acryl-datahub-cloud 0.3.7.9.1__py3-none-any.whl → 0.3.7.10rc1__py3-none-any.whl

acryl_datahub_cloud/metadata/schema_classes.py

@@ -13056,7 +13056,7 @@ class DataProcessInstanceInputClass(_Aspect):
     
     @property
     def inputs(self) -> List[str]:
-        """Input assets consumed"""
+        """Input datasets to be consumed"""
         return self._inner_dict.get('inputs')  # type: ignore
     
     @inputs.setter
@@ -21313,7 +21313,7 @@ class DataProcessInstanceKeyClass(_Aspect):
 
 
     ASPECT_NAME = 'dataProcessInstanceKey'
-    ASPECT_INFO = {'keyForEntity': 'dataProcessInstance', 'entityCategory': '_unset_', 'entityAspects': ['dataProcessInstanceInput', 'dataProcessInstanceOutput', 'dataProcessInstanceProperties', 'dataProcessInstanceRelationships', 'dataProcessInstanceRunEvent', 'status', 'testResults', 'dataPlatformInstance', 'subTypes', 'container', 'mlTrainingRunProperties', 'lineageFeatures'], 'entityDoc': 'DataProcessInstance represents an instance of a datajob/jobflow run'}
+    ASPECT_INFO = {'keyForEntity': 'dataProcessInstance', 'entityCategory': '_unset_', 'entityAspects': ['dataProcessInstanceInput', 'dataProcessInstanceOutput', 'dataProcessInstanceProperties', 'dataProcessInstanceRelationships', 'dataProcessInstanceRunEvent', 'status', 'testResults', 'lineageFeatures'], 'entityDoc': 'DataProcessInstance represents an instance of a datajob/jobflow run'}
     RECORD_SCHEMA = get_schema_type("com.linkedin.pegasus2avro.metadata.key.DataProcessInstanceKey")
 
     def __init__(self,
@@ -25298,13 +25298,8 @@ class MLModelGroupPropertiesClass(_Aspect):
 
     def __init__(self,
         customProperties: Optional[Dict[str, str]]=None,
-        trainingJobs: Union[None, List[str]]=None,
-        downstreamJobs: Union[None, List[str]]=None,
-        name: Union[None, str]=None,
         description: Union[None, str]=None,
         createdAt: Union[None, int]=None,
-        created: Union[None, "TimeStampClass"]=None,
-        lastModified: Union[None, "TimeStampClass"]=None,
         version: Union[None, "VersionTagClass"]=None,
     ):
         super().__init__()
@@ -25314,24 +25309,14 @@ class MLModelGroupPropertiesClass(_Aspect):
             self.customProperties = dict()
         else:
             self.customProperties = customProperties
-        self.trainingJobs = trainingJobs
-        self.downstreamJobs = downstreamJobs
-        self.name = name
         self.description = description
         self.createdAt = createdAt
-        self.created = created
-        self.lastModified = lastModified
         self.version = version
     
     def _restore_defaults(self) -> None:
         self.customProperties = dict()
-        self.trainingJobs = self.RECORD_SCHEMA.fields_dict["trainingJobs"].default
-        self.downstreamJobs = self.RECORD_SCHEMA.fields_dict["downstreamJobs"].default
-        self.name = self.RECORD_SCHEMA.fields_dict["name"].default
         self.description = self.RECORD_SCHEMA.fields_dict["description"].default
         self.createdAt = self.RECORD_SCHEMA.fields_dict["createdAt"].default
-        self.created = self.RECORD_SCHEMA.fields_dict["created"].default
-        self.lastModified = self.RECORD_SCHEMA.fields_dict["lastModified"].default
         self.version = self.RECORD_SCHEMA.fields_dict["version"].default
     
     
@@ -25345,36 +25330,6 @@ class MLModelGroupPropertiesClass(_Aspect):
         self._inner_dict['customProperties'] = value
     
     
-    @property
-    def trainingJobs(self) -> Union[None, List[str]]:
-        """List of jobs or process instances (if any) used to train the model or group. Visible in Lineage. Note that ML Models can also be specified as the output of a specific Data Process Instances (runs) via the DataProcessInstanceOutputs aspect."""
-        return self._inner_dict.get('trainingJobs')  # type: ignore
-    
-    @trainingJobs.setter
-    def trainingJobs(self, value: Union[None, List[str]]) -> None:
-        self._inner_dict['trainingJobs'] = value
-    
-    
-    @property
-    def downstreamJobs(self) -> Union[None, List[str]]:
-        """List of jobs or process instances (if any) that use the model or group."""
-        return self._inner_dict.get('downstreamJobs')  # type: ignore
-    
-    @downstreamJobs.setter
-    def downstreamJobs(self, value: Union[None, List[str]]) -> None:
-        self._inner_dict['downstreamJobs'] = value
-    
-    
-    @property
-    def name(self) -> Union[None, str]:
-        """Display name of the MLModelGroup"""
-        return self._inner_dict.get('name')  # type: ignore
-    
-    @name.setter
-    def name(self, value: Union[None, str]) -> None:
-        self._inner_dict['name'] = value
-    
-    
     @property
     def description(self) -> Union[None, str]:
         """Documentation of the MLModelGroup"""
@@ -25395,26 +25350,6 @@ class MLModelGroupPropertiesClass(_Aspect):
         self._inner_dict['createdAt'] = value
     
     
-    @property
-    def created(self) -> Union[None, "TimeStampClass"]:
-        """Time and Actor who created the MLModelGroup"""
-        return self._inner_dict.get('created')  # type: ignore
-    
-    @created.setter
-    def created(self, value: Union[None, "TimeStampClass"]) -> None:
-        self._inner_dict['created'] = value
-    
-    
-    @property
-    def lastModified(self) -> Union[None, "TimeStampClass"]:
-        """Date when the MLModelGroup was last modified"""
-        return self._inner_dict.get('lastModified')  # type: ignore
-    
-    @lastModified.setter
-    def lastModified(self, value: Union[None, "TimeStampClass"]) -> None:
-        self._inner_dict['lastModified'] = value
-    
-    
     @property
     def version(self) -> Union[None, "VersionTagClass"]:
         """Version of the MLModelGroup"""
@@ -25436,13 +25371,8 @@ class MLModelPropertiesClass(_Aspect):
     def __init__(self,
         customProperties: Optional[Dict[str, str]]=None,
         externalUrl: Union[None, str]=None,
-        trainingJobs: Union[None, List[str]]=None,
-        downstreamJobs: Union[None, List[str]]=None,
-        name: Union[None, str]=None,
         description: Union[None, str]=None,
         date: Union[None, int]=None,
-        created: Union[None, "TimeStampClass"]=None,
-        lastModified: Union[None, "TimeStampClass"]=None,
         version: Union[None, "VersionTagClass"]=None,
         type: Union[None, str]=None,
         hyperParameters: Union[None, Dict[str, Union[str, int, float, float, bool]]]=None,
@@ -25452,6 +25382,8 @@ class MLModelPropertiesClass(_Aspect):
         mlFeatures: Union[None, List[str]]=None,
         tags: Optional[List[str]]=None,
         deployments: Union[None, List[str]]=None,
+        trainingJobs: Union[None, List[str]]=None,
+        downstreamJobs: Union[None, List[str]]=None,
         groups: Union[None, List[str]]=None,
     ):
         super().__init__()
@@ -25462,13 +25394,8 @@ class MLModelPropertiesClass(_Aspect):
         else:
             self.customProperties = customProperties
         self.externalUrl = externalUrl
-        self.trainingJobs = trainingJobs
-        self.downstreamJobs = downstreamJobs
-        self.name = name
         self.description = description
         self.date = date
-        self.created = created
-        self.lastModified = lastModified
         self.version = version
         self.type = type
         self.hyperParameters = hyperParameters
@@ -25482,18 +25409,15 @@ class MLModelPropertiesClass(_Aspect):
         else:
             self.tags = tags
         self.deployments = deployments
+        self.trainingJobs = trainingJobs
+        self.downstreamJobs = downstreamJobs
         self.groups = groups
     
     def _restore_defaults(self) -> None:
         self.customProperties = dict()
         self.externalUrl = self.RECORD_SCHEMA.fields_dict["externalUrl"].default
-        self.trainingJobs = self.RECORD_SCHEMA.fields_dict["trainingJobs"].default
-        self.downstreamJobs = self.RECORD_SCHEMA.fields_dict["downstreamJobs"].default
-        self.name = self.RECORD_SCHEMA.fields_dict["name"].default
         self.description = self.RECORD_SCHEMA.fields_dict["description"].default
         self.date = self.RECORD_SCHEMA.fields_dict["date"].default
-        self.created = self.RECORD_SCHEMA.fields_dict["created"].default
-        self.lastModified = self.RECORD_SCHEMA.fields_dict["lastModified"].default
         self.version = self.RECORD_SCHEMA.fields_dict["version"].default
         self.type = self.RECORD_SCHEMA.fields_dict["type"].default
         self.hyperParameters = self.RECORD_SCHEMA.fields_dict["hyperParameters"].default
@@ -25503,6 +25427,8 @@ class MLModelPropertiesClass(_Aspect):
         self.mlFeatures = self.RECORD_SCHEMA.fields_dict["mlFeatures"].default
         self.tags = list()
         self.deployments = self.RECORD_SCHEMA.fields_dict["deployments"].default
+        self.trainingJobs = self.RECORD_SCHEMA.fields_dict["trainingJobs"].default
+        self.downstreamJobs = self.RECORD_SCHEMA.fields_dict["downstreamJobs"].default
         self.groups = self.RECORD_SCHEMA.fields_dict["groups"].default
     
     
@@ -25526,36 +25452,6 @@ class MLModelPropertiesClass(_Aspect):
         self._inner_dict['externalUrl'] = value
     
     
-    @property
-    def trainingJobs(self) -> Union[None, List[str]]:
-        """List of jobs or process instances (if any) used to train the model or group. Visible in Lineage. Note that ML Models can also be specified as the output of a specific Data Process Instances (runs) via the DataProcessInstanceOutputs aspect."""
-        return self._inner_dict.get('trainingJobs')  # type: ignore
-    
-    @trainingJobs.setter
-    def trainingJobs(self, value: Union[None, List[str]]) -> None:
-        self._inner_dict['trainingJobs'] = value
-    
-    
-    @property
-    def downstreamJobs(self) -> Union[None, List[str]]:
-        """List of jobs or process instances (if any) that use the model or group."""
-        return self._inner_dict.get('downstreamJobs')  # type: ignore
-    
-    @downstreamJobs.setter
-    def downstreamJobs(self, value: Union[None, List[str]]) -> None:
-        self._inner_dict['downstreamJobs'] = value
-    
-    
-    @property
-    def name(self) -> Union[None, str]:
-        """Display name of the MLModel"""
-        return self._inner_dict.get('name')  # type: ignore
-    
-    @name.setter
-    def name(self, value: Union[None, str]) -> None:
-        self._inner_dict['name'] = value
-    
-    
     @property
     def description(self) -> Union[None, str]:
         """Documentation of the MLModel"""
@@ -25576,26 +25472,6 @@ class MLModelPropertiesClass(_Aspect):
         self._inner_dict['date'] = value
     
     
-    @property
-    def created(self) -> Union[None, "TimeStampClass"]:
-        """Audit stamp containing who created this and when"""
-        return self._inner_dict.get('created')  # type: ignore
-    
-    @created.setter
-    def created(self, value: Union[None, "TimeStampClass"]) -> None:
-        self._inner_dict['created'] = value
-    
-    
-    @property
-    def lastModified(self) -> Union[None, "TimeStampClass"]:
-        """Date when the MLModel was last modified"""
-        return self._inner_dict.get('lastModified')  # type: ignore
-    
-    @lastModified.setter
-    def lastModified(self, value: Union[None, "TimeStampClass"]) -> None:
-        self._inner_dict['lastModified'] = value
-    
-    
     @property
     def version(self) -> Union[None, "VersionTagClass"]:
         """Version of the MLModel"""
@@ -25688,6 +25564,26 @@ class MLModelPropertiesClass(_Aspect):
         self._inner_dict['deployments'] = value
     
     
+    @property
+    def trainingJobs(self) -> Union[None, List[str]]:
+        """List of jobs (if any) used to train the model"""
+        return self._inner_dict.get('trainingJobs')  # type: ignore
+    
+    @trainingJobs.setter
+    def trainingJobs(self, value: Union[None, List[str]]) -> None:
+        self._inner_dict['trainingJobs'] = value
+    
+    
+    @property
+    def downstreamJobs(self) -> Union[None, List[str]]:
+        """List of jobs (if any) that use the model"""
+        return self._inner_dict.get('downstreamJobs')  # type: ignore
+    
+    @downstreamJobs.setter
+    def downstreamJobs(self, value: Union[None, List[str]]) -> None:
+        self._inner_dict['downstreamJobs'] = value
+    
+    
     @property
     def groups(self) -> Union[None, List[str]]:
         """Groups the model belongs to"""
@@ -25783,104 +25679,6 @@ class MLPrimaryKeyPropertiesClass(_Aspect):
         self._inner_dict['sources'] = value
     
     
-class MLTrainingRunPropertiesClass(_Aspect):
-    """The inputs and outputs of this training run"""
-
-
-    ASPECT_NAME = 'mlTrainingRunProperties'
-    ASPECT_INFO = {}
-    RECORD_SCHEMA = get_schema_type("com.linkedin.pegasus2avro.ml.metadata.MLTrainingRunProperties")
-
-    def __init__(self,
-        customProperties: Optional[Dict[str, str]]=None,
-        externalUrl: Union[None, str]=None,
-        id: Union[None, str]=None,
-        outputUrls: Union[None, List[str]]=None,
-        hyperParams: Union[None, List["MLHyperParamClass"]]=None,
-        trainingMetrics: Union[None, List["MLMetricClass"]]=None,
-    ):
-        super().__init__()
-        
-        if customProperties is None:
-            # default: {}
-            self.customProperties = dict()
-        else:
-            self.customProperties = customProperties
-        self.externalUrl = externalUrl
-        self.id = id
-        self.outputUrls = outputUrls
-        self.hyperParams = hyperParams
-        self.trainingMetrics = trainingMetrics
-    
-    def _restore_defaults(self) -> None:
-        self.customProperties = dict()
-        self.externalUrl = self.RECORD_SCHEMA.fields_dict["externalUrl"].default
-        self.id = self.RECORD_SCHEMA.fields_dict["id"].default
-        self.outputUrls = self.RECORD_SCHEMA.fields_dict["outputUrls"].default
-        self.hyperParams = self.RECORD_SCHEMA.fields_dict["hyperParams"].default
-        self.trainingMetrics = self.RECORD_SCHEMA.fields_dict["trainingMetrics"].default
-    
-    
-    @property
-    def customProperties(self) -> Dict[str, str]:
-        """Custom property bag."""
-        return self._inner_dict.get('customProperties')  # type: ignore
-    
-    @customProperties.setter
-    def customProperties(self, value: Dict[str, str]) -> None:
-        self._inner_dict['customProperties'] = value
-    
-    
-    @property
-    def externalUrl(self) -> Union[None, str]:
-        """URL where the reference exist"""
-        return self._inner_dict.get('externalUrl')  # type: ignore
-    
-    @externalUrl.setter
-    def externalUrl(self, value: Union[None, str]) -> None:
-        self._inner_dict['externalUrl'] = value
-    
-    
-    @property
-    def id(self) -> Union[None, str]:
-        """Run Id of the ML Training Run"""
-        return self._inner_dict.get('id')  # type: ignore
-    
-    @id.setter
-    def id(self, value: Union[None, str]) -> None:
-        self._inner_dict['id'] = value
-    
-    
-    @property
-    def outputUrls(self) -> Union[None, List[str]]:
-        """List of URLs for the Outputs of the ML Training Run"""
-        return self._inner_dict.get('outputUrls')  # type: ignore
-    
-    @outputUrls.setter
-    def outputUrls(self, value: Union[None, List[str]]) -> None:
-        self._inner_dict['outputUrls'] = value
-    
-    
-    @property
-    def hyperParams(self) -> Union[None, List["MLHyperParamClass"]]:
-        """Hyperparameters of the ML Training Run"""
-        return self._inner_dict.get('hyperParams')  # type: ignore
-    
-    @hyperParams.setter
-    def hyperParams(self, value: Union[None, List["MLHyperParamClass"]]) -> None:
-        self._inner_dict['hyperParams'] = value
-    
-    
-    @property
-    def trainingMetrics(self) -> Union[None, List["MLMetricClass"]]:
-        """Metrics of the ML Training Run"""
-        return self._inner_dict.get('trainingMetrics')  # type: ignore
-    
-    @trainingMetrics.setter
-    def trainingMetrics(self, value: Union[None, List["MLMetricClass"]]) -> None:
-        self._inner_dict['trainingMetrics'] = value
-    
-    
 class MetricsClass(_Aspect):
     """Metrics to be featured for the MLModel."""
 
@@ -35014,7 +34812,6 @@ __SCHEMA_TYPES = {
     'com.linkedin.pegasus2avro.ml.metadata.MLModelGroupProperties': MLModelGroupPropertiesClass,
     'com.linkedin.pegasus2avro.ml.metadata.MLModelProperties': MLModelPropertiesClass,
     'com.linkedin.pegasus2avro.ml.metadata.MLPrimaryKeyProperties': MLPrimaryKeyPropertiesClass,
-    'com.linkedin.pegasus2avro.ml.metadata.MLTrainingRunProperties': MLTrainingRunPropertiesClass,
     'com.linkedin.pegasus2avro.ml.metadata.Metrics': MetricsClass,
     'com.linkedin.pegasus2avro.ml.metadata.QuantitativeAnalyses': QuantitativeAnalysesClass,
     'com.linkedin.pegasus2avro.ml.metadata.SourceCode': SourceCodeClass,
@@ -35675,7 +35472,6 @@ __SCHEMA_TYPES = {
     'MLModelGroupProperties': MLModelGroupPropertiesClass,
     'MLModelProperties': MLModelPropertiesClass,
     'MLPrimaryKeyProperties': MLPrimaryKeyPropertiesClass,
-    'MLTrainingRunProperties': MLTrainingRunPropertiesClass,
     'Metrics': MetricsClass,
     'QuantitativeAnalyses': QuantitativeAnalysesClass,
     'SourceCode': SourceCodeClass,
@@ -35984,7 +35780,6 @@ ASPECT_CLASSES: List[Type[_Aspect]] = [
     MLFeaturePropertiesClass,
     MLPrimaryKeyPropertiesClass,
     MLModelPropertiesClass,
-    MLTrainingRunPropertiesClass,
     EditableMLModelGroupPropertiesClass,
     MLModelDeploymentPropertiesClass,
     EditableMLFeaturePropertiesClass,
@@ -36245,7 +36040,6 @@ class AspectBag(TypedDict, total=False):
     mlFeatureProperties: MLFeaturePropertiesClass
     mlPrimaryKeyProperties: MLPrimaryKeyPropertiesClass
     mlModelProperties: MLModelPropertiesClass
-    mlTrainingRunProperties: MLTrainingRunPropertiesClass
     editableMlModelGroupProperties: EditableMLModelGroupPropertiesClass
     mlModelDeploymentProperties: MLModelDeploymentPropertiesClass
     editableMlFeatureProperties: EditableMLFeaturePropertiesClass

acryl_datahub_cloud/metadata/schemas/DataProcessInstanceInput.avsc

@@ -10,10 +10,8 @@
       "Relationship": {
         "/*": {
           "entityTypes": [
-            "dataset",
-            "mlModel"
+            "dataset"
           ],
-          "isLineage": true,
           "name": "Consumes"
         }
       },
@@ -31,7 +29,7 @@
         "items": "string"
       },
       "name": "inputs",
-      "doc": "Input assets consumed",
+      "doc": "Input datasets to be consumed",
       "Urn": "Urn",
       "urn_is_array": true
     }

acryl_datahub_cloud/metadata/schemas/DataProcessInstanceKey.avsc

@@ -12,10 +12,6 @@
       "dataProcessInstanceRunEvent",
       "status",
       "testResults",
-      "dataPlatformInstance",
-      "subTypes",
-      "container",
-      "mlTrainingRunProperties",
       "lineageFeatures"
     ],
     "entityDoc": "DataProcessInstance represents an instance of a datajob/jobflow run"

acryl_datahub_cloud/metadata/schemas/DataProcessInstanceOutput.avsc

@@ -10,11 +10,8 @@
       "Relationship": {
         "/*": {
           "entityTypes": [
-            "dataset",
-            "mlModel"
+            "dataset"
           ],
-          "isLineage": true,
-          "isUpstream": false,
           "name": "Produces"
         }
       },

acryl_datahub_cloud/metadata/schemas/MLModelGroupProperties.avsc

@@ -21,66 +21,6 @@
       "default": {},
       "doc": "Custom property bag."
     },
-    {
-      "Relationship": {
-        "/*": {
-          "entityTypes": [
-            "dataJob",
-            "dataProcessInstance"
-          ],
-          "isLineage": true,
-          "name": "TrainedBy"
-        }
-      },
-      "type": [
-        "null",
-        {
-          "type": "array",
-          "items": "string"
-        }
-      ],
-      "name": "trainingJobs",
-      "default": null,
-      "doc": "List of jobs or process instances (if any) used to train the model or group. Visible in Lineage. Note that ML Models can also be specified as the output of a specific Data Process Instances (runs) via the DataProcessInstanceOutputs aspect."
-    },
-    {
-      "Relationship": {
-        "/*": {
-          "entityTypes": [
-            "dataJob",
-            "dataProcessInstance"
-          ],
-          "isLineage": true,
-          "isUpstream": false,
-          "name": "UsedBy"
-        }
-      },
-      "type": [
-        "null",
-        {
-          "type": "array",
-          "items": "string"
-        }
-      ],
-      "name": "downstreamJobs",
-      "default": null,
-      "doc": "List of jobs or process instances (if any) that use the model or group."
-    },
-    {
-      "Searchable": {
-        "boostScore": 10.0,
-        "enableAutocomplete": true,
-        "fieldType": "WORD_GRAM",
-        "queryByDefault": true
-      },
-      "type": [
-        "null",
-        "string"
-      ],
-      "name": "name",
-      "default": null,
-      "doc": "Display name of the MLModelGroup"
-    },
     {
       "Searchable": {
         "fieldType": "TEXT",
@@ -95,7 +35,6 @@
       "doc": "Documentation of the MLModelGroup"
     },
     {
-      "deprecated": true,
       "type": [
         "null",
         "long"
@@ -104,49 +43,6 @@
       "default": null,
       "doc": "Date when the MLModelGroup was developed"
     },
-    {
-      "type": [
-        "null",
-        {
-          "type": "record",
-          "name": "TimeStamp",
-          "namespace": "com.linkedin.pegasus2avro.common",
-          "fields": [
-            {
-              "type": "long",
-              "name": "time",
-              "doc": "When did the event occur"
-            },
-            {
-              "java": {
-                "class": "com.linkedin.pegasus2avro.common.urn.Urn"
-              },
-              "type": [
-                "null",
-                "string"
-              ],
-              "name": "actor",
-              "default": null,
-              "doc": "Optional: The actor urn involved in the event.",
-              "Urn": "Urn"
-            }
-          ],
-          "doc": "A standard event timestamp"
-        }
-      ],
-      "name": "created",
-      "default": null,
-      "doc": "Time and Actor who created the MLModelGroup"
-    },
-    {
-      "type": [
-        "null",
-        "com.linkedin.pegasus2avro.common.TimeStamp"
-      ],
-      "name": "lastModified",
-      "default": null,
-      "doc": "Date when the MLModelGroup was last modified"
-    },
     {
       "type": [
         "null",