Accept step object in dependson list

doc/workflows/pipelines/sagemaker.workflow.pipelines.rst

@@ -5,7 +5,6 @@ ConditionStep
 -------------
 
 .. autoclass:: sagemaker.workflow.condition_step.ConditionStep
-
 .. autoclass:: sagemaker.workflow.condition_step.JsonGet
 
 Conditions

src/sagemaker/workflow/_utils.py

@@ -18,7 +18,7 @@
 import tarfile
 import tempfile
 
-from typing import List
+from typing import List, Union
 
 from sagemaker import image_uris
 from sagemaker.inputs import TrainingInput
@@ -59,7 +59,7 @@ def __init__(
         entry_point: str,
         source_dir: str = None,
         dependencies: List = None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
         **kwargs,
     ):
         """Constructs a TrainingStep, given an `EstimatorBase` instance.
@@ -226,7 +226,7 @@ def __init__(
         image_uri=None,
         compile_model_family=None,
         description=None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
         tags=None,
         **kwargs,
     ):
@@ -255,8 +255,8 @@ def __init__(
             compile_model_family (str): Instance family for compiled model, if specified, a compiled
                 model will be used (default: None).
             description (str): Model Package description (default: None).
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.TrainingStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or instances
+                this step depends on
             **kwargs: additional arguments to `create_model`.
         """
         super(_RegisterModelStep, self).__init__(name, StepTypeEnum.REGISTER_MODEL, depends_on)

src/sagemaker/workflow/callback_step.py

@@ -13,7 +13,7 @@
 """The step definitions for workflow."""
 from __future__ import absolute_import
 
-from typing import List, Dict
+from typing import List, Dict, Union
 from enum import Enum
 
 import attr
@@ -84,7 +84,7 @@ def __init__(
         inputs: dict,
         outputs: List[CallbackOutput],
         cache_config: CacheConfig = None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
     ):
         """Constructs a CallbackStep.
 
@@ -95,8 +95,8 @@ def __init__(
                 in the SQS message body of callback messages.
             outputs (List[CallbackOutput]): Outputs that can be provided when completing a callback.
             cache_config (CacheConfig):  A `sagemaker.workflow.steps.CacheConfig` instance.
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.TransformStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or step instances
+                this `sagemaker.workflow.steps.CallbackStep` depends on
         """
         super(CallbackStep, self).__init__(name, StepTypeEnum.CALLBACK, depends_on)
         self.sqs_queue_url = sqs_queue_url

src/sagemaker/workflow/condition_step.py

@@ -18,6 +18,12 @@
 import attr
 
 from sagemaker.workflow.conditions import Condition
+from sagemaker.workflow.steps import (
+    Step,
+    StepTypeEnum,
+)
+from sagemaker.workflow.step_collections import StepCollection
+from sagemaker.workflow.utilities import list_to_request
 from sagemaker.workflow.entities import (
     Expression,
     RequestType,
@@ -26,12 +32,6 @@
     Properties,
     PropertyFile,
 )
-from sagemaker.workflow.steps import (
-    Step,
-    StepTypeEnum,
-)
-from sagemaker.workflow.step_collections import StepCollection
-from sagemaker.workflow.utilities import list_to_request
 
 
 class ConditionStep(Step):
@@ -40,7 +40,7 @@ class ConditionStep(Step):
     def __init__(
         self,
         name: str,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
         conditions: List[Condition] = None,
         if_steps: List[Union[Step, StepCollection]] = None,
         else_steps: List[Union[Step, StepCollection]] = None,

src/sagemaker/workflow/step_collections.py

@@ -13,7 +13,7 @@
 """The step definitions for workflow."""
 from __future__ import absolute_import
 
-from typing import List
+from typing import List, Union
 
 import attr
 
@@ -60,7 +60,7 @@ def __init__(
         response_types,
         inference_instances,
         transform_instances,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
         model_package_group_name=None,
         model_metrics=None,
         approval_status=None,
@@ -82,8 +82,8 @@ def __init__(
                 generate inferences in real-time (default: None).
             transform_instances (list): A list of the instance types on which a transformation
                 job can be run or on which an endpoint can be deployed (default: None).
-            depends_on (List[str]): The list of step names the first step in the collection
-                depends on
+            depends_on (List[str] or List[Step]): The list of step names or step instances
+                the first step in the collection depends on
             model_package_group_name (str): The Model Package Group name, exclusive to
                 `model_package_name`, using `model_package_group_name` makes the Model Package
                 versioned (default: None).
@@ -179,7 +179,7 @@ def __init__(
         max_payload=None,
         tags=None,
         volume_kms_key=None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
         **kwargs,
     ):
         """Construct steps required for a Transformer step collection:
@@ -216,8 +216,8 @@ def __init__(
                 it will be the format of the batch transform output.
             env (dict): The Environment variables to be set for use during the
                 transform job (default: None).
-            depends_on (List[str]): The list of step names the first step in
-                the collection depends on
+            depends_on (List[str] or List[Step]): The list of step names or step instances
+                the first step in the collection depends on
         """
         steps = []
         if "entry_point" in kwargs:

src/sagemaker/workflow/steps.py

@@ -63,12 +63,13 @@ class Step(Entity):
     Attributes:
         name (str): The name of the step.
         step_type (StepTypeEnum): The type of the step.
-        depends_on (List[str]): The list of step names the current step depends on
+        depends_on (List[str] or List[Step]): The list of step names or step
+            instances the current step depends on
     """
 
     name: str = attr.ib(factory=str)
     step_type: StepTypeEnum = attr.ib(factory=StepTypeEnum.factory)
-    depends_on: List[str] = attr.ib(default=None)
+    depends_on: Union[List[str], List["Step"]] = attr.ib(default=None)
 
     @property
     @abc.abstractmethod
@@ -88,11 +89,13 @@ def to_request(self) -> RequestType:
             "Arguments": self.arguments,
         }
         if self.depends_on:
-            request_dict["DependsOn"] = self.depends_on
+            request_dict["DependsOn"] = self._resolve_depends_on(self.depends_on)
+
         return request_dict
 
-    def add_depends_on(self, step_names: List[str]):
-        """Add step names to the current step depends on list"""
+    def add_depends_on(self, step_names: Union[List[str], List["Step"]]):
+        """Add step names or step instances to the current step depends on list"""
+
         if not step_names:
             return
 
@@ -105,6 +108,19 @@ def ref(self) -> Dict[str, str]:
         """Gets a reference dict for steps"""
         return {"Name": self.name}
 
+    @staticmethod
+    def _resolve_depends_on(depends_on_list: Union[List[str], List["Step"]]):
+        """Resolver the step depends on list"""
+        depends_on = []
+        for step in depends_on_list:
+            if isinstance(step, Step):
+                depends_on.append(step.name)
+            elif isinstance(step, str):
+                depends_on.append(step)
+            else:
+                raise ValueError(f"Invalid input step name: {step}")
+        return depends_on
+
 
 @attr.s
 class CacheConfig:
@@ -147,7 +163,7 @@ def __init__(
         estimator: EstimatorBase,
         inputs: Union[TrainingInput, dict, str, FileSystemInput] = None,
         cache_config: CacheConfig = None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
     ):
         """Construct a TrainingStep, given an `EstimatorBase` instance.
 
@@ -175,8 +191,8 @@ def __init__(
                     the path to the training dataset.
 
             cache_config (CacheConfig):  A `sagemaker.workflow.steps.CacheConfig` instance.
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.TrainingStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or step instances
+                this `sagemaker.workflow.steps.TrainingStep` depends on
         """
         super(TrainingStep, self).__init__(name, StepTypeEnum.TRAINING, depends_on)
         self.estimator = estimator
@@ -221,7 +237,11 @@ class CreateModelStep(Step):
     """CreateModel step for workflow."""
 
     def __init__(
-        self, name: str, model: Model, inputs: CreateModelInput, depends_on: List[str] = None
+        self,
+        name: str,
+        model: Model,
+        inputs: CreateModelInput,
+        depends_on: Union[List[str], List[Step]] = None,
     ):
         """Construct a CreateModelStep, given an `sagemaker.model.Model` instance.
 
@@ -233,8 +253,8 @@ def __init__(
             model (Model): A `sagemaker.model.Model` instance.
             inputs (CreateModelInput): A `sagemaker.inputs.CreateModelInput` instance.
                 Defaults to `None`.
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.CreateModelStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or step instances
+                this `sagemaker.workflow.steps.CreateModelStep` depends on
         """
         super(CreateModelStep, self).__init__(name, StepTypeEnum.CREATE_MODEL, depends_on)
         self.model = model
@@ -279,7 +299,7 @@ def __init__(
         transformer: Transformer,
         inputs: TransformInput,
         cache_config: CacheConfig = None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
     ):
         """Constructs a TransformStep, given an `Transformer` instance.
 
@@ -291,8 +311,8 @@ def __init__(
             transformer (Transformer): A `sagemaker.transformer.Transformer` instance.
             inputs (TransformInput): A `sagemaker.inputs.TransformInput` instance.
             cache_config (CacheConfig):  A `sagemaker.workflow.steps.CacheConfig` instance.
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.TransformStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or step instances
+                this `sagemaker.workflow.steps.TransformStep` depends on
         """
         super(TransformStep, self).__init__(name, StepTypeEnum.TRANSFORM, depends_on)
         self.transformer = transformer
@@ -355,7 +375,7 @@ def __init__(
         code: str = None,
         property_files: List[PropertyFile] = None,
         cache_config: CacheConfig = None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
     ):
         """Construct a ProcessingStep, given a `Processor` instance.
 
@@ -376,8 +396,8 @@ def __init__(
             property_files (List[PropertyFile]): A list of property files that workflow looks
                 for and resolves from the configured processing output list.
             cache_config (CacheConfig):  A `sagemaker.workflow.steps.CacheConfig` instance.
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.ProcessingStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or step instance
+                this `sagemaker.workflow.steps.ProcessingStep` depends on
         """
         super(ProcessingStep, self).__init__(name, StepTypeEnum.PROCESSING, depends_on)
         self.processor = processor
@@ -445,7 +465,7 @@ def __init__(
         inputs=None,
         job_arguments: List[str] = None,
         cache_config: CacheConfig = None,
-        depends_on: List[str] = None,
+        depends_on: Union[List[str], List[Step]] = None,
     ):
         """Construct a TuningStep, given a `HyperparameterTuner` instance.
 
@@ -485,8 +505,8 @@ def __init__(
             job_arguments (List[str]): A list of strings to be passed into the processing job.
                 Defaults to `None`.
             cache_config (CacheConfig):  A `sagemaker.workflow.steps.CacheConfig` instance.
-            depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.ProcessingStep`
-                depends on
+            depends_on (List[str] or List[Step]): A list of step names or step instance
+                this `sagemaker.workflow.steps.ProcessingStep` depends on
         """
         super(TuningStep, self).__init__(name, StepTypeEnum.TUNING, depends_on)
         self.tuner = tuner

tests/integ/test_workflow.py

@@ -1254,7 +1254,7 @@ def test_two_processing_job_depends_on(
 
     step_pyspark_2 = ProcessingStep(
         name="pyspark-process-2",
-        depends_on=[step_pyspark_1.name],
+        depends_on=[step_pyspark_1],
         processor=pyspark_processor,
         inputs=spark_run_args.inputs,
         outputs=spark_run_args.outputs,

tests/unit/sagemaker/workflow/test_steps.py

@@ -49,9 +49,9 @@
     Step,
     StepTypeEnum,
     TrainingStep,
+    TuningStep,
     TransformStep,
     CreateModelStep,
-    TuningStep,
     CacheConfig,
 )
 from tests.unit import DATA_DIR
@@ -497,6 +497,59 @@ def test_properties_describe_processing_job_response():
     }
 
 
+def test_add_depends_on(sagemaker_session):
+    processing_input_data_uri_parameter = ParameterString(
+        name="ProcessingInputDataUri", default_value=f"s3://{BUCKET}/processing_manifest"
+    )
+    instance_type_parameter = ParameterString(name="InstanceType", default_value="ml.m4.4xlarge")
+    instance_count_parameter = ParameterInteger(name="InstanceCount", default_value=1)
+    processor = Processor(
+        image_uri=IMAGE_URI,
+        role=ROLE,
+        instance_count=instance_count_parameter,
+        instance_type=instance_type_parameter,
+        sagemaker_session=sagemaker_session,
+    )
+    inputs = [
+        ProcessingInput(
+            source=processing_input_data_uri_parameter,
+            destination="processing_manifest",
+        )
+    ]
+    cache_config = CacheConfig(enable_caching=True, expire_after="PT1H")
+
+    step_1 = ProcessingStep(
+        name="MyProcessingStep-1",
+        processor=processor,
+        inputs=inputs,
+        outputs=[],
+        cache_config=cache_config,
+    )
+
+    step_2 = ProcessingStep(
+        name="MyProcessingStep-2",
+        depends_on=[step_1],
+        processor=processor,
+        inputs=inputs,
+        outputs=[],
+        cache_config=cache_config,
+    )
+
+    step_3 = ProcessingStep(
+        name="MyProcessingStep-3",
+        depends_on=[step_1],
+        processor=processor,
+        inputs=inputs,
+        outputs=[],
+        cache_config=cache_config,
+    )
+    step_3.add_depends_on([step_2.name])
+
+    assert "DependsOn" not in step_1.to_request()
+    assert step_2.to_request()["DependsOn"] == ["MyProcessingStep-1"]
+    assert step_3.to_request()["DependsOn"] == ["MyProcessingStep-1", "MyProcessingStep-2"]
+
+
 def test_single_algo_tuning_step(sagemaker_session):
     data_source_uri_parameter = ParameterString(
         name="DataSourceS3Uri", default_value=f"s3://{BUCKET}/train_manifest"