[MAINTENANCE] Rule-Based Profiler prerequisite: fix quantiles profile…

…r configuration and add comments (#4255)

great_expectations/rule_based_profiler/domain_builder/column_domain_builder.py

@@ -34,6 +34,11 @@ def __init__(
     def domain_type(self) -> Union[str, MetricDomainTypes]:
         return MetricDomainTypes.COLUMN
 
+    """
+    All DomainBuilder classes, whose "domain_type" property equals "MetricDomainTypes.COLUMN", must extend present class
+    (ColumnDomainBuilder) in order to provide full getter/setter accessor for "column_names" property (as override).
+    """
+
     @property
     def column_names(self) -> List[str]:
         return self._column_names

great_expectations/rule_based_profiler/domain_builder/domain_builder.py

@@ -68,16 +68,16 @@ def domain_type(self) -> Union[str, MetricDomainTypes]:
     def batch_request(self) -> Optional[Union[BatchRequest, RuntimeBatchRequest, dict]]:
         return self._batch_request
 
+    """
+    Full getter/setter accessors for "batch_request" and "batch" are for configuring DomainBuilder dynamically.
+    """
+
     @batch_request.setter
     def batch_request(
         self, value: Union[BatchRequest, RuntimeBatchRequest, dict]
     ) -> None:
         self._batch_request = value
 
-    @property
-    def data_context(self) -> "DataContext":  # noqa: F821
-        return self._data_context
-
     @property
     def batch(self) -> Optional[Batch]:
         return self._batch
@@ -86,6 +86,10 @@ def batch(self) -> Optional[Batch]:
     def batch(self, value: Batch) -> None:
         self._batch = value
 
+    @property
+    def data_context(self) -> "DataContext":  # noqa: F821
+        return self._data_context
+
     @abstractmethod
     def _get_domains(
         self,

great_expectations/rule_based_profiler/expectation_configuration_builder/default_expectation_configuration_builder.py

@@ -37,7 +37,7 @@ def __init__(
         if not isinstance(meta, dict):
             raise ge_exceptions.ProfilerExecutionError(
                 message=f"""Argument "{meta}" in "{self.__class__.__name__}" must be of type "dictionary" \
-(value of type "{str(type())}" was encountered).
+(value of type "{str(type(meta))}" was encountered).
 """
             )
 

great_expectations/rule_based_profiler/parameter_builder/metric_multi_batch_parameter_builder.py

@@ -69,6 +69,10 @@ def __init__(
 
         self._reduce_scalar_metric = reduce_scalar_metric
 
+    """
+    Full getter/setter accessors for needed properties are for configuring MetricMultiBatchParameterBuilder dynamically.
+    """
+
     @property
     def metric_name(self) -> str:
         return self._metric_name

great_expectations/rule_based_profiler/parameter_builder/numeric_metric_range_multi_batch_parameter_builder.py

@@ -145,6 +145,10 @@ def __init__(
 
         self._truncate_values = truncate_values
 
+    """
+    Full getter/setter accessors for needed properties are for configuring MetricMultiBatchParameterBuilder dynamically.
+    """
+
     @property
     def metric_name(self) -> str:
         return self._metric_name

great_expectations/rule_based_profiler/parameter_builder/parameter_builder.py

@@ -100,6 +100,10 @@ def build_parameters(
     def name(self) -> str:
         return self._name
 
+    """
+    Full getter/setter accessors for "batch_request" and "batch_list" are for configuring ParameterBuilder dynamically.
+    """
+
     @property
     def batch_request(self) -> Optional[Union[BatchRequest, RuntimeBatchRequest, dict]]:
         return self._batch_request
@@ -110,10 +114,6 @@ def batch_request(
     ) -> None:
         self._batch_request = value
 
-    @property
-    def data_context(self) -> "DataContext":  # noqa: F821
-        return self._data_context
-
     @property
     def batch_list(self) -> Optional[List[Batch]]:
         return self._batch_list
@@ -122,6 +122,10 @@ def batch_list(self) -> Optional[List[Batch]]:
     def batch_list(self, value: List[Batch]) -> None:
         self._batch_list = value
 
+    @property
+    def data_context(self) -> "DataContext":  # noqa: F821
+        return self._data_context
+
     @abstractmethod
     def _build_parameters(
         self,

great_expectations/rule_based_profiler/parameter_builder/regex_pattern_string_parameter_builder.py

@@ -78,6 +78,10 @@ def __init__(
 
         self._candidate_regexes = candidate_regexes
 
+    """
+    Full getter/setter accessors for needed properties are for configuring MetricMultiBatchParameterBuilder dynamically.
+    """
+
     @property
     def metric_domain_kwargs(self) -> Optional[Union[str, dict]]:
         return self._metric_domain_kwargs

great_expectations/rule_based_profiler/parameter_builder/simple_date_format_string_parameter_builder.py

@@ -123,6 +123,10 @@ def __init__(
 
         self._candidate_strings = candidate_strings
 
+    """
+    Full getter/setter accessors for needed properties are for configuring MetricMultiBatchParameterBuilder dynamically.
+    """
+
     @property
     def metric_domain_kwargs(self) -> Optional[Union[str, dict]]:
         return self._metric_domain_kwargs

tests/integration/profiling/rule_based_profilers/test_profiler_user_workflows.py

@@ -1,6 +1,6 @@
 import datetime
 from numbers import Number
-from typing import Any, Dict, List, cast
+from typing import Any, Dict, List, Tuple, cast
 
 import numpy as np
 import pandas as pd
@@ -361,7 +361,7 @@ def test_quentin_profiler_user_workflow_multi_batch_quantiles_value_ranges_rule(
     expect_column_quantile_values_to_be_between_expectation_configurations_value_ranges_by_column: Dict[
         str, List[List[Number]]
     ] = {
-        column_name: expectation_kwargs["value_ranges"]
+        column_name: expectation_kwargs["quantile_ranges"]["value_ranges"]
         for column_name, expectation_kwargs in expect_column_quantile_values_to_be_between_expectation_configurations_kwargs_dict.items()
     }
 
@@ -379,7 +379,7 @@ def test_quentin_profiler_user_workflow_multi_batch_quantiles_value_ranges_rule(
     rtol: float = 1.0e-7
     atol: float = 5.0e-2
 
-    value_range: List[Number]
+    value_ranges: List[Tuple[Tuple[float, float]]]
     paired_quantiles: zip
     column_quantiles: List[List[Number]]
     idx: int
@@ -395,12 +395,12 @@ def test_quentin_profiler_user_workflow_multi_batch_quantiles_value_ranges_rule(
                 "expect_column_quantile_values_to_be_between_quantile_ranges_by_column"
             ][column_name],
         )
-        for value_range in list(paired_quantiles):
+        for value_ranges in list(paired_quantiles):
             for idx in range(2):
                 np.testing.assert_allclose(
-                    actual=value_range[0][idx],
-                    desired=value_range[1][idx],
+                    actual=value_ranges[0][idx],
+                    desired=value_ranges[1][idx],
                     rtol=rtol,
                     atol=atol,
-                    err_msg=f"Actual value of {value_range[0][idx]} differs from expected value of {value_range[1][idx]} by more than {atol + rtol * abs(value_range[1][idx])} tolerance.",
+                    err_msg=f"Actual value of {value_ranges[0][idx]} differs from expected value of {value_ranges[1][idx]} by more than {atol + rtol * abs(value_ranges[1][idx])} tolerance.",
                 )

tests/test_fixtures/rule_based_profiler/quentin_user_workflow_verbose_profiler_config.yml

@@ -9,6 +9,7 @@ variables:
     - 2.5e-1
     - 5.0e-1
     - 7.5e-1
+  allow_relative_error: linear
   num_bootstrap_samples: 9139
 
   # BatchRequest yielding thirty five (35) batches (January, 2018 -- November, 2020 trip data)
@@ -42,15 +43,17 @@ rules:
         metric_domain_kwargs: $domain.domain_kwargs
         metric_value_kwargs:
           quantiles: $variables.quantiles
-          allow_relative_error: linear
+          allow_relative_error: $variables.allow_relative_error
         false_positive_rate: $variables.false_positive_rate
         num_bootstrap_samples: $variables.num_bootstrap_samples
     expectation_configuration_builders:
       - expectation_type: expect_column_quantile_values_to_be_between
         class_name: DefaultExpectationConfigurationBuilder
         module_name: great_expectations.rule_based_profiler.expectation_configuration_builder
         column: $domain.domain_kwargs.column
-        quantiles: $variables.quantiles
-        value_ranges: $parameter.quantile_value_ranges.value.value_range
+        quantile_ranges:
+          quantiles: $variables.quantiles
+          value_ranges: $parameter.quantile_value_ranges.value.value_range
+        allow_relative_error: $variables.allow_relative_error
         meta:
           profiler_details: $parameter.quantile_value_ranges.details