[MAINTENANCE] Remove DataContext from DataAssistant (#4931)

great_expectations/core/batch.py

@@ -628,9 +628,10 @@ def head(self, n_rows=5, fetch_all=False):
         return self._data.execution_engine.resolve_metrics((metric,))[metric.id]
 
 
+# TODO: <Alex>ALEX -- Make this helper utility of general use.</Alex>
 def materialize_batch_request(
     batch_request: Optional[Union[BatchRequestBase, dict]] = None,
-) -> Optional[Union[BatchRequest, RuntimeBatchRequest]]:
+) -> Optional[BatchRequestBase]:
     effective_batch_request: dict = get_batch_request_as_dict(
         batch_request=batch_request
     )

great_expectations/rule_based_profiler/data_assistant/data_assistant.py

@@ -3,7 +3,6 @@
 
 from great_expectations.core import ExpectationSuite
 from great_expectations.core.batch import Batch, BatchRequestBase
-from great_expectations.data_context import BaseDataContext
 from great_expectations.execution_engine.execution_engine import MetricDomainTypes
 from great_expectations.rule_based_profiler.domain_builder import DomainBuilder
 from great_expectations.rule_based_profiler.expectation_configuration_builder import (
@@ -15,9 +14,6 @@
 from great_expectations.rule_based_profiler.helpers.util import (
     convert_variables_to_dict,
 )
-from great_expectations.rule_based_profiler.helpers.util import (
-    get_validator as get_validator_using_batch_list_or_batch_request,
-)
 from great_expectations.rule_based_profiler.parameter_builder import ParameterBuilder
 from great_expectations.rule_based_profiler.rule import Rule
 from great_expectations.rule_based_profiler.rule_based_profiler import (
@@ -29,6 +25,7 @@
     DataAssistantResult,
 )
 from great_expectations.util import measure_execution_time
+from great_expectations.validator.validator import Validator
 
 
 class DataAssistant(ABC):
@@ -40,8 +37,7 @@ class DataAssistant(ABC):
 
     data_assistant: DataAssistant = VolumeDataAssistant(
         name="my_volume_data_assistant",
-        batch_request=batch_request,
-        data_context=context,
+        validator=validator,
     )
     result: DataAssistantResult = data_assistant.run()
 
@@ -56,8 +52,7 @@ class DataAssistant(ABC):
     def __init__(
         self,
         name: str,
-        batch_request: Union[BatchRequestBase, dict],
-        data_context: BaseDataContext = None,
+        validator: Validator,
     ):
         """
         DataAssistant subclasses guide "RuleBasedProfiler" to contain Rule configurations to embody profiling behaviors,
@@ -66,29 +61,17 @@ def __init__(
         and overall "ExpectationSuite" object, immediately available for validating underlying data "Batch" objects.
 
         Args:
-            name: the name of this DataAssistant object.
-            batch_request: specified for querying data Batch objects.
-            data_context: DataContext
+            name: the name of this DataAssistant object
+            validator: Validator object, containing loaded Batch objects as well as Expectation and Metric operations
         """
         self._name = name
-
-        self._data_context = data_context
-
-        self._validator = get_validator_using_batch_list_or_batch_request(
-            purpose=self.name,
-            data_context=self.data_context,
-            batch_list=None,
-            batch_request=batch_request,
-            domain=None,
-            variables=None,
-            parameters=None,
-        )
+        self._validator = validator
 
         self._profiler = RuleBasedProfiler(
             name=self.name,
             config_version=1.0,
             variables=None,
-            data_context=self.data_context,
+            data_context=self._validator.data_context,
         )
         self._build_profiler()
 
@@ -164,7 +147,8 @@ def run(
         Args:
             expectation_suite: An existing "ExpectationSuite" to update
             expectation_suite_name: A name for returned "ExpectationSuite"
-            include_citation: Whether or not to include the Profiler config in the metadata for "ExpectationSuite" produced by "RuleBasedProfiler"
+            include_citation: Flag, which controls whether or not to effective Profiler configuration should be included
+            as a citation in metadata of the "ExpectationSuite" computeds and returned by "RuleBasedProfiler"
 
         Returns:
             DataAssistantResult: The result object for the DataAssistant
@@ -192,10 +176,6 @@ def run(
     def name(self) -> str:
         return self._name
 
-    @property
-    def data_context(self) -> BaseDataContext:
-        return self._data_context
-
     @property
     def profiler(self) -> BaseRuleBasedProfiler:
         return self._profiler
@@ -268,8 +248,8 @@ def get_metrics_by_domain(self) -> Dict[Domain, Dict[str, ParameterNode]]:
         value of "DataAssistant.metrics_parameter_builders_by_domain_type" interface property and actual fully-qualified
         parameter names match interface properties of "ParameterBuilder" objects, corresponding to these "domain" types.
 
-        returns:
-            dictionaries of values for fully-qualified parameter names by domain for metrics, computed by "rulebasedprofiler" state.
+        Returns:
+            Dictionaries of values for fully-qualified parameter names by Domain for metrics, from "RuleBasedpRofiler"
         """
         # noinspection PyTypeChecker
         parameter_values_for_fully_qualified_parameter_names_by_domain: Dict[
@@ -326,7 +306,8 @@ def get_expectation_suite(
         Args:
             expectation_suite: An existing "ExpectationSuite" to update
             expectation_suite_name: A name for returned "ExpectationSuite"
-            include_citation: Whether or not to include the Profiler config in the metadata for "ExpectationSuite" produced by "RuleBasedProfiler"
+            include_citation: Flag, which controls whether or not to effective Profiler configuration should be included
+            as a citation in metadata of the "ExpectationSuite" computeds and returned by "RuleBasedProfiler"
 
         Returns:
             "ExpectationSuite" using "ExpectationConfiguration" objects, computed by "RuleBasedProfiler" state

great_expectations/rule_based_profiler/data_assistant/volume_data_assistant.py

@@ -1,7 +1,5 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
-from great_expectations.core.batch import BatchRequestBase
-from great_expectations.data_context import BaseDataContext
 from great_expectations.execution_engine.execution_engine import MetricDomainTypes
 from great_expectations.rule_based_profiler.data_assistant import DataAssistant
 from great_expectations.rule_based_profiler.parameter_builder import (
@@ -16,6 +14,7 @@
     DataAssistantResult,
     VolumeDataAssistantResult,
 )
+from great_expectations.validator.validator import Validator
 
 
 class VolumeDataAssistant(DataAssistant):
@@ -31,13 +30,11 @@ class VolumeDataAssistant(DataAssistant):
     def __init__(
         self,
         name: str,
-        batch_request: Union[BatchRequestBase, dict],
-        data_context: BaseDataContext = None,
+        validator: Validator,
     ):
         super().__init__(
             name=name,
-            batch_request=batch_request,
-            data_context=data_context,
+            validator=validator,
         )
 
     @property

great_expectations/rule_based_profiler/domain_builder/categorical_column_domain_builder.py

@@ -52,7 +52,7 @@ def __init__(
         limit_mode: Optional[Union[CardinalityLimitMode, str]] = None,
         max_unique_values: Optional[Union[str, int]] = None,
         max_proportion_unique: Optional[Union[str, float]] = None,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """Create column domains where cardinality is within the specified limit.
 
@@ -88,7 +88,7 @@ def __init__(
                 cardinality limit to use when filtering columns.
             max_proportion_unique: proportion of unique values for a
                 custom cardinality limit to use when filtering columns.
-            data_context: DataContext associated with this profiler.
+            data_context: BaseDataContext associated with this DomainBuilder
         """
         if exclude_column_names is None:
             exclude_column_names = [

great_expectations/rule_based_profiler/domain_builder/column_domain_builder.py

@@ -39,7 +39,7 @@ def __init__(
         exclude_semantic_types: Optional[
             Union[str, SemanticDomainTypes, List[Union[str, SemanticDomainTypes]]]
         ] = None,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """
         A semantic type is distinguished from the structured column type;
@@ -56,7 +56,7 @@ def __init__(
             to be included
             exclude_semantic_types: single/multiple type specifications using SemanticDomainTypes (or str equivalents)
             to be excluded
-            data_context: DataContext
+            data_context: BaseDataContext associated with this DomainBuilder
 
         Inclusion/Exclusion Logic:
         (include_column_names|table_columns - exclude_column_names) + (include_semantic_types - exclude_semantic_types)

great_expectations/rule_based_profiler/domain_builder/column_pair_domain_builder.py

@@ -14,12 +14,12 @@ class ColumnPairDomainBuilder(ColumnDomainBuilder):
     def __init__(
         self,
         include_column_names: Optional[Union[str, Optional[List[str]]]] = None,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """
         Args:
-            include_column_names: Explicitly specified exactly two desired columns.
-            data_context: DataContext associated with this profiler.
+            include_column_names: Explicitly specified exactly two desired columns
+            data_context: BaseDataContext associated with this DomainBuilder
         """
         super().__init__(
             include_column_names=include_column_names,

great_expectations/rule_based_profiler/domain_builder/domain_builder.py

@@ -27,11 +27,11 @@ class DomainBuilder(Builder, ABC):
 
     def __init__(
         self,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """
         Args:
-            data_context: DataContext
+            data_context: BaseDataContext associated with DomainBuilder
         """
         super().__init__(data_context=data_context)
 

great_expectations/rule_based_profiler/domain_builder/map_metric_column_domain_builder.py

@@ -37,7 +37,7 @@ def __init__(
         max_unexpected_values: Union[str, int] = 0,
         max_unexpected_ratio: Optional[Union[str, float]] = None,
         min_max_unexpected_values_proportion: Union[str, float] = 9.75e-1,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """
         Create column domains using tolerance for inter-Batch proportion of adherence to intra-Batch "unexpected_count"
@@ -59,9 +59,9 @@ def __init__(
             max_unexpected_values: maximum "unexpected_count" value of "map_metric_name" (intra-Batch)
             max_unexpected_ratio: maximum "unexpected_count" value of "map_metric_name" divided by number of records
             (intra-Batch); if both "max_unexpected_values" and "max_unexpected_ratio" are specified, then
-            "max_unexpected_ratio" is used (and "max_unexpected_values" is ignored).
+            "max_unexpected_ratio" is used (and "max_unexpected_values" is ignored)
             min_max_unexpected_values_proportion: minimum fraction of Batch objects adhering to "max_unexpected_values"
-            data_context: DataContext associated with this profiler.
+            data_context: BaseDataContext associated with this DomainBuilder
 
         For example (using default values of "max_unexpected_values" and "min_max_unexpected_values_proportion"):
         Suppose that "map_metric_name" is "column_values.nonnull" and consider the following three Batches of data:

great_expectations/rule_based_profiler/domain_builder/multi_column_domain_builder.py

@@ -14,12 +14,12 @@ class MultiColumnDomainBuilder(ColumnDomainBuilder):
     def __init__(
         self,
         include_column_names: Optional[Union[str, Optional[List[str]]]] = None,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """
         Args:
-            include_column_names: Explicitly specified desired columns.
-            data_context: DataContext associated with this profiler.
+            include_column_names: Explicitly specified desired columns
+            data_context: BaseDataContext associated with this DomainBuilder
         """
         super().__init__(
             include_column_names=include_column_names,

great_expectations/rule_based_profiler/domain_builder/table_domain_builder.py

@@ -8,11 +8,11 @@
 class TableDomainBuilder(DomainBuilder):
     def __init__(
         self,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     ):
         """
         Args:
-            data_context: DataContext
+            data_context: BaseDataContext associated with this DomainBuilder
         """
         super().__init__(data_context=data_context)
 

great_expectations/rule_based_profiler/expectation_configuration_builder/default_expectation_configuration_builder.py

@@ -70,19 +70,19 @@ def __init__(
         validation_parameter_builder_configs: Optional[
             List[ParameterBuilderConfig]
         ] = None,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
         **kwargs,
     ):
         """
         Args:
             expectation_type: the "expectation_type" argument of "ExpectationConfiguration" object to be emitted.
-            meta: the "meta" argument of "ExpectationConfiguration" object to be emitted.
+            meta: the "meta" argument of "ExpectationConfiguration" object to be emitted
             condition: Boolean statement (expressed as string and following specified grammar), which controls whether
-            or not underlying logic should be executed and thus resulting "ExpectationConfiguration" emitted.
+            or not underlying logic should be executed and thus resulting "ExpectationConfiguration" emitted
             validation_parameter_builder_configs: ParameterBuilder configurations, having whose outputs available (as
-            fully-qualified parameter names) is pre-requisite for present ExpectationConfigurationBuilder instance.
-            These "ParameterBuilder" configurations help build kwargs needed for this "ExpectationConfigurationBuilder".
-            data_context: DataContext
+            fully-qualified parameter names) is pre-requisite for present ExpectationConfigurationBuilder instance
+            These "ParameterBuilder" configurations help build kwargs needed for this "ExpectationConfigurationBuilder"
+            data_context: BaseDataContext associated with this ExpectationConfigurationBuilder
             kwargs: additional arguments
         """
 

great_expectations/rule_based_profiler/expectation_configuration_builder/expectation_configuration_builder.py

@@ -31,7 +31,7 @@ def __init__(
         validation_parameter_builder_configs: Optional[
             List[ParameterBuilderConfig]
         ] = None,
-        data_context: Optional["DataContext"] = None,  # noqa: F821
+        data_context: Optional["BaseDataContext"] = None,  # noqa: F821
         **kwargs
     ):
         """
@@ -41,8 +41,8 @@ def __init__(
             expectation_type: the "expectation_type" argument of "ExpectationConfiguration" object to be emitted.
             validation_parameter_builder_configs: ParameterBuilder configurations, having whose outputs available (as
             fully-qualified parameter names) is pre-requisite for present ExpectationConfigurationBuilder instance.
-            These "ParameterBuilder" configurations help build kwargs needed for this "ExpectationConfigurationBuilder".
-            data_context: DataContext
+            These "ParameterBuilder" configurations help build kwargs needed for this "ExpectationConfigurationBuilder"
+            data_context: BaseDataContext associated with this ExpectationConfigurationBuilder
             kwargs: additional arguments
         """
 
@@ -146,7 +146,7 @@ def validation_parameter_builders(self) -> Optional[List[ParameterBuilder]]:
 
 def init_rule_expectation_configuration_builders(
     expectation_configuration_builder_configs: List[dict],
-    data_context: Optional["DataContext"] = None,  # noqa: F821
+    data_context: Optional["BaseDataContext"] = None,  # noqa: F821
 ) -> List["ExpectationConfigurationBuilder"]:  # noqa: F821
     expectation_configuration_builder_config: dict
     return [
@@ -162,7 +162,7 @@ def init_expectation_configuration_builder(
     expectation_configuration_builder_config: Union[
         "ExpectationConfigurationBuilder", dict  # noqa: F821
     ],
-    data_context: Optional["DataContext"] = None,  # noqa: F821
+    data_context: Optional["BaseDataContext"] = None,  # noqa: F821
 ) -> "ExpectationConfigurationBuilder":  # noqa: F821
     if not isinstance(expectation_configuration_builder_config, dict):
         expectation_configuration_builder_config = (

great_expectations/rule_based_profiler/helpers/util.py

@@ -37,7 +37,7 @@
 def get_validator(
     purpose: str,
     *,
-    data_context: Optional["DataContext"] = None,  # noqa: F821
+    data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     batch_list: Optional[List[Batch]] = None,
     batch_request: Optional[Union[str, BatchRequestBase, dict]] = None,
     domain: Optional[Domain] = None,
@@ -92,7 +92,7 @@ def get_validator(
 
 
 def get_batch_ids(
-    data_context: Optional["DataContext"] = None,  # noqa: F821
+    data_context: Optional["BaseDataContext"] = None,  # noqa: F821
     batch_list: Optional[List[Batch]] = None,
     batch_request: Optional[Union[str, BatchRequestBase, dict]] = None,
     domain: Optional[Domain] = None,
@@ -126,7 +126,7 @@ def get_batch_ids(
 
 
 def build_batch_request(
-    batch_request: Optional[Union[str, BatchRequest, RuntimeBatchRequest, dict]] = None,
+    batch_request: Optional[Union[str, BatchRequestBase, dict]] = None,
     domain: Optional[Domain] = None,
     variables: Optional[ParameterContainer] = None,
     parameters: Optional[Dict[str, ParameterContainer]] = None,
@@ -136,11 +136,11 @@ def build_batch_request(
 
     # Obtain BatchRequest from "rule state" (i.e., variables and parameters); from instance variable otherwise.
     effective_batch_request: Optional[
-        Union[BatchRequest, RuntimeBatchRequest, dict]
+        Union[BatchRequestBase, dict]
     ] = get_parameter_value_and_validate_return_type(
         domain=domain,
         parameter_reference=batch_request,
-        expected_return_type=(BatchRequest, RuntimeBatchRequest, dict),
+        expected_return_type=(BatchRequestBase, dict),
         variables=variables,
         parameters=parameters,
     )