openmetadata-ingestion 1.3.4.0__py3-none-any.whl → 1.4.0.0rc2__py3-none-any.whl

metadata/profiler/interface/pandas/profiler_interface.py

@@ -22,7 +22,11 @@ from typing import Dict, List, Optional
 
 from sqlalchemy import Column
 
-from metadata.generated.schema.entity.data.table import CustomMetricProfile, TableData
+from metadata.generated.schema.entity.data.table import (
+    CustomMetricProfile,
+    DataType,
+    TableData,
+)
 from metadata.generated.schema.entity.services.connections.database.datalakeConnection import (
     DatalakeConnection,
 )
@@ -32,12 +36,9 @@ from metadata.profiler.api.models import ThreadPoolMetrics
 from metadata.profiler.interface.profiler_interface import ProfilerInterface
 from metadata.profiler.metrics.core import MetricTypes
 from metadata.profiler.metrics.registry import Metrics
-from metadata.readers.dataframe.models import DatalakeTableSchemaWrapper
+from metadata.profiler.processor.metric_filter import MetricFilter
 from metadata.utils.constants import COMPLEX_COLUMN_SEPARATOR, SAMPLE_DATA_DEFAULT_COUNT
-from metadata.utils.datalake.datalake_utils import (
-    GenericDataFrameColumnParser,
-    fetch_dataframe,
-)
+from metadata.utils.datalake.datalake_utils import GenericDataFrameColumnParser
 from metadata.utils.logger import profiler_interface_registry_logger
 from metadata.utils.sqa_like_column import SQALikeColumn
 
@@ -85,29 +86,48 @@ class PandasProfilerInterface(ProfilerInterface, PandasInterfaceMixin):
         )
 
         self.client = self.connection.client
-        self.dfs = self._convert_table_to_list_of_dataframe_objects()
+        self.dfs = self.return_ometa_dataframes_sampled(
+            service_connection_config=self.service_connection_config,
+            client=self.client,
+            table=self.table_entity,
+            profile_sample_config=profile_sample_config,
+        )
         self.sampler = self._get_sampler()
-        self.complex_dataframe_sample = deepcopy(self.sampler.random_sample())
-
-    def _convert_table_to_list_of_dataframe_objects(self):
-        """From a table entity, return the corresponding dataframe object
+        self.complex_dataframe_sample = deepcopy(
+            self.sampler.random_sample(is_sampled=True)
+        )
+        self.complex_df()
 
-        Returns:
-            List[DataFrame]
-        """
-        data = fetch_dataframe(
-            config_source=self.service_connection_config.configSource,
-            client=self.client,
-            file_fqn=DatalakeTableSchemaWrapper(
-                key=self.table_entity.name.__root__,
-                bucket_name=self.table_entity.databaseSchema.name,
-                file_extension=self.table_entity.fileFormat,
-            ),
+    def complex_df(self):
+        """Assign DataTypes to dataframe columns as per the parsed column type"""
+        coltype_mapping_df = []
+        data_formats = (
+            GenericDataFrameColumnParser._data_formats  # pylint: disable=protected-access
         )
+        for index, df in enumerate(self.complex_dataframe_sample):
+            if index == 0:
+                for col in self.table.columns:
+                    coltype = next(
+                        (
+                            key
+                            for key, value in data_formats.items()
+                            if col.dataType == value
+                        ),
+                        None,
+                    )
+                    if coltype and col.dataType not in {DataType.JSON, DataType.ARRAY}:
+                        coltype_mapping_df.append(coltype)
+                    else:
+                        coltype_mapping_df.append("object")
 
-        if not data:
-            raise TypeError(f"Couldn't fetch {self.table_entity.name.__root__}")
-        return data
+            try:
+                self.complex_dataframe_sample[index] = df.astype(
+                    dict(zip(df.keys(), coltype_mapping_df))
+                )
+            except (TypeError, ValueError) as err:
+                self.complex_dataframe_sample[index] = df
+                logger.warning(f"NaN/NoneType found in the Dataframe: {err}")
+                break
 
     def _get_sampler(self):
         """Get dataframe sampler from config"""
@@ -171,19 +191,19 @@ class PandasProfilerInterface(ProfilerInterface, PandasInterfaceMixin):
         """
         import pandas as pd  # pylint: disable=import-outside-toplevel
 
+        row_dict = {}
         try:
-            row_dict = {}
             for metric in metrics:
                 metric_resp = metric(column).df_fn(runner)
                 row_dict[metric.name()] = (
                     None if pd.isnull(metric_resp) else metric_resp
                 )
-            return row_dict
         except Exception as exc:
             logger.debug(
                 f"{traceback.format_exc()}\nError trying to compute profile for {exc}"
             )
             raise RuntimeError(exc)
+        return row_dict
 
     def _compute_query_metrics(
         self,
@@ -283,7 +303,7 @@ class PandasProfilerInterface(ProfilerInterface, PandasInterfaceMixin):
         metric_func: ThreadPoolMetrics,
     ):
         """Run metrics in processor worker"""
-        logger.debug(f"Running profiler for {metric_func.table}")
+        logger.debug(f"Running profiler for {metric_func.table.name.__root__}")
         try:
             row = None
             if self.complex_dataframe_sample:
@@ -360,13 +380,14 @@ class PandasProfilerInterface(ProfilerInterface, PandasInterfaceMixin):
 
     def get_all_metrics(
         self,
-        metric_funcs: list,
+        metric_funcs: List[ThreadPoolMetrics],
     ):
         """get all profiler metrics"""
 
         profile_results = {"table": {}, "columns": defaultdict(dict)}
         metric_list = [
-            self.compute_metrics(metric_func) for metric_func in metric_funcs
+            self.compute_metrics(metric_func)
+            for metric_func in MetricFilter.filter_empty_metrics(metric_funcs)
         ]
         for metric_result in metric_list:
             profile, column, metric_type = metric_result

metadata/profiler/interface/profiler_interface.py

@@ -425,8 +425,12 @@ class ProfilerInterface(ABC):
         runner,
         *args,
         **kwargs,
-    ):
-        """Get metrics"""
+    ) -> Dict[str, Any]:
+        """Get metrics
+        Return:
+            Dict[str, Any]: dict of metrics tio be merged into the final column profile. Keys need to be compatible with
+            the `metadata.generated.schema.entity.data.table.ColumnProfile` schema.
+        """
         raise NotImplementedError
 
     @abstractmethod

metadata/profiler/interface/profiler_interface_factory.py

@@ -27,9 +27,15 @@ from metadata.generated.schema.entity.services.connections.database.datalakeConn
 from metadata.generated.schema.entity.services.connections.database.db2Connection import (
     Db2Connection,
 )
+from metadata.generated.schema.entity.services.connections.database.dynamoDBConnection import (
+    DynamoDBConnection,
+)
 from metadata.generated.schema.entity.services.connections.database.mariaDBConnection import (
     MariaDBConnection,
 )
+from metadata.generated.schema.entity.services.connections.database.mongoDBConnection import (
+    MongoDBConnection,
+)
 from metadata.generated.schema.entity.services.connections.database.singleStoreConnection import (
     SingleStoreConnection,
 )
@@ -43,6 +49,8 @@ from metadata.generated.schema.entity.services.connections.database.unityCatalog
     UnityCatalogConnection,
 )
 from metadata.generated.schema.entity.services.databaseService import DatabaseConnection
+from metadata.profiler.factory import Factory
+from metadata.profiler.interface.nosql.profiler_interface import NoSQLProfilerInterface
 from metadata.profiler.interface.pandas.profiler_interface import (
     PandasProfilerInterface,
 )
@@ -76,27 +84,7 @@ from metadata.profiler.interface.sqlalchemy.unity_catalog.profiler_interface imp
 )
 
 
-class ProfilerInterfaceFactory:
-    """Creational factory for profiler interface objects"""
-
-    def __init__(self):
-        self._interface_type = {}
-
-    def register(self, interface_type: str, interface_class):
-        """Register a new interface"""
-        self._interface_type[interface_type] = interface_class
-
-    def register_many(self, interface_dict):
-        """
-        Registers multiple profiler interfaces at once.
-
-        Args:
-            interface_dict: A dictionary mapping connection class names (strings) to their
-            corresponding profiler interface classes.
-        """
-        for interface_type, interface_class in interface_dict.items():
-            self.register(interface_type, interface_class)
-
+class ProfilerInterfaceFactory(Factory):
     def create(self, interface_type: str, *args, **kwargs):
         """Create interface object based on interface type"""
         interface_class = self._interface_type.get(interface_type)
@@ -118,6 +106,7 @@ profilers = {
     UnityCatalogConnection.__name__: UnityCatalogProfilerInterface,
     DatabricksConnection.__name__: DatabricksProfilerInterface,
     Db2Connection.__name__: DB2ProfilerInterface,
+    MongoDBConnection.__name__: NoSQLProfilerInterface,
+    DynamoDBConnection.__name__: NoSQLProfilerInterface,
 }
-
 profiler_interface_factory.register_many(profilers)

metadata/profiler/interface/sqlalchemy/databricks/profiler_interface.py

@@ -13,14 +13,91 @@
 Interfaces with database for all database engine
 supporting sqlalchemy abstraction layer
 """
+from typing import List
 
+from pyhive.sqlalchemy_hive import HiveCompiler
+from sqlalchemy import Column, inspect
 
+from metadata.generated.schema.entity.data.table import Column as OMColumn
+from metadata.generated.schema.entity.data.table import ColumnName, DataType, TableData
+from metadata.generated.schema.entity.services.databaseService import (
+    DatabaseServiceType,
+)
 from metadata.profiler.interface.sqlalchemy.profiler_interface import (
     SQAProfilerInterface,
 )
+from metadata.profiler.orm.converter.base import build_orm_col
 
 
 class DatabricksProfilerInterface(SQAProfilerInterface):
+    """Databricks profiler interface"""
+
+    def visit_column(self, *args, **kwargs):
+        result = super(  # pylint: disable=bad-super-call
+            HiveCompiler, self
+        ).visit_column(*args, **kwargs)
+        dot_count = result.count(".")
+        # Here the databricks uses HiveCompiler.
+        # the `result` here would be `db.schema.table` or `db.schema.table.column`
+        # for struct it will be `db.schema.table.column.nestedchild.nestedchild` etc
+        # the logic is to add the backticks to nested children.
+        if dot_count > 2:
+            splitted_result = result.split(".", 2)[-1].split(".")
+            result = ".".join(result.split(".", 2)[:-1])
+            result += "." + "`.`".join(splitted_result)
+        return result
+
     def __init__(self, service_connection_config, **kwargs):
         super().__init__(service_connection_config=service_connection_config, **kwargs)
         self.set_catalog(self.session)
+        HiveCompiler.visit_column = DatabricksProfilerInterface.visit_column
+
+    def _get_struct_columns(self, columns: List[OMColumn], parent: str):
+        """Get struct columns"""
+
+        columns_list = []
+        for idx, col in enumerate(columns):
+            if col.dataType != DataType.STRUCT:
+                col.name = ColumnName(__root__=f"{parent}.{col.name.__root__}")
+                col = build_orm_col(idx, col, DatabaseServiceType.Databricks)
+                col._set_parent(  # pylint: disable=protected-access
+                    self.table.__table__
+                )
+                columns_list.append(col)
+            else:
+                col = self._get_struct_columns(
+                    col.children, f"{parent}.{col.name.__root__}"
+                )
+                columns_list.extend(col)
+        return columns_list
+
+    def get_columns(self) -> Column:
+        """Get columns from table"""
+        columns = []
+        for idx, column in enumerate(self.table_entity.columns):
+            if column.dataType == DataType.STRUCT:
+                columns.extend(
+                    self._get_struct_columns(column.children, column.name.__root__)
+                )
+            else:
+                col = build_orm_col(idx, column, DatabaseServiceType.Databricks)
+                col._set_parent(  # pylint: disable=protected-access
+                    self.table.__table__
+                )
+                columns.append(col)
+        return columns
+
+    def fetch_sample_data(self, table, columns) -> TableData:
+        """Fetch sample data from database
+
+        Args:
+            table: ORM declarative table
+
+        Returns:
+            TableData: sample table data
+        """
+        sampler = self._get_sampler(
+            table=table,
+        )
+
+        return sampler.fetch_sample_data(list(inspect(self.table).c))

metadata/profiler/interface/sqlalchemy/profiler_interface.py

@@ -39,6 +39,7 @@ from metadata.profiler.metrics.static.stddev import StdDev
 from metadata.profiler.metrics.static.sum import Sum
 from metadata.profiler.orm.functions.table_metric_computer import TableMetricComputer
 from metadata.profiler.orm.registry import Dialects
+from metadata.profiler.processor.metric_filter import MetricFilter
 from metadata.profiler.processor.runner import QueryRunner
 from metadata.utils.constants import SAMPLE_DATA_DEFAULT_COUNT
 from metadata.utils.custom_thread_pool import CustomThreadPoolExecutor
@@ -480,7 +481,7 @@ class SQAProfilerInterface(ProfilerInterface, SQAInterfaceMixin):
                     self.compute_metrics_in_thread,
                     metric_func,
                 )
-                for metric_func in metric_funcs
+                for metric_func in MetricFilter.filter_empty_metrics(metric_funcs)
             ]
 
             for future in futures:

metadata/profiler/interface/sqlalchemy/unity_catalog/profiler_interface.py

@@ -18,15 +18,12 @@ supporting sqlalchemy abstraction layer
 from metadata.ingestion.source.database.databricks.connection import (
     get_connection as databricks_get_connection,
 )
-from metadata.profiler.interface.sqlalchemy.profiler_interface import (
-    SQAProfilerInterface,
+from metadata.profiler.interface.sqlalchemy.databricks.profiler_interface import (
+    DatabricksProfilerInterface,
 )
 
 
-class UnityCatalogProfilerInterface(SQAProfilerInterface):
-    def __init__(self, service_connection_config, **kwargs):
-        super().__init__(service_connection_config=service_connection_config, **kwargs)
-
+class UnityCatalogProfilerInterface(DatabricksProfilerInterface):
     def create_session(self):
         self.connection = databricks_get_connection(self.service_connection_config)
         super().create_session()

metadata/profiler/metrics/composed/distinct_ratio.py

@@ -16,6 +16,7 @@ Distinct Ratio Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.count import Count
 from metadata.profiler.metrics.static.distinct_count import DistinctCount
@@ -29,7 +30,7 @@ class DistinctRatio(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "distinctProportion"
+        return MetricType.distinctProportion.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/composed/duplicate_count.py

@@ -16,6 +16,7 @@ Count Duplicates Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.count import Count
 from metadata.profiler.metrics.static.distinct_count import DistinctCount
@@ -29,7 +30,7 @@ class DuplicateCount(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "duplicateCount"
+        return MetricType.duplicateCount.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/composed/ilike_ratio.py

@@ -16,6 +16,7 @@ ILIKE Ratio Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.count import Count
 from metadata.profiler.metrics.static.ilike_count import ILikeCount
@@ -29,7 +30,7 @@ class ILikeRatio(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "iLikeRatio"
+        return MetricType.iLikeRatio.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/composed/iqr.py

@@ -16,6 +16,7 @@ Inter Quartile Range Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.window.first_quartile import FirstQuartile
 from metadata.profiler.metrics.window.third_quartile import ThirdQuartile
@@ -28,7 +29,7 @@ class InterQuartileRange(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "interQuartileRange"
+        return MetricType.interQuartileRange.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/composed/like_ratio.py

@@ -16,6 +16,7 @@ LIKE Ratio Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.count import Count
 from metadata.profiler.metrics.static.like_count import LikeCount
@@ -29,7 +30,7 @@ class LikeRatio(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "likeRatio"
+        return MetricType.likeRatio.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/composed/non_parametric_skew.py

@@ -16,6 +16,7 @@ Non Parametric Skew definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.mean import Mean
 from metadata.profiler.metrics.static.stddev import StdDev
@@ -29,7 +30,7 @@ class NonParametricSkew(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "nonParametricSkew"
+        return MetricType.nonParametricSkew.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/composed/null_ratio.py

@@ -16,6 +16,7 @@ Null Ratio Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.count import Count
 from metadata.profiler.metrics.static.null_count import NullCount
@@ -29,7 +30,7 @@ class NullRatio(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "nullProportion"
+        return MetricType.nullProportion.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:
@@ -48,10 +49,12 @@ class NullRatio(ComposedMetric):
         Safely compute null ratio based on the profiler
         results of other Metrics
         """
+        import pandas as pd
+
         res_count = res.get(Count.name())
         res_null = res.get(NullCount.name())
 
-        if res_count is not None and res_null is not None:
-            return res_null / (res_null + res_count)
-
+        if not pd.isnull(res_count) and not pd.isnull(res_null):
+            result = res_null / (res_null + res_count)
+            return None if pd.isnull(result) else result
         return None

metadata/profiler/metrics/composed/unique_ratio.py

@@ -16,6 +16,7 @@ Unique Ratio Composed Metric definition
 
 from typing import Any, Dict, Optional, Tuple
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import ComposedMetric
 from metadata.profiler.metrics.static.count import Count
 from metadata.profiler.metrics.static.unique_count import UniqueCount
@@ -29,7 +30,7 @@ class UniqueRatio(ComposedMetric):
 
     @classmethod
     def name(cls):
-        return "uniqueProportion"
+        return MetricType.uniqueProportion.value
 
     @classmethod
     def required_metrics(cls) -> Tuple[str, ...]:

metadata/profiler/metrics/core.py

@@ -18,11 +18,14 @@ Metric Core definitions
 from abc import ABC, abstractmethod
 from enum import Enum
 from functools import wraps
-from typing import Any, Dict, Optional, Tuple, TypeVar
+from typing import Any, Callable, Dict, Optional, Tuple, TypeVar
 
 from sqlalchemy import Column
 from sqlalchemy.orm import DeclarativeMeta, Session
 
+from metadata.generated.schema.entity.data.table import Table
+from metadata.profiler.adaptors.nosql_adaptor import NoSQLAdaptor
+
 # When creating complex metrics, use inherit_cache = CACHE
 CACHE = True
 
@@ -87,6 +90,9 @@ def add_props(**kwargs):
     return inner
 
 
+T = TypeVar("T")
+
+
 class Metric(ABC):
     """
     Parent class metric
@@ -153,6 +159,13 @@ class Metric(ABC):
         """
         return self.col.type.python_type if self.col else None
 
+    def nosql_fn(self, client: NoSQLAdaptor) -> Callable[[Table], Optional[T]]:
+        """
+        Return the function to be used for NoSQL clients to calculate the metric.
+        By default, returns a "do nothing" function that returns None.
+        """
+        return lambda table: None
+
 
 TMetric = TypeVar("TMetric", bound=Metric)
 

metadata/profiler/metrics/hybrid/histogram.py

@@ -18,6 +18,7 @@ from typing import Any, Dict, List, Optional, Union, cast
 from sqlalchemy import and_, case, column, func
 from sqlalchemy.orm import DeclarativeMeta, Session
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.composed.iqr import InterQuartileRange
 from metadata.profiler.metrics.core import HybridMetric
 from metadata.profiler.metrics.static.count import Count
@@ -44,7 +45,7 @@ class Histogram(HybridMetric):
 
     @classmethod
     def name(cls):
-        return "histogram"
+        return MetricType.histogram.value
 
     @property
     def metric_type(self):

metadata/profiler/metrics/registry.py

@@ -42,6 +42,7 @@ from metadata.profiler.metrics.static.min_length import MinLength
 from metadata.profiler.metrics.static.not_like_count import NotLikeCount
 from metadata.profiler.metrics.static.not_regexp_match_count import NotRegexCount
 from metadata.profiler.metrics.static.null_count import NullCount
+from metadata.profiler.metrics.static.null_missing_count import NullMissingCount
 from metadata.profiler.metrics.static.regexp_match_count import RegexCount
 from metadata.profiler.metrics.static.row_count import RowCount
 from metadata.profiler.metrics.static.stddev import StdDev
@@ -103,3 +104,6 @@ class Metrics(MetricRegistry):
 
     # Hybrid Metrics
     HISTOGRAM = Histogram
+
+    # Missing Count
+    NULL_MISSING_COUNT = NullMissingCount

metadata/profiler/metrics/static/column_count.py

@@ -21,6 +21,7 @@ from sqlalchemy.ext.compiler import compiles
 from sqlalchemy.orm import DeclarativeMeta
 from sqlalchemy.sql.functions import FunctionElement
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import CACHE, StaticMetric, _label
 from metadata.profiler.orm.registry import Dialects
 
@@ -60,7 +61,7 @@ class ColumnCount(StaticMetric):
 
     @classmethod
     def name(cls):
-        return "columnCount"
+        return MetricType.columnCount.value
 
     @classmethod
     def is_col_metric(cls) -> bool:

metadata/profiler/metrics/static/column_names.py

@@ -21,6 +21,7 @@ from sqlalchemy.ext.compiler import compiles
 from sqlalchemy.orm import DeclarativeMeta
 from sqlalchemy.sql.functions import FunctionElement
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import CACHE, StaticMetric, _label
 from metadata.profiler.orm.registry import Dialects
 
@@ -60,7 +61,7 @@ class ColumnNames(StaticMetric):
 
     @classmethod
     def name(cls):
-        return "columnNames"
+        return MetricType.columnNames.value
 
     @classmethod
     def is_col_metric(cls) -> bool:

metadata/profiler/metrics/static/count.py

@@ -17,6 +17,7 @@ Count Metric definition
 
 from sqlalchemy import column, func
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import StaticMetric, _label
 from metadata.profiler.orm.functions.count import CountFn
 from metadata.utils.logger import profiler_logger
@@ -33,7 +34,7 @@ class Count(StaticMetric):
 
     @classmethod
     def name(cls):
-        return "valuesCount"
+        return MetricType.valuesCount.value
 
     @property
     def metric_type(self):

metadata/profiler/metrics/static/count_in_set.py

@@ -18,6 +18,7 @@ from typing import List
 
 from sqlalchemy import case, column
 
+from metadata.generated.schema.configuration.profilerConfiguration import MetricType
 from metadata.profiler.metrics.core import StaticMetric, _label
 from metadata.profiler.orm.functions.sum import SumFn
 from metadata.utils.logger import profiler_logger
@@ -40,7 +41,7 @@ class CountInSet(StaticMetric):
 
     @classmethod
     def name(cls):
-        return "countInSet"
+        return MetricType.countInSet.value
 
     @property
     def metric_type(self):