[MAINTENANCE] Replace black formatter with ruff format

.pre-commit-config.yaml

@@ -17,16 +17,13 @@ repos:
         args: [--branch, develop, --branch, main]
       - id: detect-private-key
         exclude: tests/test_fixtures/database_key_test*
-  - repo: https://github.com/psf/black
-    rev: 23.11.0
-    hooks:
-      - id: black-jupyter
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: "v0.2.2"
     hooks:
       - id: ruff
         files: ^(great_expectations|assets|contrib|scripts|tasks\.py|tests) # TODO: add docs/ etc.
         args: ["--fix"]
+      - id: ruff-format
   # Github Actions Linter
   # Need to be able to inline ignore errors
   # https://github.com/rhysd/actionlint/issues/237

assets/scripts/build_package_gallery.py

@@ -104,7 +104,9 @@ def write_results_to_disk(path: str, package_manifests: List[dict]) -> None:
 if __name__ == "__main__":
     pwd = os.path.abspath(os.getcwd())  # noqa: PTH100, PTH109
     root = os.path.join(  # noqa: PTH118
-        os.path.dirname(os.path.abspath(__file__)), "..", ".."  # noqa: PTH100, PTH120
+        os.path.dirname(os.path.abspath(__file__)),
+        "..",
+        "..",
     )
     try:
         os.chdir(root)

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_column_values_confidence_for_data_label_to_be_greater_than_or_equal_to_threshold.py

@@ -186,7 +186,5 @@ class ExpectColumnValuesConfidenceForDataLabelToBeGreaterThanOrEqualToThreshold(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectColumnValuesConfidenceForDataLabelToBeGreaterThanOrEqualToThreshold().run_diagnostics()
-    )
+    diagnostics_report = ExpectColumnValuesConfidenceForDataLabelToBeGreaterThanOrEqualToThreshold().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_column_values_confidence_for_data_label_to_be_less_than_or_equal_to_threshold.py

@@ -187,7 +187,5 @@ class ExpectColumnValuesConfidenceForDataLabelToBeLessThanOrEqualToThreshold(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectColumnValuesConfidenceForDataLabelToBeLessThanOrEqualToThreshold().run_diagnostics()
-    )
+    diagnostics_report = ExpectColumnValuesConfidenceForDataLabelToBeLessThanOrEqualToThreshold().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_column_values_to_be_probabilistically_greater_than_or_equal_to_threshold.py

@@ -166,7 +166,5 @@ class ExpectColumnValuesToBeProbabilisticallyGreaterThanOrEqualToThreshold(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectColumnValuesToBeProbabilisticallyGreaterThanOrEqualToThreshold().run_diagnostics()
-    )
+    diagnostics_report = ExpectColumnValuesToBeProbabilisticallyGreaterThanOrEqualToThreshold().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_profile_numeric_columns_diff_between_exclusive_threshold_range.py

@@ -321,7 +321,5 @@ class ExpectProfileNumericColumnsDiffBetweenExclusiveThresholdRange(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectProfileNumericColumnsDiffBetweenExclusiveThresholdRange().run_diagnostics()
-    )
+    diagnostics_report = ExpectProfileNumericColumnsDiffBetweenExclusiveThresholdRange().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_profile_numeric_columns_diff_between_inclusive_threshold_range.py

@@ -323,7 +323,5 @@ class ExpectProfileNumericColumnsDiffBetweenInclusiveThresholdRange(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectProfileNumericColumnsDiffBetweenInclusiveThresholdRange().run_diagnostics()
-    )
+    diagnostics_report = ExpectProfileNumericColumnsDiffBetweenInclusiveThresholdRange().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_profile_numeric_columns_percent_diff_between_exclusive_threshold_range.py

@@ -362,7 +362,5 @@ class ExpectProfileNumericColumnsPercentDiffBetweenExclusiveThresholdRange(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectProfileNumericColumnsPercentDiffBetweenExclusiveThresholdRange().run_diagnostics()
-    )
+    diagnostics_report = ExpectProfileNumericColumnsPercentDiffBetweenExclusiveThresholdRange().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_profile_numeric_columns_percent_diff_between_inclusive_threshold_range.py

@@ -358,7 +358,5 @@ class ExpectProfileNumericColumnsPercentDiffBetweenInclusiveThresholdRange(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectProfileNumericColumnsPercentDiffBetweenInclusiveThresholdRange().run_diagnostics()
-    )
+    diagnostics_report = ExpectProfileNumericColumnsPercentDiffBetweenInclusiveThresholdRange().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_profile_numeric_columns_percent_diff_greater_than_or_equal_to_threshold.py

@@ -355,7 +355,5 @@ class ExpectProfileNumericColumnsPercentDiffGreaterThanOrEqualToThreshold(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectProfileNumericColumnsPercentDiffGreaterThanOrEqualToThreshold().run_diagnostics()
-    )
+    diagnostics_report = ExpectProfileNumericColumnsPercentDiffGreaterThanOrEqualToThreshold().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/expectations/expect_profile_numeric_columns_percent_diff_less_than_or_equal_to_threshold.py

@@ -355,7 +355,5 @@ class ExpectProfileNumericColumnsPercentDiffLessThanOrEqualToThreshold(
 
 
 if __name__ == "__main__":
-    diagnostics_report = (
-        ExpectProfileNumericColumnsPercentDiffLessThanOrEqualToThreshold().run_diagnostics()
-    )
+    diagnostics_report = ExpectProfileNumericColumnsPercentDiffLessThanOrEqualToThreshold().run_diagnostics()
     print(diagnostics_report.generate_checklist())

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/tests/conftest.py

@@ -171,7 +171,8 @@ def bobby_columnar_table_multi_batch_deterministic_data_context(
     project_path: str = str(tmp_path_factory.mktemp("taxi_data_context"))
     context_path: str = os.path.join(project_path, "great_expectations")  # noqa: PTH118
     os.makedirs(  # noqa: PTH103
-        os.path.join(context_path, "expectations"), exist_ok=True  # noqa: PTH118
+        os.path.join(context_path, "expectations"),
+        exist_ok=True,
     )
     data_path: str = os.path.join(context_path, "..", "data")  # noqa: PTH118
     os.makedirs(os.path.join(data_path), exist_ok=True)  # noqa: PTH118, PTH103
@@ -262,7 +263,8 @@ def bobby_columnar_table_multi_batch_probabilistic_data_context(
     project_path: str = str(tmp_path_factory.mktemp("taxi_data_context"))
     context_path: str = os.path.join(project_path, "great_expectations")  # noqa: PTH118
     os.makedirs(  # noqa: PTH103
-        os.path.join(context_path, "expectations"), exist_ok=True  # noqa: PTH118
+        os.path.join(context_path, "expectations"),
+        exist_ok=True,
     )
     data_path: str = os.path.join(context_path, "..", "data")  # noqa: PTH118
     os.makedirs(os.path.join(data_path), exist_ok=True)  # noqa: PTH118, PTH103

contrib/capitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/tests/rule_based_profiler/data_assistant/test_data_profiler_structured_data_assistant.py

@@ -168,9 +168,7 @@ def test_profile_data_profiler_structured_data_assistant_metrics_count(
     for (
         domain,
         parameter_values_for_fully_qualified_parameter_names,
-    ) in (
-        bobby_profile_data_profiler_structured_data_assistant_result.metrics_by_domain.items()
-    ):
+    ) in bobby_profile_data_profiler_structured_data_assistant_result.metrics_by_domain.items():
         if domain.is_superset(other=domain_key):
             num_metrics += len(parameter_values_for_fully_qualified_parameter_names)
 
@@ -180,9 +178,7 @@ def test_profile_data_profiler_structured_data_assistant_metrics_count(
     for (
         domain,
         parameter_values_for_fully_qualified_parameter_names,
-    ) in (
-        bobby_profile_data_profiler_structured_data_assistant_result.metrics_by_domain.items()
-    ):
+    ) in bobby_profile_data_profiler_structured_data_assistant_result.metrics_by_domain.items():
         num_metrics += len(parameter_values_for_fully_qualified_parameter_names)
     assert (
         num_metrics == 50

contrib/cli/great_expectations_contrib/cli.py

@@ -13,7 +13,8 @@
 # The following link points to the repo where the Cookiecutter template is hosted
 URL = "https://github.com/great-expectations/great-expectations-contrib-cookiecutter"
 PACKAGE_PATH = os.path.join(  # noqa: PTH118
-    os.getcwd(), ".great_expectations_package.json"  # noqa: PTH109
+    os.getcwd(),
+    ".great_expectations_package.json",
 )
 
 

contrib/cli/great_expectations_contrib/commands.py

@@ -61,9 +61,9 @@ def publish_cmd() -> None:
 def perform_check(suppress_output: bool) -> bool:
     commands = [
         Command(
-            "black",
-            "black --check .",
-            "Please ensure that your files are linted properly with `black .`",
+            "ruff format",
+            "ruff format --check .",
+            "Please ensure that your files are linted properly with `ruff format .`",
         ),
         # TODO: update this (or don't)
         Command(

contrib/cli/great_expectations_contrib/package.py

@@ -106,9 +106,7 @@ def update_package_state(self) -> None:
         """
         Parses diagnostic reports from package Expectations and uses them to update JSON state
         """
-        diagnostics = (
-            GreatExpectationsContribPackageManifest.retrieve_package_expectations_diagnostics()
-        )
+        diagnostics = GreatExpectationsContribPackageManifest.retrieve_package_expectations_diagnostics()
         self._update_attrs_with_diagnostics(diagnostics)
 
     def _update_attrs_with_diagnostics(

contrib/cli/requirements.txt

@@ -1,9 +1,8 @@
-black[jupyter]==23.10.1 # Linting / code style
 Click>=7.1.2         # CLI tooling
 cookiecutter==2.1.1  # Project templating
 mypy==1.7.1            # Type checker
 pydantic>=1.0        # Needed for mypy plugin
 pytest>=5.3.5        # Test framework
-ruff==0.2.2        # Linting / code style
+ruff==0.2.2        # Linting / code style / formatting
 twine==3.7.1         # Packaging
 wheel==0.38.1        # Packaging

contrib/experimental/great_expectations_experimental/expectations/expect_multicolumn_product_values_to_be_equal_to_single_column.py

@@ -91,6 +91,7 @@ class ExpectMulticolumnProductToBeEqualToSingleColumn(MulticolumnMapExpectation)
             A numeric value that is included in the calculation to equal the nth column. \
             The calculation becomes col_a * col_b * ... * col_n-1 * additional_value == col_n
     """
+
     # </snippet>
 
     # These examples will be shown in the public gallery.

contrib/experimental/great_expectations_experimental/expectations/expect_multicolumn_sum_values_to_be_equal_to_single_column.py

@@ -88,6 +88,7 @@ class ExpectMulticolumnSumValuesToBeEqualToSingleColumn(MulticolumnMapExpectatio
             A numeric value that is included in the calculation to equal the nth column. \
             The calculation becomes col_a + col_b + ... + col_n-1 + additional_value == col_n
     """
+
     # </snippet>
 
     additional_value: Optional[float] = None

contrib/experimental/great_expectations_experimental/expectations/expect_queried_column_value_frequency_to_meet_threshold.py

@@ -64,11 +64,14 @@ def validate_configuration(
 
         try:
             assert value is not None, "'value' must be specified"
-            assert (isinstance(threshold, (int, float)) and 0 < threshold <= 1) or (
-                isinstance(threshold, list)
-                and all(isinstance(x, (int, float)) for x in threshold)
-                and all(0 < x <= 1 for x in threshold)
-                and 0 < sum(threshold) <= 1
+            assert (
+                (isinstance(threshold, (int, float)) and 0 < threshold <= 1)
+                or (
+                    isinstance(threshold, list)
+                    and all(isinstance(x, (int, float)) for x in threshold)
+                    and all(0 < x <= 1 for x in threshold)
+                    and 0 < sum(threshold) <= 1
+                )
             ), "'threshold' must be 1, a float between 0 and 1, or a list of floats whose sum is between 0 and 1"
             if isinstance(threshold, list):
                 assert isinstance(value, list) and len(value) == len(

contrib/experimental/great_expectations_experimental/expectations/expect_value_at_index.py

@@ -188,7 +188,7 @@ class ExpectValueAtIndex(ColumnMapExpectation):
         ],
         "contributors": [
             "@prem1835213",
-            "@YaosenLin"
+            "@YaosenLin",
             # Github handles for all contributors to this Expectation.
             #         "@your_name_here", # Don't forget to add your github handle here!
         ],

contrib/experimental/great_expectations_experimental/rule_based_profiler/data_assistant/growth_numeric_data_assistant.py

@@ -75,9 +75,7 @@ def get_rules(self) -> Optional[List[Rule]]:
         """
         table_rule: Rule = self._build_table_rule()
 
-        total_count_metric_multi_batch_parameter_builder_for_evaluations: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_table_row_count_metric_multi_batch_parameter_builder()
-        )
+        total_count_metric_multi_batch_parameter_builder_for_evaluations: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_table_row_count_metric_multi_batch_parameter_builder()
         column_value_nonnullity_rule: Rule = build_map_metric_rule(
             data_assistant_class_name=self.__class__.__name__,
             rule_name="column_value_nonnullity_rule",
@@ -134,12 +132,8 @@ def _build_table_rule() -> Rule:
 
         # Step-2: Declare "ParameterBuilder" for every metric of interest.
 
-        table_row_count_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_table_row_count_metric_multi_batch_parameter_builder()
-        )
-        table_columns_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_table_columns_metric_multi_batch_parameter_builder()
-        )
+        table_row_count_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_table_row_count_metric_multi_batch_parameter_builder()
+        table_columns_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_table_columns_metric_multi_batch_parameter_builder()
 
         # Step-3: Declare "ParameterBuilder" for every "validation" need in "ExpectationConfigurationBuilder" objects.
 
@@ -267,24 +261,12 @@ def _build_numeric_columns_rule() -> Rule:
         column_histogram_single_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.build_histogram_single_batch_parameter_builder(
             name="column_values.partition",
         )
-        column_min_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_min_metric_multi_batch_parameter_builder()
-        )
-        column_max_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_max_metric_multi_batch_parameter_builder()
-        )
-        column_quantile_values_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_quantile_values_metric_multi_batch_parameter_builder()
-        )
-        column_median_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_median_metric_multi_batch_parameter_builder()
-        )
-        column_mean_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_mean_metric_multi_batch_parameter_builder()
-        )
-        column_standard_deviation_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_standard_deviation_metric_multi_batch_parameter_builder()
-        )
+        column_min_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_min_metric_multi_batch_parameter_builder()
+        column_max_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_max_metric_multi_batch_parameter_builder()
+        column_quantile_values_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_quantile_values_metric_multi_batch_parameter_builder()
+        column_median_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_median_metric_multi_batch_parameter_builder()
+        column_mean_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_mean_metric_multi_batch_parameter_builder()
+        column_standard_deviation_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_standard_deviation_metric_multi_batch_parameter_builder()
 
         # Step-3: Declare "ParameterBuilder" for every "validation" need in "ExpectationConfigurationBuilder" objects.
 
@@ -579,9 +561,7 @@ def _build_categorical_columns_rule() -> Rule:
 
         # Step-2: Declare "ParameterBuilder" for every metric of interest.
 
-        column_distinct_values_count_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = (
-            DataAssistant.commonly_used_parameter_builders.get_column_distinct_values_count_metric_multi_batch_parameter_builder()
-        )
+        column_distinct_values_count_metric_multi_batch_parameter_builder_for_metrics: ParameterBuilder = DataAssistant.commonly_used_parameter_builders.get_column_distinct_values_count_metric_multi_batch_parameter_builder()
 
         # Step-3: Declare "ParameterBuilder" for every "validation" need in "ExpectationConfigurationBuilder" objects.