mlrun 1.7.2__py3-none-any.whl → 1.8.0rc1__py3-none-any.whl

mlrun/model_monitoring/helpers.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 
 import datetime
+import os
 import typing
 
 import numpy as np
@@ -27,7 +28,9 @@ import mlrun.artifacts
 import mlrun.common.model_monitoring.helpers
 import mlrun.common.schemas.model_monitoring.constants as mm_constants
 import mlrun.data_types.infer
+import mlrun.datastore
 import mlrun.model_monitoring
+import mlrun.utils.helpers
 from mlrun.common.schemas.model_monitoring.model_endpoints import (
     ModelEndpointMonitoringMetric,
     _compose_full_name,
@@ -98,7 +101,74 @@ def get_monitoring_parquet_path(
     return parquet_path
 
 
-def get_connection_string(secret_provider: typing.Callable[[str], str] = None) -> str:
+def get_monitoring_stats_directory_path(
+    project: str,
+    kind: str = mm_constants.FileTargetKind.STATS,
+) -> str:
+    """
+    Get model monitoring stats target for the current project and kind. The stats target path is based on the
+    project artifact path. If project artifact path is not defined, the stats target path will be based on MLRun
+    artifact path.
+    :param project:     Project object.
+    :param kind:        indicate the kind of the stats path
+    :return:            Monitoring stats target path.
+    """
+    stats_path = mlrun.mlconf.get_model_monitoring_file_target_path(
+        project=project,
+        kind=kind,
+    )
+    return stats_path
+
+
+def _get_monitoring_current_stats_file_path(project: str, endpoint_id: str) -> str:
+    return os.path.join(
+        get_monitoring_stats_directory_path(project),
+        f"{endpoint_id}_current_stats.json",
+    )
+
+
+def _get_monitoring_drift_measures_file_path(project: str, endpoint_id: str) -> str:
+    return os.path.join(
+        get_monitoring_stats_directory_path(project),
+        f"{endpoint_id}_drift_measures.json",
+    )
+
+
+def get_monitoring_current_stats_data(
+    project: str, endpoint_id: str
+) -> mlrun.datastore.DataItem:
+    """
+    getter for data item of current stats for project and endpoint
+    :param project: project name str
+    :param endpoint_id: endpoint id str
+    :return: DataItem
+    """
+    return mlrun.datastore.store_manager.object(
+        _get_monitoring_current_stats_file_path(
+            project=project, endpoint_id=endpoint_id
+        )
+    )
+
+
+def get_monitoring_drift_measures_data(
+    project: str, endpoint_id: str
+) -> mlrun.datastore.DataItem:
+    """
+    getter for data item of drift measures for project and endpoint
+    :param project: project name str
+    :param endpoint_id: endpoint id str
+    :return: DataItem
+    """
+    return mlrun.datastore.store_manager.object(
+        _get_monitoring_drift_measures_file_path(
+            project=project, endpoint_id=endpoint_id
+        )
+    )
+
+
+def get_connection_string(
+    secret_provider: typing.Optional[typing.Callable[[str], str]] = None,
+) -> str:
     """Get endpoint store connection string from the project secret. If wasn't set, take it from the system
     configurations.
 
@@ -350,3 +420,29 @@ def enrich_model_endpoint_with_model_uri(
     model_endpoint.spec.model_uri = mlrun.datastore.get_store_uri(
         kind=mlrun.utils.helpers.StorePrefix.Model, uri=model_artifact_uri
     )
+
+
+def _get_monitoring_schedules_folder_path(project: str) -> str:
+    return typing.cast(
+        str,
+        mlrun.mlconf.get_model_monitoring_file_target_path(
+            project=project, kind=mm_constants.FileTargetKind.MONITORING_SCHEDULES
+        ),
+    )
+
+
+def _get_monitoring_schedules_file_path(*, project: str, endpoint_id: str) -> str:
+    return os.path.join(
+        _get_monitoring_schedules_folder_path(project), f"{endpoint_id}.json"
+    )
+
+
+def get_monitoring_schedules_data(
+    *, project: str, endpoint_id: str
+) -> mlrun.datastore.DataItem:
+    """
+    Get the model monitoring schedules' data item of the project's model endpoint.
+    """
+    return mlrun.datastore.store_manager.object(
+        _get_monitoring_schedules_file_path(project=project, endpoint_id=endpoint_id)
+    )

mlrun/model_monitoring/model_endpoint.py

@@ -14,7 +14,7 @@
 #
 
 from dataclasses import dataclass, field
-from typing import Any
+from typing import Any, Optional
 
 import mlrun.model
 from mlrun.common.model_monitoring.helpers import FeatureStats
@@ -104,7 +104,9 @@ class ModelEndpoint(mlrun.model.ModelObj):
         )
 
     @classmethod
-    def from_flat_dict(cls, struct=None, fields=None, deprecated_fields: dict = None):
+    def from_flat_dict(
+        cls, struct=None, fields=None, deprecated_fields: Optional[dict] = None
+    ):
         new_obj = cls()
         new_obj._metadata = mlrun.model.VersionedObjMetadata().from_dict(
             struct=struct, fields=fields, deprecated_fields=deprecated_fields

mlrun/model_monitoring/stream_processing.py

@@ -51,7 +51,7 @@ class EventStreamProcessor:
         parquet_target: str,
         aggregate_windows: typing.Optional[list[str]] = None,
         aggregate_period: str = "5m",
-        model_monitoring_access_key: str = None,
+        model_monitoring_access_key: typing.Optional[str] = None,
     ):
         # General configurations, mainly used for the storey steps in the future serving graph
         self.project = project
@@ -85,7 +85,7 @@ class EventStreamProcessor:
         v3io_access_key: typing.Optional[str] = None,
         v3io_framesd: typing.Optional[str] = None,
         v3io_api: typing.Optional[str] = None,
-        model_monitoring_access_key: str = None,
+        model_monitoring_access_key: typing.Optional[str] = None,
     ):
         # Get the V3IO configurations
         self.v3io_framesd = v3io_framesd or mlrun.mlconf.v3io_framesd

mlrun/model_monitoring/tracking_policy.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import warnings
-from typing import Union
+from typing import Optional, Union
 
 import mlrun.common.schemas.schedule
 import mlrun.model
@@ -74,7 +74,9 @@ class TrackingPolicy(mlrun.model.ModelObj):
         self.default_controller_image = default_controller_image
 
     @classmethod
-    def from_dict(cls, struct=None, fields=None, deprecated_fields: dict = None):
+    def from_dict(
+        cls, struct=None, fields=None, deprecated_fields: Optional[dict] = None
+    ):
         new_obj = super().from_dict(
             struct, fields=cls._dict_fields, deprecated_fields=deprecated_fields
         )
@@ -102,7 +104,12 @@ class TrackingPolicy(mlrun.model.ModelObj):
                 )
         return new_obj
 
-    def to_dict(self, fields: list = None, exclude: list = None, strip: bool = False):
+    def to_dict(
+        self,
+        fields: Optional[list] = None,
+        exclude: Optional[list] = None,
+        strip: bool = False,
+    ):
         struct = super().to_dict(
             fields,
             exclude=[

mlrun/model_monitoring/writer.py

@@ -13,7 +13,8 @@
 # limitations under the License.
 
 import json
-from typing import Any, Callable, NewType
+from datetime import datetime, timezone
+from typing import Any, Callable, NewType, Optional
 
 import mlrun.common.model_monitoring
 import mlrun.common.schemas
@@ -26,10 +27,16 @@ from mlrun.common.schemas.model_monitoring.constants import (
     ResultData,
     ResultKindApp,
     ResultStatusApp,
+    StatsData,
+    StatsKind,
     WriterEvent,
     WriterEventKind,
 )
 from mlrun.common.schemas.notification import NotificationKind, NotificationSeverity
+from mlrun.model_monitoring.db._stats import (
+    ModelMonitoringCurrentStatsFile,
+    ModelMonitoringDriftMeasuresFile,
+)
 from mlrun.model_monitoring.helpers import get_result_instance_fqn
 from mlrun.serving.utils import StepToDict
 from mlrun.utils import logger
@@ -105,7 +112,7 @@ class ModelMonitoringWriter(StepToDict):
     def __init__(
         self,
         project: str,
-        secret_provider: Callable = None,
+        secret_provider: Optional[Callable] = None,
     ) -> None:
         self.project = project
         self.name = project  # required for the deployment process
@@ -190,6 +197,8 @@ class ModelMonitoringWriter(StepToDict):
             expected_keys.extend(MetricData.list())
         elif kind == WriterEventKind.RESULT:
             expected_keys.extend(ResultData.list())
+        elif kind == WriterEventKind.STATS:
+            expected_keys.extend(StatsData.list())
         else:
             raise _WriterEventValueError(
                 f"Unknown event kind: {kind}, expected one of: {WriterEventKind.list()}"
@@ -198,16 +207,50 @@ class ModelMonitoringWriter(StepToDict):
         if missing_keys:
             raise _WriterEventValueError(
                 f"The received event misses some keys compared to the expected "
-                f"monitoring application event schema: {missing_keys}"
+                f"monitoring application event schema: {missing_keys} for event kind {kind}"
             )
 
         return result_event, kind
 
+    def write_stats(self, event: _AppResultEvent) -> None:
+        """
+        Write to file the application stats event
+        :param event: application stats event
+        """
+        endpoint_id = event[WriterEvent.ENDPOINT_ID]
+        logger.debug(
+            "Updating the model endpoint with stats",
+            endpoint_id=endpoint_id,
+        )
+        stat_kind = event.get(StatsData.STATS_NAME)
+        data, timestamp_str = event.get(StatsData.STATS), event.get(StatsData.TIMESTAMP)
+        timestamp = datetime.fromisoformat(timestamp_str).astimezone(tz=timezone.utc)
+        if stat_kind == StatsKind.CURRENT_STATS.value:
+            ModelMonitoringCurrentStatsFile(self.project, endpoint_id).write(
+                data, timestamp
+            )
+        elif stat_kind == StatsKind.DRIFT_MEASURES.value:
+            ModelMonitoringDriftMeasuresFile(self.project, endpoint_id).write(
+                data, timestamp
+            )
+        logger.info(
+            "Updating the model endpoint statistics",
+            endpoint_id=endpoint_id,
+            stats_kind=stat_kind,
+        )
+
     def do(self, event: _RawEvent) -> None:
         event, kind = self._reconstruct_event(event)
         logger.info("Starting to write event", event=event)
+        if (
+            kind == WriterEventKind.STATS
+            and event[WriterEvent.APPLICATION_NAME]
+            == HistogramDataDriftApplicationConstants.NAME
+        ):
+            self.write_stats(event)
+            logger.info("Model monitoring writer finished handling event")
+            return
         self._tsdb_connector.write_application_event(event=event.copy(), kind=kind)
-        self._app_result_store.write_application_event(event=event.copy(), kind=kind)
 
         logger.info("Completed event DB writes")
 
@@ -247,26 +290,4 @@ class ModelMonitoringWriter(StepToDict):
                 result_kind=event[ResultData.RESULT_KIND],
             )
 
-        if (
-            kind == WriterEventKind.RESULT
-            and event[WriterEvent.APPLICATION_NAME]
-            == HistogramDataDriftApplicationConstants.NAME
-            and event[ResultData.RESULT_NAME]
-            == HistogramDataDriftApplicationConstants.GENERAL_RESULT_NAME
-        ):
-            endpoint_id = event[WriterEvent.ENDPOINT_ID]
-            logger.info(
-                "Updating the model endpoint with metadata specific to the histogram "
-                "data drift app",
-                endpoint_id=endpoint_id,
-            )
-            attributes = json.loads(event[ResultData.RESULT_EXTRA_DATA])
-            attributes[EventFieldType.DRIFT_STATUS] = str(
-                attributes[EventFieldType.DRIFT_STATUS]
-            )
-            self._app_result_store.update_model_endpoint(
-                endpoint_id=endpoint_id,
-                attributes=attributes,
-            )
-
         logger.info("Model monitoring writer finished handling event")

mlrun/package/__init__.py

@@ -11,14 +11,11 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
-
-# flake8: noqa  - this is until we take care of the F401 violations with respect to __all__ & sphinx
 
 import functools
 import inspect
 from collections import OrderedDict
-from typing import Callable, Union
+from typing import Callable, Optional, Union
 
 from ..config import config
 from .context_handler import ContextHandler
@@ -40,8 +37,8 @@ from .utils import (
 
 
 def handler(
-    labels: dict[str, str] = None,
-    outputs: list[Union[str, dict[str, str]]] = None,
+    labels: Optional[dict[str, str]] = None,
+    outputs: Optional[list[Union[str, dict[str, str]]]] = None,
     inputs: Union[bool, dict[str, Union[str, type]]] = True,
 ):
     """

mlrun/package/context_handler.py

@@ -216,7 +216,7 @@ class ContextHandler:
                     )
             # Link packages:
             self._packagers_manager.link_packages(
-                additional_artifacts=self._context.artifacts,
+                additional_artifact_uris=self._context.artifact_uris,
                 additional_results=self._context.results,
             )
             # Log the packed results and artifacts:

mlrun/package/packager.py

@@ -14,7 +14,7 @@
 #
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 from mlrun.artifacts import Artifact
 from mlrun.datastore import DataItem
@@ -144,9 +144,9 @@ class Packager(ABC):
     def pack(
         self,
         obj: Any,
-        key: str = None,
-        artifact_type: str = None,
-        configurations: dict = None,
+        key: Optional[str] = None,
+        artifact_type: Optional[str] = None,
+        configurations: Optional[dict] = None,
     ) -> Union[tuple[Artifact, dict], dict]:
         """
         Pack an object as the given artifact type using the provided configurations.
@@ -165,8 +165,8 @@ class Packager(ABC):
     def unpack(
         self,
         data_item: DataItem,
-        artifact_type: str = None,
-        instructions: dict = None,
+        artifact_type: Optional[str] = None,
+        instructions: Optional[dict] = None,
     ) -> Any:
         """
         Unpack the data item's artifact by the provided type using the given instructions.
@@ -180,7 +180,10 @@ class Packager(ABC):
         pass
 
     def is_packable(
-        self, obj: Any, artifact_type: str = None, configurations: dict = None
+        self,
+        obj: Any,
+        artifact_type: Optional[str] = None,
+        configurations: Optional[dict] = None,
     ) -> bool:
         """
         Check if this packager can pack an object of the provided type as the provided artifact type.
@@ -212,7 +215,7 @@ class Packager(ABC):
         return True
 
     def is_unpackable(
-        self, data_item: DataItem, type_hint: type, artifact_type: str = None
+        self, data_item: DataItem, type_hint: type, artifact_type: Optional[str] = None
     ) -> bool:
         """
         Check if this packager can unpack an input according to the user-given type hint and the provided artifact type.
@@ -315,7 +318,7 @@ class Packager(ABC):
         )
 
     def get_data_item_local_path(
-        self, data_item: DataItem, add_to_future_clearing_path: bool = None
+        self, data_item: DataItem, add_to_future_clearing_path: Optional[bool] = None
     ) -> str:
         """
         Get the local path to the item handled by the data item provided. The local path can be the same as the data

mlrun/package/packagers/__init__.py

@@ -11,8 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
 
-# flake8: noqa  - this is until we take care of the F401 violations with respect to __all__ & sphinx
 from .default_packager import DefaultPackager
 from .numpy_packagers import NumPySupportedFormat

mlrun/package/packagers/default_packager.py

@@ -15,7 +15,7 @@
 import inspect
 from abc import ABCMeta
 from types import MethodType
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 import docstring_parser
 
@@ -323,9 +323,9 @@ class DefaultPackager(Packager, metaclass=_DefaultPackagerMeta):
     def pack(
         self,
         obj: Any,
-        key: str = None,
-        artifact_type: str = None,
-        configurations: dict = None,
+        key: Optional[str] = None,
+        artifact_type: Optional[str] = None,
+        configurations: Optional[dict] = None,
     ) -> Union[tuple[Artifact, dict], dict]:
         """
         Pack an object as the given artifact type using the provided configurations.
@@ -361,8 +361,8 @@ class DefaultPackager(Packager, metaclass=_DefaultPackagerMeta):
     def unpack(
         self,
         data_item: DataItem,
-        artifact_type: str = None,
-        instructions: dict = None,
+        artifact_type: Optional[str] = None,
+        instructions: Optional[dict] = None,
     ) -> Any:
         """
         Unpack the data item's artifact by the provided type using the given instructions.
@@ -399,7 +399,10 @@ class DefaultPackager(Packager, metaclass=_DefaultPackagerMeta):
         return unpack_method(data_item, **instructions)
 
     def is_packable(
-        self, obj: Any, artifact_type: str = None, configurations: dict = None
+        self,
+        obj: Any,
+        artifact_type: Optional[str] = None,
+        configurations: Optional[dict] = None,
     ) -> bool:
         """
         Check if this packager can pack an object of the provided type as the provided artifact type.
@@ -480,10 +483,10 @@ class DefaultPackager(Packager, metaclass=_DefaultPackagerMeta):
         self,
         data_item: DataItem,
         pickle_module_name: str = DEFAULT_PICKLE_MODULE,
-        object_module_name: str = None,
-        python_version: str = None,
-        pickle_module_version: str = None,
-        object_module_version: str = None,
+        object_module_name: Optional[str] = None,
+        python_version: Optional[str] = None,
+        pickle_module_version: Optional[str] = None,
+        object_module_version: Optional[str] = None,
     ) -> Any:
         """
         Unpack the data item's object, unpickle it using the instructions, and return.

mlrun/package/packagers/numpy_packagers.py

@@ -16,7 +16,7 @@ import os
 import pathlib
 import tempfile
 from abc import ABC, abstractmethod
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -371,7 +371,10 @@ class NumPyNDArrayPackager(DefaultPackager):
         return artifact, {}
 
     def unpack_file(
-        self, data_item: DataItem, file_format: str = None, allow_pickle: bool = False
+        self,
+        data_item: DataItem,
+        file_format: Optional[str] = None,
+        allow_pickle: bool = False,
     ) -> np.ndarray:
         """
         Unpack a numppy array from file.
@@ -474,7 +477,7 @@ class _NumPyNDArrayCollectionPackager(DefaultPackager):
     def unpack_file(
         self,
         data_item: DataItem,
-        file_format: str = None,
+        file_format: Optional[str] = None,
         allow_pickle: bool = False,
     ) -> dict[str, np.ndarray]:
         """
@@ -548,7 +551,10 @@ class NumPyNDArrayDictPackager(_NumPyNDArrayCollectionPackager):
     PACKABLE_OBJECT_TYPE = dict[str, np.ndarray]
 
     def is_packable(
-        self, obj: Any, artifact_type: str = None, configurations: dict = None
+        self,
+        obj: Any,
+        artifact_type: Optional[str] = None,
+        configurations: Optional[dict] = None,
     ) -> bool:
         """
         Check if the object provided is a dictionary of numpy arrays.
@@ -602,7 +608,7 @@ class NumPyNDArrayDictPackager(_NumPyNDArrayCollectionPackager):
     def unpack_file(
         self,
         data_item: DataItem,
-        file_format: str = None,
+        file_format: Optional[str] = None,
         allow_pickle: bool = False,
     ) -> dict[str, np.ndarray]:
         """
@@ -633,7 +639,10 @@ class NumPyNDArrayListPackager(_NumPyNDArrayCollectionPackager):
     PACKABLE_OBJECT_TYPE = list[np.ndarray]
 
     def is_packable(
-        self, obj: Any, artifact_type: str = None, configurations: dict = None
+        self,
+        obj: Any,
+        artifact_type: Optional[str] = None,
+        configurations: Optional[dict] = None,
     ) -> bool:
         """
         Check if the object provided is a list of numpy arrays.
@@ -679,7 +688,7 @@ class NumPyNDArrayListPackager(_NumPyNDArrayCollectionPackager):
     def unpack_file(
         self,
         data_item: DataItem,
-        file_format: str = None,
+        file_format: Optional[str] = None,
         allow_pickle: bool = False,
     ) -> list[np.ndarray]:
         """