[MAINTENANCE] refactor to remove rule based profiler

[joshua-stauffer]

remove deprecated code.

[netlify]

✅ Deploy Preview for niobium-lead-7998 canceled.

Name	Link
🔨 Latest commit	b0da768
🔍 Latest deploy log	https://app.netlify.com/sites/niobium-lead-7998/deploys/67d3eb890169410008223c1c

[codecov]

❌ 2 Tests Failed:

Tests completed	Failed	Passed	Skipped
21993	2	21991	5715

View the top 2 failed test(s) by shortest run time

tests.experimental.metric_repository.test_metric_list_metric_retriever_integration::test_get_metrics_full_cdm

Stack Traces | 0.055s run time

cloud_context_and_batch_request_with_simple_dataframe = ({
  "checkpoint_store_name": "default_checkpoint_store",
  "config_version": 4,
  "data_context_id": "12345678-1234-5...-01-02
2                   NaN                   NaN  ...    True 2020-01-03

[3 rows x 6 columns]}, partitioner=None))

    @pytest.mark.cloud
    def test_get_metrics_full_cdm(
        cloud_context_and_batch_request_with_simple_dataframe: tuple[CloudDataContext, BatchRequest],
    ):
        context, batch_request = cloud_context_and_batch_request_with_simple_dataframe
        cdm_metrics_list: List[MetricTypes] = [
            MetricTypes.TABLE_ROW_COUNT,
            MetricTypes.TABLE_COLUMNS,
            MetricTypes.TABLE_COLUMN_TYPES,
            MetricTypes.COLUMN_MIN,
            MetricTypes.COLUMN_MAX,
            MetricTypes.COLUMN_MEAN,
            MetricTypes.COLUMN_MEDIAN,
            MetricTypes.COLUMN_NULL_COUNT,
        ]
        metric_retriever = MetricListMetricRetriever(context)
>       metrics = metric_retriever.get_metrics(
            batch_request=batch_request, metric_list=cdm_metrics_list
        )

.../experimental/metric_repository/test_metric_list_metric_retriever_integration.py:124: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
.../hostedtoolcache/Python/3.9.21....../x64/lib/python3.9.../experimental/metric_repository/metric_list_metric_retriever.py:76: in get_metrics
    numeric_column_names = self._get_numeric_column_names(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <great_expectations.experimental.metric_repository.metric_list_metric_retriever.MetricListMetricRetriever object at 0x7fc44dd4a100>
batch_request = BatchRequest(datasource_name='my_pandas_datasource', data_asset_name='dataframe', options={'dataframe':    numeric_wit...0-01-02
2                   NaN                   NaN  ...    True 2020-01-03

[3 rows x 6 columns]}, partitioner=None)
exclude_column_names = []

    def _get_numeric_column_names(
        self,
        batch_request: BatchRequest,
        exclude_column_names: List[str],
    ) -> list[str]:
        """Get the names of all numeric columns in the batch."""
        table_column_types = self._get_table_column_types(batch_request)
        numeric_column_names = []
        for column_type in table_column_types.value:
>           if column_type.get("type") and column_type["type"].upper() in [
                "FLOAT",
                "INTEGER",
                "NUMERIC",
                "DECIMAL",
            ]:
E           AttributeError: 'numpy.dtypes.Float64DType' object has no attribute 'upper'

.../hostedtoolcache/Python/3.9.21....../x64/lib/python3.9.../experimental/metric_repository/metric_retriever.py:162: AttributeError

tests.experimental.metric_repository.test_metric_list_metric_retriever_integration::test_get_metrics_table_metrics_only

Stack Traces | 0.067s run time

cloud_context_and_batch_request_with_simple_dataframe = ({
  "checkpoint_store_name": "default_checkpoint_store",
  "config_version": 4,
  "data_context_id": "12345678-1234-5...-01-02
2                   NaN                   NaN  ...    True 2020-01-03

[3 rows x 6 columns]}, partitioner=None))

    @pytest.mark.cloud
    def test_get_metrics_table_metrics_only(
        cloud_context_and_batch_request_with_simple_dataframe: tuple[CloudDataContext, BatchRequest],
    ):
        context, batch_request = cloud_context_and_batch_request_with_simple_dataframe
        table_metrics_list: List[MetricTypes] = [
            MetricTypes.TABLE_ROW_COUNT,
            MetricTypes.TABLE_COLUMNS,
            MetricTypes.TABLE_COLUMN_TYPES,
        ]
        metric_retriever = MetricListMetricRetriever(context)
        metrics = metric_retriever.get_metrics(
            batch_request=batch_request, metric_list=table_metrics_list
        )
        validator = context.get_validator(batch_request=batch_request)
        batch_id = validator.active_batch.id
    
        expected_metrics = [
            TableMetric[int](
                batch_id=batch_id,
                metric_name="table.row_count",
                value=3,
                exception=None,
            ),
            TableMetric[List[str]](
                batch_id=batch_id,
                metric_name="table.columns",
                value=[
                    "numeric_with_nulls_1",
                    "numeric_with_nulls_2",
                    "string",
                    "string_with_nulls",
                    "boolean",
                    "datetime",
                ],
                exception=None,
            ),
            TableMetric[List[str]](
                batch_id=batch_id,
                metric_name="table.column_types",
                value=[
                    {"name": "numeric_with_nulls_1", "type": "float64"},
                    {"name": "numeric_with_nulls_2", "type": "float64"},
                    {"name": "string", "type": "object"},
                    {"name": "string_with_nulls", "type": "object"},
                    {"name": "boolean", "type": "bool"},
                    {"name": "datetime", "type": "datetime64[ns]"},
                ],
                exception=None,
            ),
        ]
    
        # Assert each metric so it is easier to see which one fails (instead of assert metrics == expected_metrics):  # noqa: E501 # FIXME CoP
        assert len(metrics) == len(expected_metrics)
        for metric in metrics:
>           assert metric.dict() in [expected_metric.dict() for expected_metric in expected_metrics]
E           AssertionError: assert {'batch_id': 'my_pandas_datasource-dataframe', 'metric_name': 'table.column_types', 'value': [{'name': 'numeric_with_nulls_1', 'type': dtype('float64')}, {'name': 'numeric_with_nulls_2', 'type': dtype('float64')}, {'name': 'string', 'type': dtype('O')}, {'name': 'string_with_nulls', 'type': dtype('O')}, {'name': 'boolean', 'type': dtype('bool')}, {'name': 'datetime', 'type': dtype('<M8[ns]')}], 'exception': None, '__orig_class__': great_expectations.experimental.metric_repository.metrics.TableMetric[list[dict[str, str]]], 'value_type': 'list[dict[str, str]]', 'metric_type': 'TableMetric'} in [{'batch_id': 'my_pandas_datasource-dataframe', 'metric_name': 'table.row_count', 'value': 3, 'exception': None, '__orig_class__': great_expectations.experimental.metric_repository.metrics.TableMetric[int], 'value_type': 'int', 'metric_type': 'TableMetric'}, {'batch_id': 'my_pandas_datasource-dataframe', 'metric_name': 'table.columns', 'value': ['numeric_with_nulls_1', 'numeric_with_nulls_2', 'string', 'string_with_nulls', 'boolean', 'datetime'], 'exception': None, '__orig_class__': great_expectations.experimental.metric_repository.metrics.TableMetric[typing.List[str]], 'value_type': 'typing.List[str]', 'metric_type': 'TableMetric'}, {'batch_id': 'my_pandas_datasource-dataframe', 'metric_name': 'table.column_types', 'value': [{'name': 'numeric_with_nulls_1', 'type': 'float64'}, {'name': 'numeric_with_nulls_2', 'type': 'float64'}, {'name': 'string', 'type': 'object'}, {'name': 'string_with_nulls', 'type': 'object'}, {'name': 'boolean', 'type': 'bool'}, {'name': 'datetime', 'type': 'datetime64[ns]'}], 'exception': None, '__orig_class__': great_expectations.experimental.metric_repository.metrics.TableMetric[typing.List[str]], 'value_type': 'typing.List[str]', 'metric_type': 'TableMetric'}]
E            +  where {'batch_id': 'my_pandas_datasource-dataframe', 'metric_name': 'table.column_types', 'value': [{'name': 'numeric_with_nulls_1', 'type': dtype('float64')}, {'name': 'numeric_with_nulls_2', 'type': dtype('float64')}, {'name': 'string', 'type': dtype('O')}, {'name': 'string_with_nulls', 'type': dtype('O')}, {'name': 'boolean', 'type': dtype('bool')}, {'name': 'datetime', 'type': dtype('<M8[ns]')}], 'exception': None, '__orig_class__': great_expectations.experimental.metric_repository.metrics.TableMetric[list[dict[str, str]]], 'value_type': 'list[dict[str, str]]', 'metric_type': 'TableMetric'} = dict()
E            +    where dict = TableMetric(batch_id='my_pandas_datasource-dataframe', metric_name='table.column_types', value=[{'name': 'numeric_with_nulls_1', 'type': dtype('float64')}, {'name': 'numeric_with_nulls_2', 'type': dtype('float64')}, {'name': 'string', 'type': dtype('O')}, {'name': 'string_with_nulls', 'type': dtype('O')}, {'name': 'boolean', 'type': dtype('bool')}, {'name': 'datetime', 'type': dtype('<M8[ns]')}], exception=None).dict

.../experimental/metric_repository/test_metric_list_metric_retriever_integration.py:105: AssertionError

To view more test analytics, go to the Test Analytics Dashboard
_{📋 Got 3 mins? Take this short survey to help us improve Test Analytics.}