages/great_expectations/checkpoint/checkpoint.py:305, in BaseCheckpoint.run(self, template_name, run_name_template, expectation_suite_name, batch_request, validator, action_list, evaluation_parameters, runtime_configuration, validations, profilers, run_id, run_name, run_time, result_format, expectation_suite_ge_cloud_id)
303 if len(validations) > 0:
304 for idx, validation_dict in enumerate(validations):
→ 305 self._run_validation(
306 substituted_runtime_config=substituted_runtime_config,
307 async_validation_operator_results=async_validation_operator_results,
308 async_executor=async_executor,
309 result_format=result_format,
310 run_id=run_id,
311 idx=idx,
312 validation_dict=validation_dict,
313 )
314 else:
315 self._run_validation(
316 substituted_runtime_config=substituted_runtime_config,
317 async_validation_operator_results=async_validation_operator_results,
(…)
320 run_id=run_id,
321 )File ~/miniconda/lib/python3.12/site-packages/great_expectations/checkpoint/checkpoint.py:531, in BaseCheckpoint._run_validation(self, substituted_runtime_config, async_validation_operator_results, async_executor, result_format, run_id, idx, validation_dict)
527 operator_run_kwargs[“catch_exceptions”] = catch_exceptions_validation
529 validation_id: str | None = substituted_validation_dict.get(“id”)
→ 531 async_validation_operator_result = async_executor.submit(
532 action_list_validation_operator.run,
533 assets_to_validate=[validator],
534 run_id=run_id,
535 evaluation_parameters=substituted_validation_dict.get(
536 “evaluation_parameters”
537 ),
538 result_format=result_format,
539 checkpoint_identifier=checkpoint_identifier,
540 checkpoint_name=self.name,
541 validation_id=validation_id,
542 **operator_run_kwargs,
543 )
544 async_validation_operator_results.append(async_validation_operator_result)
545 except (
546 gx_exceptions.CheckpointError,
547 gx_exceptions.ExecutionEngineError,
548 gx_exceptions.MetricError,
549 ) as e:File ~/miniconda/lib/python3.12/site-packages/great_expectations/core/async_executor.py:106, in AsyncExecutor.submit(self, fn, *args, **kwargs)
102 return AsyncResult(
103 future=self._thread_pool_executor.submit(fn, *args, **kwargs) # type: ignore[union-attr]
104 )
105 else:
→ 106 return AsyncResult(value=fn(*args, **kwargs))File ~/miniconda/lib/python3.12/site-packages/great_expectations/validation_operators/validation_operators.py:413, in ActionListValidationOperator.run(self, assets_to_validate, run_id, evaluation_parameters, run_name, run_time, catch_exceptions, result_format, checkpoint_identifier, checkpoint_name, validation_id)
408 validation_result.meta[“validation_id”] = validation_id
409 validation_result.meta[“checkpoint_id”] = (
410 checkpoint_identifier.id if checkpoint_identifier else None
411 )
→ 413 batch_actions_results = self._run_actions(
414 batch=batch,
415 expectation_suite_identifier=expectation_suite_identifier,
416 expectation_suite=batch._expectation_suite,
417 batch_validation_result=validation_result,
418 run_id=run_id,
419 validation_result_id=validation_result_id,
420 checkpoint_identifier=checkpoint_identifier,
421 )
423 run_result_obj = {
424 “validation_result”: validation_result,
425 “actions_results”: batch_actions_results,
426 }
427 run_results[validation_result_id] = run_result_objFile ~/miniconda/lib/python3.12/site-packages/great_expectations/validation_operators/validation_operators.py:506, in ActionListValidationOperator._run_actions(self, batch, expectation_suite_identifier, expectation_suite, batch_validation_result, run_id, validation_result_id, checkpoint_identifier)
504 except Exception as e:
505 logger.exception(f"Error running action with name {action[‘name’]}")
→ 506 raise e
508 return batch_actions_resultsFile ~/miniconda/lib/python3.12/site-packages/great_expectations/validation_operators/validation_operators.py:476, in ActionListValidationOperator._run_actions(self, batch, expectation_suite_identifier, expectation_suite, batch_validation_result, run_id, validation_result_id, checkpoint_identifier)
470 validation_result_id = ValidationResultIdentifier(
471 expectation_suite_identifier=expectation_suite_identifier,
472 run_id=run_id,
473 batch_identifier=batch_identifier,
474 )
475 try:
→ 476 action_result = self.actions[name].run(
477 validation_result_suite_identifier=validation_result_id,
478 validation_result_suite=batch_validation_result,
479 data_asset=batch,
480 payload=batch_actions_results,
481 expectation_suite_identifier=expectation_suite_identifier,
482 checkpoint_identifier=checkpoint_identifier,
483 )
485 # Transform action_result if it not a dictionary.
486 if isinstance(action_result, GXCloudResourceRef):File ~/miniconda/lib/python3.12/site-packages/great_expectations/checkpoint/actions.py:101, in ValidationAction.run(self, validation_result_suite, validation_result_suite_identifier, data_asset, expectation_suite_identifier, checkpoint_identifier, **kwargs)
73 @public_api
74 def run(
75 self,
(…)
83 **kwargs,
84 ):
85 “”“Public entrypoint GX uses to trigger a ValidationAction.
86
87 When a ValidationAction is configured in a Checkpoint, this method gets called
(…)
99 A Dict describing the result of the Action.
100 “””
→ 101 return self._run(
102 validation_result_suite=validation_result_suite,
103 validation_result_suite_identifier=validation_result_suite_identifier,
104 data_asset=data_asset,
105 expectation_suite_identifier=expectation_suite_identifier,
106 checkpoint_identifier=checkpoint_identifier,
107 **kwargs,
108 )File ~/miniconda/lib/python3.12/site-packages/great_expectations/checkpoint/actions.py:1190, in UpdateDataDocsAction._run(self, validation_result_suite, validation_result_suite_identifier, data_asset, payload, expectation_suite_identifier, checkpoint_identifier)
1184 raise TypeError(
1185 f"validation_result_id must be of type ValidationResultIdentifier or GeCloudIdentifier, not {type(validation_result_suite_identifier)}"
1186 )
1188 # TODO Update for RenderedDataDocs
1189 # build_data_docs will return the index page for the validation results, but we want to return the url for the validation result using the code below
→ 1190 self.data_context.build_data_docs(
1191 site_names=self._site_names,
1192 resource_identifiers=[
1193 validation_result_suite_identifier,
1194 expectation_suite_identifier,
1195 ],
1196 )
1197 #
1198 data_docs_validation_results: dict = {}File ~/miniconda/lib/python3.12/site-packages/great_expectations/core/usage_statistics/usage_statistics.py:266, in usage_statistics_enabled_method..usage_statistics_wrapped_method(*args, **kwargs)
263 args_payload = args_payload_fn(*args, **kwargs) or {}
264 nested_update(event_payload, args_payload)
→ 266 result = func(*args, **kwargs)
267 message[“success”] = True
268 except Exception:File ~/miniconda/lib/python3.12/site-packages/great_expectations/data_context/data_context/abstract_data_context.py:5318, in AbstractDataContext.build_data_docs(self, site_names, resource_identifiers, dry_run, build_index)
5279 @usage_statistics_enabled_method(
5280 event_name=UsageStatsEvents.DATA_CONTEXT_BUILD_DATA_DOCS,
5281 )
(…)
5290 build_index: bool = True,
5291 ) → dict[str, str]:
5292 “”“Build Data Docs for your project.
5293
5294 --Documentation–
(…)
5316 ClassInstantiationError: Site config in your Data Context config is not valid.
5317 “””
→ 5318 return self._build_data_docs(
5319 site_names=site_names,
5320 resource_identifiers=resource_identifiers,
5321 dry_run=dry_run,
5322 build_index=build_index,
5323 )File ~/miniconda/lib/python3.12/site-packages/great_expectations/data_context/data_context/abstract_data_context.py:5349, in AbstractDataContext._build_data_docs(self, site_names, resource_identifiers, dry_run, build_index)
5346 complete_site_config = site_config
5347 module_name = “great_expectations.render.renderer.site_builder”
5348 site_builder: SiteBuilder = (
→ 5349 self._init_site_builder_for_data_docs_site_creation(
5350 site_name=site_name,
5351 site_config=site_config,
5352 )
5353 )
5354 if not site_builder:
5355 raise gx_exceptions.ClassInstantiationError(
5356 module_name=module_name,
5357 package_name=None,
5358 class_name=complete_site_config[“class_name”],
5359 )File ~/miniconda/lib/python3.12/site-packages/great_expectations/data_context/data_context/abstract_data_context.py:5384, in AbstractDataContext._init_site_builder_for_data_docs_site_creation(self, site_name, site_config)
5379 def _init_site_builder_for_data_docs_site_creation(
5380 self,
5381 site_name: str,
5382 site_config: dict,
5383 ) → SiteBuilder:
→ 5384 site_builder: SiteBuilder = instantiate_class_from_config(
5385 config=site_config,
5386 runtime_environment={
5387 “data_context”: self,
5388 “root_directory”: self.root_directory,
5389 “site_name”: site_name,
5390 },
5391 config_defaults={
5392 “class_name”: “SiteBuilder”,
5393 “module_name”: “great_expectations.render.renderer.site_builder”,
5394 },
5395 )
5396 return site_builderFile ~/miniconda/lib/python3.12/site-packages/great_expectations/data_context/util.py:92, in instantiate_class_from_config(config, runtime_environment, config_defaults)
90 class_instance = class_(**config_with_defaults)
91 except TypeError as e:
—> 92 raise TypeError(
93 f"Couldn’t instantiate class: {class_name} with config: \n\t{format_dict_for_error_message(config_with_defaults)}\n \n"
94 + str(e)
95 )
97 return class_instanceTypeError: Couldn’t instantiate class: SiteBuilder with config:
S3_site {‘class_name’: ‘SiteBuilder’, ‘store_backend’: {‘class_name’: ‘TupleS3StoreBackend’, ‘bucket’: ‘de-c2w3a1-359994195626-us-east-1-gx-docs’}, ‘site_index_builder’: {‘class_name’: ‘DefaultSiteIndexBuilder’}}
data_context {
“anonymous_usage_statistics”: {
“explicit_id”: true,
“data_context_id”: “243df769-99f4-460f-8029-9b26d719854f”,
“usage_statistics_url”: “https://stats.greatexpectations.io/great_expectations/v1/usage_statistics”,
“enabled”: true,
“explicit_url”: false
},
“checkpoint_store_name”: “checkpoint_store”,
“config_variables_file_path”: “uncommitted/config_variables.yml”,
“config_version”: 3.0,
“data_docs_sites”: {
“local_site”: {
“S3_site”: {
“class_name”: “SiteBuilder”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-docs”
},
“site_index_builder”: {
“class_name”: “DefaultSiteIndexBuilder”
}
}
}
},
“datasources”: {},
“evaluation_parameter_store_name”: “evaluation_parameter_store”,
“expectations_store_name”: “expectations_store”,
“fluent_datasources”: {},
“include_rendered_content”: {
“globally”: false,
“expectation_validation_result”: false,
“expectation_suite”: false
},
“plugins_directory”: “plugins/”,
“stores”: {
“expectations_store”: {
“class_name”: “ExpectationsStore”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-artifacts”,
“prefix”: “expectations/”
}
},
“validations_store”: {
“class_name”: “ValidationsStore”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-artifacts”,
“prefix”: “validations/”
}
},
“evaluation_parameter_store”: {
“class_name”: “EvaluationParameterStore”
},
“checkpoint_store”: {
“class_name”: “CheckpointStore”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“suppress_store_backend_id”: false,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-artifacts”,
“prefix”: “checkpoints/”
}
},
“profiler_store”: {
“class_name”: “ProfilerStore”,
“store_backend”: {
“class_name”: “TupleFilesystemStoreBackend”,
“suppress_store_backend_id”: true,
“base_directory”: “profilers/”
}
}
},
“validations_store_name”: “validations_store”
}
site_name local_site
runtime_environment {‘data_context’: {
“anonymous_usage_statistics”: {
“explicit_id”: true,
“data_context_id”: “243df769-99f4-460f-8029-9b26d719854f”,
“usage_statistics_url”: “https://stats.greatexpectations.io/great_expectations/v1/usage_statistics”,
“enabled”: true,
“explicit_url”: false
},
“checkpoint_store_name”: “checkpoint_store”,
“config_variables_file_path”: “uncommitted/config_variables.yml”,
“config_version”: 3.0,
“data_docs_sites”: {
“local_site”: {
“S3_site”: {
“class_name”: “SiteBuilder”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-docs”
},
“site_index_builder”: {
“class_name”: “DefaultSiteIndexBuilder”
}
}
}
},
“datasources”: {},
“evaluation_parameter_store_name”: “evaluation_parameter_store”,
“expectations_store_name”: “expectations_store”,
“fluent_datasources”: {},
“include_rendered_content”: {
“globally”: false,
“expectation_validation_result”: false,
“expectation_suite”: false
},
“plugins_directory”: “plugins/”,
“stores”: {
“expectations_store”: {
“class_name”: “ExpectationsStore”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-artifacts”,
“prefix”: “expectations/”
}
},
“validations_store”: {
“class_name”: “ValidationsStore”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-artifacts”,
“prefix”: “validations/”
}
},
“evaluation_parameter_store”: {
“class_name”: “EvaluationParameterStore”
},
“checkpoint_store”: {
“class_name”: “CheckpointStore”,
“store_backend”: {
“class_name”: “TupleS3StoreBackend”,
“suppress_store_backend_id”: false,
“bucket”: “de-c2w3a1-359994195626-us-east-1-gx-artifacts”,
“prefix”: “checkpoints/”
}
},
“profiler_store”: {
“class_name”: “ProfilerStore”,
“store_backend”: {
“class_name”: “TupleFilesystemStoreBackend”,
“suppress_store_backend_id”: true,
“base_directory”: “profilers/”
}
}
},
“validations_store_name”: “validations_store”
}, ‘root_directory’: ‘/home/coder/project/gx’, ‘site_name’: ‘local_site’}SiteBuilder.init() missing 1 required positional argument: ‘store_backend’
All the following cells failed to run correctly as well, including a 404 error on visiting the S3 docs bucket URL.
