Merge branch 'master' into feat/jumpstart-model-table-update

Author: shreyapandit

CHANGELOG.md

@@ -1,5 +1,26 @@
 # Changelog
 
+## v2.88.1 (2022-04-27)
+
+### Bug Fixes and Other Changes
+
+ * Add encryption setting to tar_and_upload_dir method
+
+## v2.88.0 (2022-04-26)
+
+### Features
+
+ * jumpstart notebook utils -- list model ids, scripts, tasks, frameworks
+
+### Bug Fixes and Other Changes
+
+ * local mode printing of credentials during docker login closes #2180
+ * disable endpoint context test
+
+### Documentation Changes
+
+ * sm model parallel 1.8.0 release notes
+
 ## v2.87.0 (2022-04-20)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.87.1.dev0
+2.88.2.dev0

src/sagemaker/amazon/amazon_estimator.py

@@ -27,6 +27,7 @@
 from sagemaker.estimator import EstimatorBase, _TrainingJob
 from sagemaker.inputs import FileSystemInput, TrainingInput
 from sagemaker.utils import sagemaker_timestamp
+from sagemaker.workflow.pipeline_context import runnable_by_pipeline
 
 logger = logging.getLogger(__name__)
 
@@ -192,6 +193,7 @@ def _prepare_for_training(self, records, mini_batch_size=None, job_name=None):
         self.feature_dim = feature_dim
         self.mini_batch_size = mini_batch_size
 
+    @runnable_by_pipeline
     def fit(
         self,
         records,

src/sagemaker/clarify.py

@@ -803,7 +803,8 @@ def _run(
                 output_name="analysis_result",
                 s3_upload_mode="EndOfJob",
             )
-            super().run(
+
+            return super().run(
                 inputs=[data_input, config_input],
                 outputs=[result_output],
                 wait=wait,
@@ -871,7 +872,7 @@ def run_pre_training_bias(
                 job_name = utils.name_from_base(self.job_name_prefix)
             else:
                 job_name = utils.name_from_base("Clarify-Pretraining-Bias")
-        self._run(
+        return self._run(
             data_config,
             analysis_config,
             wait,
@@ -957,7 +958,7 @@ def run_post_training_bias(
                 job_name = utils.name_from_base(self.job_name_prefix)
             else:
                 job_name = utils.name_from_base("Clarify-Posttraining-Bias")
-        self._run(
+        return self._run(
             data_config,
             analysis_config,
             wait,
@@ -1060,7 +1061,7 @@ def run_bias(
                 job_name = utils.name_from_base(self.job_name_prefix)
             else:
                 job_name = utils.name_from_base("Clarify-Bias")
-        self._run(
+        return self._run(
             data_config,
             analysis_config,
             wait,
@@ -1167,7 +1168,7 @@ def run_explainability(
                 job_name = utils.name_from_base(self.job_name_prefix)
             else:
                 job_name = utils.name_from_base("Clarify-Explainability")
-        self._run(
+        return self._run(
             data_config,
             analysis_config,
             wait,

src/sagemaker/estimator.py

@@ -16,9 +16,9 @@
 import json
 import logging
 import os
-from typing import Any, Dict
 import uuid
 from abc import ABCMeta, abstractmethod
+from typing import Any, Dict
 
 from six import string_types, with_metaclass
 from six.moves.urllib.parse import urlparse
@@ -75,6 +75,10 @@
     name_from_base,
 )
 from sagemaker.workflow import is_pipeline_variable
+from sagemaker.workflow.pipeline_context import (
+    PipelineSession,
+    runnable_by_pipeline,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -721,6 +725,7 @@ def _stage_user_code_in_s3(self) -> str:
             dependencies=self.dependencies,
             kms_key=kms_key,
             s3_resource=self.sagemaker_session.s3_resource,
+            settings=self.sagemaker_session.settings,
         )
 
     def _prepare_rules(self):
@@ -896,6 +901,7 @@ def latest_job_profiler_artifacts_path(self):
             )
         return None
 
+    @runnable_by_pipeline
     def fit(self, inputs=None, wait=True, logs="All", job_name=None, experiment_config=None):
         """Train a model using the input training dataset.
 
@@ -1341,7 +1347,9 @@ def register(
     @property
     def model_data(self):
         """str: The model location in S3. Only set if Estimator has been ``fit()``."""
-        if self.latest_training_job is not None:
+        if self.latest_training_job is not None and not isinstance(
+            self.sagemaker_session, PipelineSession
+        ):
             model_uri = self.sagemaker_session.sagemaker_client.describe_training_job(
                 TrainingJobName=self.latest_training_job.name
             )["ModelArtifacts"]["S3ModelArtifacts"]
@@ -1767,6 +1775,7 @@ def start_new(cls, estimator, inputs, experiment_config):
             all information about the started training job.
         """
         train_args = cls._get_train_args(estimator, inputs, experiment_config)
+
         estimator.sagemaker_session.train(**train_args)
 
         return cls(estimator.sagemaker_session, estimator._current_job_name)

src/sagemaker/model.py

@@ -447,6 +447,7 @@ def _upload_code(self, key_prefix: str, repack: bool = False) -> None:
                 script=self.entry_point,
                 directory=self.source_dir,
                 dependencies=self.dependencies,
+                settings=self.sagemaker_session.settings,
             )
 
         if repack and self.model_data is not None and self.entry_point is not None:

src/sagemaker/processing.py

@@ -28,16 +28,13 @@
 
 from six.moves.urllib.parse import urlparse
 from six.moves.urllib.request import url2pathname
-
 from sagemaker import s3
 from sagemaker.job import _Job
 from sagemaker.local import LocalSession
 from sagemaker.utils import base_name_from_image, get_config_value, name_from_base
 from sagemaker.session import Session
 from sagemaker.workflow import is_pipeline_variable
-from sagemaker.workflow.properties import Properties
-from sagemaker.workflow.parameters import Parameter
-from sagemaker.workflow.entities import Expression
+from sagemaker.workflow.pipeline_context import runnable_by_pipeline
 from sagemaker.dataset_definition.inputs import S3Input, DatasetDefinition
 from sagemaker.apiutils._base_types import ApiObject
 from sagemaker.s3 import S3Uploader
@@ -133,6 +130,7 @@ def __init__(
 
         self.sagemaker_session = sagemaker_session or Session()
 
+    @runnable_by_pipeline
     def run(
         self,
         inputs=None,
@@ -314,10 +312,10 @@ def _normalize_inputs(self, inputs=None, kms_key=None):
                 if file_input.input_name is None:
                     file_input.input_name = "input-{}".format(count)
 
-                if isinstance(file_input.source, Properties) or file_input.dataset_definition:
+                if is_pipeline_variable(file_input.source) or file_input.dataset_definition:
                     normalized_inputs.append(file_input)
                     continue
-                if isinstance(file_input.s3_input.s3_uri, (Parameter, Expression, Properties)):
+                if is_pipeline_variable(file_input.s3_input.s3_uri):
                     normalized_inputs.append(file_input)
                     continue
                 # If the source is a local path, upload it to S3
@@ -367,7 +365,7 @@ def _normalize_outputs(self, outputs=None):
                 # Generate a name for the ProcessingOutput if it doesn't have one.
                 if output.output_name is None:
                     output.output_name = "output-{}".format(count)
-                if isinstance(output.destination, (Parameter, Expression, Properties)):
+                if is_pipeline_variable(output.destination):
                     normalized_outputs.append(output)
                     continue
                 # If the output's destination is not an s3_uri, create one.
@@ -497,6 +495,7 @@ def get_run_args(
         """
         return RunArgs(code=code, inputs=inputs, outputs=outputs, arguments=arguments)
 
+    @runnable_by_pipeline
     def run(
         self,
         code,
@@ -1600,7 +1599,7 @@ def run(  # type: ignore[override]
         )
 
         # Submit a processing job.
-        super().run(
+        return super().run(
             code=s3_runproc_sh,
             inputs=inputs,
             outputs=outputs,

src/sagemaker/session.py

@@ -19,6 +19,7 @@
 import re
 import sys
 import time
+import typing
 import warnings
 from typing import List, Dict, Any, Sequence
 
@@ -551,7 +552,6 @@ def train(  # noqa: C901
             retry_strategy(dict): Defines RetryStrategy for InternalServerFailures.
                 * max_retry_attsmpts (int): Number of times a job should be retried.
                 The key in RetryStrategy is 'MaxRetryAttempts'.
-
         Returns:
             str: ARN of the training job, if it is created.
         """
@@ -585,9 +585,13 @@ def train(  # noqa: C901
             environment=environment,
             retry_strategy=retry_strategy,
         )
-        LOGGER.info("Creating training-job with name: %s", job_name)
-        LOGGER.debug("train request: %s", json.dumps(train_request, indent=4))
-        self.sagemaker_client.create_training_job(**train_request)
+
+        def submit(request):
+            LOGGER.info("Creating training-job with name: %s", job_name)
+            LOGGER.debug("train request: %s", json.dumps(request, indent=4))
+            self.sagemaker_client.create_training_job(**request)
+
+        self._intercept_create_request(train_request, submit)
 
     def _get_train_request(  # noqa: C901
         self,
@@ -912,9 +916,13 @@ def process(
             tags=tags,
             experiment_config=experiment_config,
         )
-        LOGGER.info("Creating processing-job with name %s", job_name)
-        LOGGER.debug("process request: %s", json.dumps(process_request, indent=4))
-        self.sagemaker_client.create_processing_job(**process_request)
+
+        def submit(request):
+            LOGGER.info("Creating processing-job with name %s", job_name)
+            LOGGER.debug("process request: %s", json.dumps(request, indent=4))
+            self.sagemaker_client.create_processing_job(**request)
+
+        self._intercept_create_request(process_request, submit)
 
     def _get_process_request(
         self,
@@ -2086,9 +2094,12 @@ def create_tuning_job(
             tags=tags,
         )
 
-        LOGGER.info("Creating hyperparameter tuning job with name: %s", job_name)
-        LOGGER.debug("tune request: %s", json.dumps(tune_request, indent=4))
-        self.sagemaker_client.create_hyper_parameter_tuning_job(**tune_request)
+        def submit(request):
+            LOGGER.info("Creating hyperparameter tuning job with name: %s", job_name)
+            LOGGER.debug("tune request: %s", json.dumps(request, indent=4))
+            self.sagemaker_client.create_hyper_parameter_tuning_job(**request)
+
+        self._intercept_create_request(tune_request, submit)
 
     def _get_tuning_request(
         self,
@@ -2553,9 +2564,12 @@ def transform(
             model_client_config=model_client_config,
         )
 
-        LOGGER.info("Creating transform job with name: %s", job_name)
-        LOGGER.debug("Transform request: %s", json.dumps(transform_request, indent=4))
-        self.sagemaker_client.create_transform_job(**transform_request)
+        def submit(request):
+            LOGGER.info("Creating transform job with name: %s", job_name)
+            LOGGER.debug("Transform request: %s", json.dumps(request, indent=4))
+            self.sagemaker_client.create_transform_job(**request)
+
+        self._intercept_create_request(transform_request, submit)
 
     def _create_model_request(
         self,
@@ -4161,6 +4175,18 @@ def account_id(self) -> str:
         )
         return sts_client.get_caller_identity()["Account"]
 
+    def _intercept_create_request(self, request: typing.Dict, create):
+        """This function intercepts the create job request.
+
+        PipelineSession inherits this Session class and will override
+        this function to intercept the create request.
+
+        Args:
+            request (dict): the create job request
+            create (functor): a functor calls the sagemaker client create method
+        """
+        create(request)
+
 
 def get_model_package_args(
     content_types,

src/sagemaker/spark/processing.py

@@ -249,7 +249,7 @@ def run(
         """
         self._current_job_name = self._generate_current_job_name(job_name=job_name)
 
-        super().run(
+        return super().run(
             submit_app,
             inputs,
             outputs,
@@ -868,7 +868,7 @@ def run(
             spark_event_logs_s3_uri=spark_event_logs_s3_uri,
         )
 
-        super().run(
+        return super().run(
             submit_app=submit_app,
             inputs=extended_inputs,
             outputs=extended_outputs,
@@ -1125,7 +1125,7 @@ def run(
             spark_event_logs_s3_uri=spark_event_logs_s3_uri,
         )
 
-        super().run(
+        return super().run(
             submit_app=submit_app,
             inputs=extended_inputs,
             outputs=extended_outputs,

src/sagemaker/transformer.py

@@ -17,6 +17,8 @@
 
 from sagemaker.job import _Job
 from sagemaker.session import Session
+from sagemaker.workflow.pipeline_context import runnable_by_pipeline
+from sagemaker.workflow import is_pipeline_variable
 from sagemaker.utils import base_name_from_image, name_from_base
 
 
@@ -106,6 +108,7 @@ def __init__(
 
         self.sagemaker_session = sagemaker_session or Session()
 
+    @runnable_by_pipeline
     def transform(
         self,
         data,
@@ -197,7 +200,11 @@ def transform(
             base_name = self.base_transform_job_name
 
             if base_name is None:
-                base_name = self._retrieve_base_name()
+                base_name = (
+                    "transform-job"
+                    if is_pipeline_variable(self.model_name)
+                    else self._retrieve_base_name()
+                )
 
             self._current_job_name = name_from_base(base_name)
 
@@ -370,6 +377,7 @@ def start_new(
             experiment_config,
             model_client_config,
         )
+
         transformer.sagemaker_session.transform(**transform_args)
 
         return cls(transformer.sagemaker_session, transformer._current_job_name)