[MAINTENANCE] Databricks data type expectation tests #10734
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,164 @@ | ||
| from datetime import datetime, timezone | ||
|
|
||
| import pandas as pd | ||
| import pytest | ||
|
|
||
| from great_expectations.compatibility.sqlalchemy import sqltypes | ||
| from great_expectations.expectations import ( | ||
| ExpectColumnDistinctValuesToContainSet, | ||
| ExpectColumnSumToBeBetween, | ||
| ExpectColumnValuesToBeBetween, | ||
| ExpectColumnValuesToBeInSet, | ||
| ExpectColumnValuesToBeOfType, | ||
| ) | ||
| from tests.integration.test_utils.data_source_config import DatabricksDatasourceTestConfig | ||
| from tests.integration.test_utils.data_source_config.databricks import DatabricksBatchTestSetup | ||
|
|
||
| pytestmark = pytest.mark.databricks | ||
|
|
||
|
|
||
| class TestDatabricksDataTypes: | ||
| """This set of tests ensures that we can run expectations against every data | ||
| type supported by Databricks. | ||
|
|
||
| https://docs.databricks.com/en/sql/language-manual/sql-ref-datatypes.html | ||
| """ | ||
|
|
||
| BOOL_COL_NAME = "my_bool" | ||
| DATE_COL_NAME = "my_date" | ||
| NUMERIC_COL_NAME = "my_number" | ||
| STRING_COL_NAME = "my_string" | ||
|
|
||
| DATA_FRAME = pd.DataFrame( | ||
| { | ||
| BOOL_COL_NAME: [True, False, True, False], | ||
| DATE_COL_NAME: [ | ||
| datetime(2021, 1, 1, tzinfo=timezone.utc).date(), | ||
| datetime(2021, 1, 2, tzinfo=timezone.utc).date(), | ||
| datetime(2021, 1, 3, tzinfo=timezone.utc).date(), | ||
| datetime(2021, 1, 4, tzinfo=timezone.utc).date(), | ||
| ], | ||
| NUMERIC_COL_NAME: [1, 2, 3, 4], | ||
| STRING_COL_NAME: ["a", "b", "c", "d"], | ||
| } | ||
| ) | ||
|
|
||
| @pytest.mark.parametrize( | ||
| "column_type", | ||
| [ | ||
| sqltypes.SMALLINT, | ||
| sqltypes.INT, | ||
| sqltypes.BIGINT, | ||
| sqltypes.DECIMAL, | ||
| sqltypes.FLOAT, | ||
| sqltypes.REAL, | ||
| ], | ||
| ) | ||
| def test_number(self, column_type: sqltypes.TypeEngine): | ||
| batch_setup = DatabricksBatchTestSetup( | ||
| config=DatabricksDatasourceTestConfig( | ||
| column_types={self.NUMERIC_COL_NAME: column_type} | ||
| ), | ||
| data=self.DATA_FRAME, | ||
| extra_data={}, | ||
| ) | ||
| with batch_setup.batch_test_context() as batch: | ||
| result = batch.validate( | ||
| expect=ExpectColumnSumToBeBetween( | ||
| column=self.NUMERIC_COL_NAME, | ||
| min_value=9, | ||
| max_value=11, | ||
| ) | ||
| ) | ||
| assert result.success | ||
|
|
||
| def test_varchar(self): | ||
| column_type = sqltypes.String | ||
| batch_setup = DatabricksBatchTestSetup( | ||
| config=DatabricksDatasourceTestConfig(column_types={self.STRING_COL_NAME: column_type}), | ||
| data=self.DATA_FRAME, | ||
| extra_data={}, | ||
| ) | ||
| with batch_setup.batch_test_context() as batch: | ||
| result = batch.validate( | ||
| expect=ExpectColumnDistinctValuesToContainSet( | ||
| column=self.STRING_COL_NAME, | ||
| value_set=[ | ||
| "a", | ||
| "b", | ||
| ], | ||
| ) | ||
| ) | ||
| assert result.success | ||
|
|
||
| def test_boolean(self): | ||
| column_type = sqltypes.BOOLEAN | ||
| batch_setup = DatabricksBatchTestSetup( | ||
| config=DatabricksDatasourceTestConfig(column_types={self.BOOL_COL_NAME: column_type}), | ||
| data=self.DATA_FRAME, | ||
| extra_data={}, | ||
| ) | ||
| with batch_setup.batch_test_context() as batch: | ||
| result = batch.validate( | ||
| expect=ExpectColumnValuesToBeInSet( | ||
| column=self.BOOL_COL_NAME, value_set=[True, False] | ||
| ) | ||
| ) | ||
| assert result.success | ||
|
|
||
| @pytest.mark.xfail( | ||
| strict=True, | ||
| reason="Expectation fails despite the type_ param being the same as the observed value.", | ||
| ) | ||
| def test_boolean__expect_column_values_to_be_of_type(self): | ||
| column_type = sqltypes.BOOLEAN | ||
| batch_setup = DatabricksBatchTestSetup( | ||
| config=DatabricksDatasourceTestConfig(column_types={self.BOOL_COL_NAME: column_type}), | ||
| data=self.DATA_FRAME, | ||
| extra_data={}, | ||
| ) | ||
| with batch_setup.batch_test_context() as batch: | ||
| result = batch.validate( | ||
| expect=ExpectColumnValuesToBeOfType(column=self.BOOL_COL_NAME, type_="Boolean") | ||
| ) | ||
| assert result.success | ||
|
|
||
| def test_date(self): | ||
| column_type = sqltypes.DATE | ||
| batch_setup = DatabricksBatchTestSetup( | ||
| config=DatabricksDatasourceTestConfig(column_types={self.DATE_COL_NAME: column_type}), | ||
| data=self.DATA_FRAME, | ||
| extra_data={}, | ||
| ) | ||
| with batch_setup.batch_test_context() as batch: | ||
| result = batch.validate( | ||
| expect=ExpectColumnValuesToBeBetween( | ||
| column=self.DATE_COL_NAME, | ||
| min_value=datetime(year=2021, month=1, day=1, tzinfo=timezone.utc).date(), | ||
| max_value=datetime(year=2024, month=1, day=1, tzinfo=timezone.utc).date(), | ||
| ) | ||
| ) | ||
| assert result.success | ||
|
|
||
| @pytest.mark.parametrize( | ||
| "column_type", | ||
| [ | ||
| sqltypes.TIMESTAMP(timezone=False), | ||
| sqltypes.TIMESTAMP(timezone=True), | ||
| ], | ||
| ) | ||
| def test_timestamp(self, column_type: sqltypes.TIMESTAMP): | ||
| batch_setup = DatabricksBatchTestSetup( | ||
| config=DatabricksDatasourceTestConfig(column_types={self.DATE_COL_NAME: column_type}), | ||
| data=self.DATA_FRAME, | ||
| extra_data={}, | ||
| ) | ||
| with batch_setup.batch_test_context() as batch: | ||
| result = batch.validate( | ||
| expect=ExpectColumnValuesToBeBetween( | ||
| column=self.DATE_COL_NAME, | ||
| min_value=datetime(year=2021, month=1, day=1, tzinfo=timezone.utc), | ||
| max_value=datetime(year=2024, month=1, day=1, tzinfo=timezone.utc), | ||
| ) | ||
| ) | ||
| assert result.success | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
is there a ticket for this?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
https://greatexpectations.atlassian.net/browse/CORE-692