acryl-datahub 1.0.0rc18__py3-none-any.whl → 1.3.0.1rc9__py3-none-any.whl

datahub/sdk/main_client.py

@@ -1,16 +1,30 @@
 from __future__ import annotations
 
-from typing import Optional, overload
+from typing import TYPE_CHECKING, Optional, overload
 
 from datahub.errors import SdkUsageError
 from datahub.ingestion.graph.client import DataHubGraph, get_default_graph
-from datahub.ingestion.graph.config import DatahubClientConfig
+from datahub.ingestion.graph.config import ClientMode, DatahubClientConfig
 from datahub.sdk.entity_client import EntityClient
-from datahub.sdk.resolver_client import ResolverClient
+from datahub.sdk.lineage_client import LineageClient
 from datahub.sdk.search_client import SearchClient
 
+if TYPE_CHECKING:
+    from datahub.sdk.resolver_client import ResolverClient
+
 
 class DataHubClient:
+    """Main client for interacting with DataHub.
+
+    This class provides the primary interface for interacting with DataHub,
+    including entity management, search, and resolution capabilities.
+
+    The client can be initialized in three ways:
+    1. With a server URL and optional token
+    2. With a DatahubClientConfig object
+    3. With an existing (legacy) :py:class:`DataHubGraph` instance
+    """
+
     @overload
     def __init__(self, *, server: str, token: Optional[str] = None): ...
     @overload
@@ -25,6 +39,17 @@ class DataHubClient:
         graph: Optional[DataHubGraph] = None,
         config: Optional[DatahubClientConfig] = None,
     ):
+        """Initialize a new DataHubClient instance.
+
+        Args:
+            server: The URL of the DataHub server (e.g. "http://localhost:8080").
+            token: Optional authentication token.
+            graph: An existing DataHubGraph instance to use.
+            config: A DatahubClientConfig object with connection details.
+
+        Raises:
+            SdkUsageError: If invalid combinations of arguments are provided.
+        """
         if server is not None:
             if config is not None:
                 raise SdkUsageError("Cannot specify both server and config")
@@ -40,10 +65,16 @@ class DataHubClient:
 
         self._graph = graph
 
-    # TODO: test connection
+    def test_connection(self) -> None:
+        self._graph.test_connection()
 
     @classmethod
-    def from_env(cls) -> "DataHubClient":
+    def from_env(
+        cls,
+        *,
+        client_mode: ClientMode = ClientMode.SDK,
+        datahub_component: Optional[str] = None,
+    ) -> "DataHubClient":
         """Initialize a DataHubClient from the environment variables or ~/.datahubenv file.
 
         This will first check DATAHUB_GMS_URL and DATAHUB_GMS_TOKEN. If not present,
@@ -53,6 +84,10 @@ class DataHubClient:
         If you're looking to specify the server/token in code, use the
         DataHubClient(server=..., token=...) constructor instead.
 
+        Args:
+            client_mode: [internal] The client mode to use. Defaults to "SDK".
+            datahub_component: [internal] The DataHub component name to include in the user agent.
+
         Returns:
             A DataHubClient instance.
         """
@@ -60,7 +95,10 @@ class DataHubClient:
         # Inspired by the DockerClient.from_env() method.
         # TODO: This one also reads from ~/.datahubenv, so the "from_env" name might be a bit confusing.
         # That file is part of the "environment", but is not a traditional "env variable".
-        graph = get_default_graph()
+        graph = get_default_graph(
+            client_mode=client_mode,
+            datahub_component=datahub_component,
+        )
 
         return cls(graph=graph)
 
@@ -69,11 +107,48 @@ class DataHubClient:
         return EntityClient(self)
 
     @property
-    def resolve(self) -> ResolverClient:
+    def resolve(self) -> "ResolverClient":
+        try:
+            from acryl_datahub_cloud.sdk import (  # type: ignore[import-not-found]
+                ResolverClient,
+            )
+        except ImportError:
+            # If the client is not installed, use the one from the SDK.
+            from datahub.sdk.resolver_client import (  # type: ignore[assignment]
+                ResolverClient,
+            )
         return ResolverClient(self)
 
     @property
     def search(self) -> SearchClient:
         return SearchClient(self)
 
-    # TODO: lineage client
+    @property
+    def lineage(self) -> LineageClient:
+        return LineageClient(self)
+
+    @property
+    def assertions(self):  # type: ignore[report-untyped-call]  # Not available due to circular import issues
+        try:
+            from acryl_datahub_cloud.sdk import AssertionsClient
+        except ImportError as e:
+            if "acryl_datahub_cloud" in str(e):
+                raise SdkUsageError(
+                    "AssertionsClient is not installed, please install it with `pip install acryl-datahub-cloud`"
+                ) from e
+            else:
+                raise e
+        return AssertionsClient(self)
+
+    @property
+    def subscriptions(self):  # type: ignore[report-untyped-call]  # Not available due to circular import issues
+        try:
+            from acryl_datahub_cloud.sdk import SubscriptionClient
+        except ImportError as e:
+            if "acryl_datahub_cloud" in str(e):
+                raise SdkUsageError(
+                    "SubscriptionClient is not installed, please install it with `pip install acryl-datahub-cloud`"
+                ) from e
+            else:
+                raise e
+        return SubscriptionClient(self)

datahub/sdk/mlmodel.py

@@ -0,0 +1,383 @@
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Dict, List, Optional, Sequence, Type, Union
+
+from typing_extensions import Self
+
+from datahub.emitter.mce_builder import DEFAULT_ENV
+from datahub.metadata.schema_classes import (
+    AspectBag,
+    MLHyperParamClass,
+    MLMetricClass,
+    MLModelPropertiesClass,
+)
+from datahub.metadata.urns import (
+    DataProcessInstanceUrn,
+    MlModelGroupUrn,
+    MlModelUrn,
+    Urn,
+)
+from datahub.sdk._shared import (
+    DomainInputType,
+    HasDomain,
+    HasInstitutionalMemory,
+    HasOwnership,
+    HasPlatformInstance,
+    HasStructuredProperties,
+    HasTags,
+    HasTerms,
+    HasVersion,
+    HyperParamsInputType,
+    LinksInputType,
+    MLTrainingJobInputType,
+    OwnersInputType,
+    StructuredPropertyInputType,
+    TagsInputType,
+    TermsInputType,
+    TrainingMetricsInputType,
+    convert_hyper_params,
+    convert_training_metrics,
+    make_time_stamp,
+    parse_time_stamp,
+)
+from datahub.sdk.entity import Entity, ExtraAspectsType
+
+
+class MLModel(
+    HasPlatformInstance,
+    HasOwnership,
+    HasInstitutionalMemory,
+    HasTags,
+    HasTerms,
+    HasDomain,
+    HasVersion,
+    HasStructuredProperties,
+    Entity,
+):
+    __slots__ = ()
+
+    @classmethod
+    def get_urn_type(cls) -> Type[MlModelUrn]:
+        return MlModelUrn
+
+    def __init__(
+        self,
+        id: str,
+        platform: str,
+        version: Optional[str] = None,
+        aliases: Optional[List[str]] = None,
+        platform_instance: Optional[str] = None,
+        env: str = DEFAULT_ENV,
+        name: Optional[str] = None,
+        description: Optional[str] = None,
+        training_metrics: Optional[TrainingMetricsInputType] = None,
+        hyper_params: Optional[HyperParamsInputType] = None,
+        external_url: Optional[str] = None,
+        custom_properties: Optional[Dict[str, str]] = None,
+        created: Optional[datetime] = None,
+        last_modified: Optional[datetime] = None,
+        owners: Optional[OwnersInputType] = None,
+        links: Optional[LinksInputType] = None,
+        tags: Optional[TagsInputType] = None,
+        terms: Optional[TermsInputType] = None,
+        domain: Optional[DomainInputType] = None,
+        model_group: Optional[Union[str, MlModelGroupUrn]] = None,
+        training_jobs: Optional[MLTrainingJobInputType] = None,
+        downstream_jobs: Optional[MLTrainingJobInputType] = None,
+        structured_properties: Optional[StructuredPropertyInputType] = None,
+        extra_aspects: ExtraAspectsType = None,
+    ):
+        urn = MlModelUrn(platform=platform, name=id, env=env)
+        super().__init__(urn)
+        self._set_extra_aspects(extra_aspects)
+        self._set_platform_instance(urn.platform, platform_instance)
+        self._ensure_model_props()
+
+        # Initialize properties in logical groups
+        self._init_basic_properties(
+            version=version,
+            name=name,
+            aliases=aliases,
+            description=description,
+            external_url=external_url,
+            custom_properties=custom_properties,
+            created=created,
+            last_modified=last_modified,
+        )
+
+        self._init_ml_specific_properties(
+            training_metrics=training_metrics,
+            hyper_params=hyper_params,
+            model_group=model_group,
+            training_jobs=training_jobs,
+            downstream_jobs=downstream_jobs,
+        )
+
+        self._init_metadata_properties(
+            owners=owners,
+            links=links,
+            tags=tags,
+            terms=terms,
+            domain=domain,
+            structured_properties=structured_properties,
+        )
+
+    @classmethod
+    def _new_from_graph(cls, urn: Urn, current_aspects: AspectBag) -> Self:
+        assert isinstance(urn, MlModelUrn)
+        entity = cls(
+            id=urn.name,
+            platform=urn.platform,
+            env=urn.env,
+        )
+        return entity._init_from_graph(current_aspects)
+
+    @property
+    def urn(self) -> MlModelUrn:
+        return self._urn  # type: ignore
+
+    def _ensure_model_props(
+        self,
+    ) -> MLModelPropertiesClass:
+        return self._setdefault_aspect(MLModelPropertiesClass())
+
+    @property
+    def name(self) -> Optional[str]:
+        return self._ensure_model_props().name
+
+    def set_name(self, name: str) -> None:
+        self._ensure_model_props().name = name
+
+    @property
+    def description(self) -> Optional[str]:
+        return self._ensure_model_props().description
+
+    def set_description(self, description: str) -> None:
+        self._ensure_model_props().description = description
+
+    @property
+    def external_url(self) -> Optional[str]:
+        return self._ensure_model_props().externalUrl
+
+    def set_external_url(self, external_url: str) -> None:
+        self._ensure_model_props().externalUrl = external_url
+
+    @property
+    def custom_properties(self) -> Optional[Dict[str, str]]:
+        return self._ensure_model_props().customProperties
+
+    def set_custom_properties(self, custom_properties: Dict[str, str]) -> None:
+        self._ensure_model_props().customProperties = custom_properties
+
+    @property
+    def created(self) -> Optional[datetime]:
+        return parse_time_stamp(self._ensure_model_props().created)
+
+    def set_created(self, created: datetime) -> None:
+        self._ensure_model_props().created = make_time_stamp(created)
+
+    @property
+    def last_modified(self) -> Optional[datetime]:
+        return parse_time_stamp(self._ensure_model_props().lastModified)
+
+    def set_last_modified(self, last_modified: datetime) -> None:
+        self._ensure_model_props().lastModified = make_time_stamp(last_modified)
+
+    @property
+    def training_metrics(self) -> Optional[List[MLMetricClass]]:
+        return self._ensure_model_props().trainingMetrics
+
+    def set_training_metrics(self, metrics: TrainingMetricsInputType) -> None:
+        self._ensure_model_props().trainingMetrics = convert_training_metrics(metrics)
+
+    def add_training_metrics(self, metrics: TrainingMetricsInputType) -> None:
+        props = self._ensure_model_props()
+        if props.trainingMetrics is None:
+            props.trainingMetrics = []
+        if isinstance(metrics, list):
+            props.trainingMetrics.extend(
+                [
+                    MLMetricClass(name=metric.name, value=metric.value)
+                    for metric in metrics
+                ]
+            )
+        else:
+            # For dictionary case, use the key as name and value as value
+            for name, value in metrics.items():
+                props.trainingMetrics.append(MLMetricClass(name=name, value=value))
+
+    @property
+    def hyper_params(self) -> Optional[List[MLHyperParamClass]]:
+        return self._ensure_model_props().hyperParams
+
+    def set_hyper_params(self, params: HyperParamsInputType) -> None:
+        self._ensure_model_props().hyperParams = convert_hyper_params(params)
+
+    def add_hyper_params(self, params: HyperParamsInputType) -> None:
+        props = self._ensure_model_props()
+        if props.hyperParams is None:
+            props.hyperParams = []
+        if isinstance(params, list):
+            props.hyperParams.extend(
+                [
+                    MLHyperParamClass(name=param.name, value=param.value)
+                    for param in params
+                ]
+            )
+        else:
+            # For dictionary case, iterate through key-value pairs
+            for name, value in params.items():
+                props.hyperParams.append(MLHyperParamClass(name=name, value=value))
+
+    @property
+    def model_group(self) -> Optional[str]:
+        props = self._ensure_model_props()
+        groups = props.groups
+        if groups is None or len(groups) == 0:
+            return None
+        return groups[0]
+
+    def set_model_group(self, group: Union[str, MlModelGroupUrn]) -> None:
+        self._ensure_model_props().groups = [str(group)]
+
+    @property
+    def training_jobs(self) -> Optional[List[str]]:
+        return self._ensure_model_props().trainingJobs
+
+    def set_training_jobs(self, training_jobs: MLTrainingJobInputType) -> None:
+        self._ensure_model_props().trainingJobs = [str(job) for job in training_jobs]
+
+    def add_training_job(
+        self, training_job: Union[str, DataProcessInstanceUrn]
+    ) -> None:
+        props = self._ensure_model_props()
+        if props.trainingJobs is None:
+            props.trainingJobs = []
+        props.trainingJobs.append(str(training_job))
+
+    def remove_training_job(
+        self, training_job: Union[str, DataProcessInstanceUrn]
+    ) -> None:
+        props = self._ensure_model_props()
+        if props.trainingJobs is not None:
+            job_str = str(training_job)
+            props.trainingJobs = [job for job in props.trainingJobs if job != job_str]
+
+    @property
+    def downstream_jobs(self) -> Optional[List[str]]:
+        return self._ensure_model_props().downstreamJobs
+
+    def set_downstream_jobs(
+        self, downstream_jobs: Sequence[Union[str, DataProcessInstanceUrn]]
+    ) -> None:
+        self._ensure_model_props().downstreamJobs = [
+            str(job) for job in downstream_jobs
+        ]
+
+    def add_downstream_job(
+        self, downstream_job: Union[str, DataProcessInstanceUrn]
+    ) -> None:
+        props = self._ensure_model_props()
+        if props.downstreamJobs is None:
+            props.downstreamJobs = []
+        props.downstreamJobs.append(str(downstream_job))
+
+    def remove_downstream_job(
+        self, downstream_job: Union[str, DataProcessInstanceUrn]
+    ) -> None:
+        props = self._ensure_model_props()
+        if props.downstreamJobs is not None:
+            job_str = str(downstream_job)
+            props.downstreamJobs = [
+                job for job in props.downstreamJobs if job != job_str
+            ]
+
+    @property
+    def deployments(self) -> Optional[List[str]]:
+        return self._ensure_model_props().deployments
+
+    def set_deployments(self, deployments: Sequence[str]) -> None:
+        self._ensure_model_props().deployments = list(deployments)
+
+    def add_deployment(self, deployment: str) -> None:
+        props = self._ensure_model_props()
+        if props.deployments is None:
+            props.deployments = []
+        if deployment not in props.deployments:
+            props.deployments.append(deployment)
+
+    def remove_deployment(self, deployment: str) -> None:
+        props = self._ensure_model_props()
+        if props.deployments is not None:
+            props.deployments = [d for d in props.deployments if d != deployment]
+
+    def _init_basic_properties(
+        self,
+        version: Optional[str] = None,
+        name: Optional[str] = None,
+        aliases: Optional[List[str]] = None,
+        description: Optional[str] = None,
+        external_url: Optional[str] = None,
+        custom_properties: Optional[Dict[str, str]] = None,
+        created: Optional[datetime] = None,
+        last_modified: Optional[datetime] = None,
+    ) -> None:
+        if version is not None:
+            self.set_version(version)
+        if name is not None:
+            self.set_name(name)
+        if aliases is not None:
+            self.set_version_aliases(aliases)
+        if description is not None:
+            self.set_description(description)
+        if external_url is not None:
+            self.set_external_url(external_url)
+        if custom_properties is not None:
+            self.set_custom_properties(custom_properties)
+        if created is not None:
+            self.set_created(created)
+        if last_modified is not None:
+            self.set_last_modified(last_modified)
+
+    def _init_ml_specific_properties(
+        self,
+        training_metrics: Optional[TrainingMetricsInputType] = None,
+        hyper_params: Optional[HyperParamsInputType] = None,
+        model_group: Optional[Union[str, MlModelGroupUrn]] = None,
+        training_jobs: Optional[MLTrainingJobInputType] = None,
+        downstream_jobs: Optional[MLTrainingJobInputType] = None,
+    ) -> None:
+        if training_metrics is not None:
+            self.set_training_metrics(training_metrics)
+        if hyper_params is not None:
+            self.set_hyper_params(hyper_params)
+        if model_group is not None:
+            self.set_model_group(model_group)
+        if training_jobs is not None:
+            self.set_training_jobs(training_jobs)
+        if downstream_jobs is not None:
+            self.set_downstream_jobs(downstream_jobs)
+
+    def _init_metadata_properties(
+        self,
+        owners: Optional[OwnersInputType] = None,
+        links: Optional[LinksInputType] = None,
+        tags: Optional[TagsInputType] = None,
+        terms: Optional[TermsInputType] = None,
+        domain: Optional[DomainInputType] = None,
+        structured_properties: Optional[StructuredPropertyInputType] = None,
+    ) -> None:
+        if owners is not None:
+            self.set_owners(owners)
+        if links is not None:
+            self.set_links(links)
+        if tags is not None:
+            self.set_tags(tags)
+        if terms is not None:
+            self.set_terms(terms)
+        if domain is not None:
+            self.set_domain(domain)
+        if structured_properties is not None:
+            for key, value in structured_properties.items():
+                self.set_structured_property(property_urn=key, values=value)