great-expectations · Kilo59 · Mar 5, 2024 · Feb 26, 2024 · Feb 26, 2024 · Feb 26, 2024
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -3,7 +3,7 @@
 
 - [ ] Description of PR changes above includes a link to [an existing GitHub issue](https://github.com/great-expectations/great_expectations/issues)
 - [ ] PR title is prefixed with one of: [BUGFIX], [FEATURE], [DOCS], [MAINTENANCE], [CONTRIB]
-- [ ] Code is linted - run `invoke lint` (uses `black` + `ruff`)
+- [ ] Code is linted - run `invoke lint` (uses `ruff format` + `ruff check`)
 - [ ] Appropriate tests and docs have been updated
 
 For more information about contributing, see [Contribute](https://docs.greatexpectations.io/docs/contributing/contributing_checklist).

diff --git a/.pre-commit-config.yaml b/.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"
+    rev: "v0.3.0"
     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

diff --git a/assets/scripts/build_gallery.py b/assets/scripts/build_gallery.py
@@ -439,19 +439,19 @@ def combine_backend_results(
                 tests=diagnostic_object.tests,
                 backend_test_result_counts=backend_test_result_counts_object,
             )
-            expectations_info[expectation_name][
-                "maturity_checklist"
-            ] = maturity_checklist_object.to_dict()
-            expectations_info[expectation_name][
-                "coverage_score"
-            ] = Expectation._get_coverage_score(
-                backend_test_result_counts=backend_test_result_counts_object,
-                execution_engines=diagnostic_object.execution_engines,
+            expectations_info[expectation_name]["maturity_checklist"] = (
+                maturity_checklist_object.to_dict()
+            )
+            expectations_info[expectation_name]["coverage_score"] = (
+                Expectation._get_coverage_score(
+                    backend_test_result_counts=backend_test_result_counts_object,
+                    execution_engines=diagnostic_object.execution_engines,
+                )
             )
-            expectations_info[expectation_name]["library_metadata"][
-                "maturity"
-            ] = Expectation._get_final_maturity_level(
-                maturity_checklist=maturity_checklist_object
+            expectations_info[expectation_name]["library_metadata"]["maturity"] = (
+                Expectation._get_final_maturity_level(
+                    maturity_checklist=maturity_checklist_object
+                )
             )
 
         for bad_key_name in bad_key_names:

diff --git a/assets/scripts/build_package_gallery.py b/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)

diff --git a/ci/checks/check_no_line_number_snippets.py b/ci/checks/check_no_line_number_snippets.py
@@ -2,6 +2,7 @@
 Purpose: To ensure that no docs snippets use the file and line number convention,
 only the named snippets convention.
 """
+
 import pathlib
 import re
 import shutil

diff --git a/ci/checks/validate_docs_snippets.py b/ci/checks/validate_docs_snippets.py
@@ -3,6 +3,7 @@
 
 In short, this script creates a temporary Docusaurus build and utilizes grep to parse for stray tags.
 """
+
 from __future__ import annotations
 
 import shutil

diff --git a/...xpect_column_values_confidence_for_data_label_to_be_greater_than_or_equal_to_threshold.py b/...xpect_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())
diff --git a/...s/expect_column_values_confidence_for_data_label_to_be_less_than_or_equal_to_threshold.py b/...s/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())
diff --git a/...ectations/expectations/expect_column_values_to_be_equal_to_or_greater_than_profile_min.py b/...ectations/expectations/expect_column_values_to_be_equal_to_or_greater_than_profile_min.py
@@ -3,6 +3,7 @@
 For detailed instructions on how to use it, please see:
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_column_map_expectations
 """
+
 from typing import Any
 
 import dataprofiler as dp

diff --git a/...expectations/expectations/expect_column_values_to_be_equal_to_or_less_than_profile_max.py b/...expectations/expectations/expect_column_values_to_be_equal_to_or_less_than_profile_max.py
@@ -3,6 +3,7 @@
 For detailed instructions on how to use it, please see:
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_column_map_expectations
 """
+
 from typing import Any
 
 import dataprofiler as dp

diff --git a/...ations/expect_column_values_to_be_probabilistically_greater_than_or_equal_to_threshold.py b/...ations/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())
diff --git a/...ons/expectations/expect_profile_numeric_columns_diff_between_exclusive_threshold_range.py b/...ons/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())
diff --git a/...ons/expectations/expect_profile_numeric_columns_diff_between_inclusive_threshold_range.py b/...ons/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())
diff --git a/...ctations/expect_profile_numeric_columns_percent_diff_between_exclusive_threshold_range.py b/...ctations/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())
diff --git a/...ctations/expect_profile_numeric_columns_percent_diff_between_inclusive_threshold_range.py b/...ctations/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())
diff --git a/...tations/expect_profile_numeric_columns_percent_diff_greater_than_or_equal_to_threshold.py b/...tations/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())
diff --git a/...pectations/expect_profile_numeric_columns_percent_diff_less_than_or_equal_to_threshold.py b/...pectations/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())
diff --git a/...pitalone_dataprofiler_expectations/capitalone_dataprofiler_expectations/tests/conftest.py b/...pitalone_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

diff --git a/.../tests/rule_based_profiler/data_assistant/test_data_profiler_structured_data_assistant.py b/.../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
@@ -193,9 +189,9 @@ def test_profile_data_profiler_structured_data_assistant_metrics_count(
 def test_profile_data_profiler_structured_data_assistant_result_batch_id_to_batch_identifier_display_name_map_coverage(
     bobby_profile_data_profiler_structured_data_assistant_result: DataProfilerStructuredDataAssistantResult,
 ):
-    metrics_by_domain: Optional[
-        Dict[Domain, Dict[str, ParameterNode]]
-    ] = bobby_profile_data_profiler_structured_data_assistant_result.metrics_by_domain
+    metrics_by_domain: Optional[Dict[Domain, Dict[str, ParameterNode]]] = (
+        bobby_profile_data_profiler_structured_data_assistant_result.metrics_by_domain
+    )
 
     parameter_values_for_fully_qualified_parameter_names: Dict[str, ParameterNode]
     parameter_node: ParameterNode

diff --git a/contrib/cli/great_expectations_contrib/cli.py b/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",
 )
 
 

diff --git a/contrib/cli/great_expectations_contrib/commands.py b/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(

diff --git a/contrib/cli/great_expectations_contrib/package.py b/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(

diff --git a/contrib/cli/requirements.txt b/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==0.3.0        # Linting / code style / formatting
 twine==3.7.1         # Packaging
 wheel==0.38.1        # Packaging
diff --git a/...t_expectations_experimental/expectations/expect_column_values_after_split_to_be_unique.py b/...t_expectations_experimental/expectations/expect_column_values_after_split_to_be_unique.py
@@ -4,7 +4,6 @@
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_column_map_expectations
 """
 
-
 from great_expectations.execution_engine import PandasExecutionEngine
 from great_expectations.expectations.expectation import ColumnMapExpectation
 from great_expectations.expectations.metrics import (

diff --git a/...reat_expectations_experimental/expectations/expect_column_values_not_to_be_future_date.py b/...reat_expectations_experimental/expectations/expect_column_values_not_to_be_future_date.py
@@ -3,6 +3,7 @@
 For detailed instructions on how to use it, please see:
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_column_map_expectations
 """
+
 from datetime import date
 
 from dateutil.parser import parse

diff --git a/...mental/great_expectations_experimental/expectations/expect_column_values_to_match_thai.py b/...mental/great_expectations_experimental/expectations/expect_column_values_to_match_thai.py
@@ -4,7 +4,6 @@
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_regex_based_column_map_expectations
 """
 
-
 from great_expectations.expectations.regex_based_column_map_expectation import (
     RegexBasedColumnMapExpectation,
 )
@@ -21,7 +20,7 @@ class ExpectColumnValuesToMatchThai(RegexBasedColumnMapExpectation):
 
     # These values will be used to configure the metric created by your expectation
     regex_camel_name = "RegexName"
-    regex = "[\u0E00-\u0E7F]+"
+    regex = "[\u0e00-\u0e7f]+"
     semantic_type_name_plural = None
 
     # These examples will be shown in the public gallery.

diff --git a/...xpectations_experimental/expectations/expect_multicolumn_datetime_difference_in_months.py b/...xpectations_experimental/expectations/expect_multicolumn_datetime_difference_in_months.py
@@ -52,7 +52,6 @@ def date_diff_in_months(row):
 
 # This class defines the Expectation itself
 class ExpectMulticolumnDatetimeDifferenceInMonths(MulticolumnMapExpectation):
-
     """Expect the difference of 2 datetime columns is equal to another column in month.
 
     This means that for each row, we expect end_datetime - start_datetime = gap (in months)

diff --git a/...imental/expectations/expect_multicolumn_datetime_difference_to_be_less_than_two_months.py b/...imental/expectations/expect_multicolumn_datetime_difference_to_be_less_than_two_months.py
@@ -54,7 +54,6 @@ def date_diff_in_months(row):
 class ExpectMulticolumnDatetimeDifferenceToBeLessThanTwoMonths(
     MulticolumnMapExpectation
 ):
-
     """Expect the difference of 2 datetime columns to be less than or equal to 2 months.
 
     This means that for each row, we expect end_datetime - start_datetime <= 2 (in months)

diff --git a/...perimental/expectations/expect_multicolumn_product_values_to_be_equal_to_single_column.py b/...perimental/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.

diff --git a/...eat_expectations_experimental/expectations/expect_multicolumn_sum_values_to_be_between.py b/...eat_expectations_experimental/expectations/expect_multicolumn_sum_values_to_be_between.py
@@ -3,6 +3,7 @@
 For detailed instructions on how to use it, please see:
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_multicolumn_map_expectations
 """
+
 import functools
 import operator
 

diff --git a/...s_experimental/expectations/expect_multicolumn_sum_values_to_be_equal_to_single_column.py b/...s_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

diff --git a/...ions_experimental/expectations/expect_queried_column_value_frequency_to_meet_threshold.py b/...ions_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(

diff --git a/...tations_experimental/expectations/expect_query_to_have_no_duplicate_value_combinations.py b/...tations_experimental/expectations/expect_query_to_have_no_duplicate_value_combinations.py
@@ -4,7 +4,6 @@
     https://docs.greatexpectations.io/docs/guides/expectations/creating_custom_expectations/how_to_create_custom_query_expectations
 """
 
-
 from typing import Union
 
 from great_expectations.execution_engine import ExecutionEngine

diff --git a/contrib/experimental/great_expectations_experimental/expectations/expect_value_at_index.py b/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!
         ],