sagemaker 2.53.0__tar.gz → 2.54.1.dev0__tar.gz

sagemaker-2.54.1.dev0/PKG-INFO

@@ -0,0 +1,252 @@
+Metadata-Version: 2.1
+Name: sagemaker
+Version: 2.54.1.dev0
+Summary: Open source library for training and deploying models on Amazon SageMaker.
+Home-page: https://github.com/aws/sagemaker-python-sdk/
+Author: Amazon Web Services
+License: Apache License 2.0
+Keywords: ML Amazon AWS AI Tensorflow MXNet
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Provides-Extra: local
+Provides-Extra: scipy
+Provides-Extra: all
+Provides-Extra: test
+License-File: LICENSE.txt
+
+.. image:: https://github.com/aws/sagemaker-python-sdk/raw/master/branding/icon/sagemaker-banner.png
+    :height: 100px
+    :alt: SageMaker
+
+====================
+SageMaker Python SDK
+====================
+
+.. image:: https://img.shields.io/pypi/v/sagemaker.svg
+   :target: https://pypi.python.org/pypi/sagemaker
+   :alt: Latest Version
+
+.. image:: https://img.shields.io/pypi/pyversions/sagemaker.svg
+   :target: https://pypi.python.org/pypi/sagemaker
+   :alt: Supported Python Versions
+
+.. image:: https://img.shields.io/badge/code_style-black-000000.svg
+   :target: https://github.com/python/black
+   :alt: Code style: black
+
+.. image:: https://readthedocs.org/projects/sagemaker/badge/?version=stable
+   :target: https://sagemaker.readthedocs.io/en/stable/
+   :alt: Documentation Status
+
+SageMaker Python SDK is an open source library for training and deploying machine learning models on Amazon SageMaker.
+
+With the SDK, you can train and deploy models using popular deep learning frameworks **Apache MXNet** and **TensorFlow**.
+You can also train and deploy models with **Amazon algorithms**,
+which are scalable implementations of core machine learning algorithms that are optimized for SageMaker and GPU training.
+If you have **your own algorithms** built into SageMaker compatible Docker containers, you can train and host models using these as well.
+
+For detailed documentation, including the API reference, see `Read the Docs <https://sagemaker.readthedocs.io>`_.
+
+Table of Contents
+-----------------
+
+#. `Installing SageMaker Python SDK <#installing-the-sagemaker-python-sdk>`__
+#. `Using the SageMaker Python SDK <https://sagemaker.readthedocs.io/en/stable/overview.html>`__
+#. `Using MXNet <https://sagemaker.readthedocs.io/en/stable/using_mxnet.html>`__
+#. `Using TensorFlow <https://sagemaker.readthedocs.io/en/stable/using_tf.html>`__
+#. `Using Chainer <https://sagemaker.readthedocs.io/en/stable/using_chainer.html>`__
+#. `Using PyTorch <https://sagemaker.readthedocs.io/en/stable/using_pytorch.html>`__
+#. `Using Scikit-learn <https://sagemaker.readthedocs.io/en/stable/using_sklearn.html>`__
+#. `Using XGBoost <https://sagemaker.readthedocs.io/en/stable/using_xgboost.html>`__
+#. `SageMaker Reinforcement Learning Estimators <https://sagemaker.readthedocs.io/en/stable/using_rl.html>`__
+#. `SageMaker SparkML Serving <#sagemaker-sparkml-serving>`__
+#. `Amazon SageMaker Built-in Algorithm Estimators <src/sagemaker/amazon/README.rst>`__
+#. `Using SageMaker AlgorithmEstimators <https://sagemaker.readthedocs.io/en/stable/overview.html#using-sagemaker-algorithmestimators>`__
+#. `Consuming SageMaker Model Packages <https://sagemaker.readthedocs.io/en/stable/overview.html#consuming-sagemaker-model-packages>`__
+#. `BYO Docker Containers with SageMaker Estimators <https://sagemaker.readthedocs.io/en/stable/overview.html#byo-docker-containers-with-sagemaker-estimators>`__
+#. `SageMaker Automatic Model Tuning <https://sagemaker.readthedocs.io/en/stable/overview.html#sagemaker-automatic-model-tuning>`__
+#. `SageMaker Batch Transform <https://sagemaker.readthedocs.io/en/stable/overview.html#sagemaker-batch-transform>`__
+#. `Secure Training and Inference with VPC <https://sagemaker.readthedocs.io/en/stable/overview.html#secure-training-and-inference-with-vpc>`__
+#. `BYO Model <https://sagemaker.readthedocs.io/en/stable/overview.html#byo-model>`__
+#. `Inference Pipelines <https://sagemaker.readthedocs.io/en/stable/overview.html#inference-pipelines>`__
+#. `Amazon SageMaker Operators in Apache Airflow <https://sagemaker.readthedocs.io/en/stable/using_workflow.html>`__
+#. `SageMaker Autopilot <src/sagemaker/automl/README.rst>`__
+#. `Model Monitoring <https://sagemaker.readthedocs.io/en/stable/amazon_sagemaker_model_monitoring.html>`__
+#. `SageMaker Debugger <https://sagemaker.readthedocs.io/en/stable/amazon_sagemaker_debugger.html>`__
+#. `SageMaker Processing <https://sagemaker.readthedocs.io/en/stable/amazon_sagemaker_processing.html>`__
+
+
+Installing the SageMaker Python SDK
+-----------------------------------
+
+The SageMaker Python SDK is built to PyPI and can be installed with pip as follows:
+
+::
+
+    pip install sagemaker
+
+You can install from source by cloning this repository and running a pip install command in the root directory of the repository:
+
+::
+
+    git clone https://github.com/aws/sagemaker-python-sdk.git
+    cd sagemaker-python-sdk
+    pip install .
+
+Supported Operating Systems
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+SageMaker Python SDK supports Unix/Linux and Mac.
+
+Supported Python Versions
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+SageMaker Python SDK is tested on:
+
+- Python 3.6
+- Python 3.7
+- Python 3.8
+
+AWS Permissions
+~~~~~~~~~~~~~~~
+
+As a managed service, Amazon SageMaker performs operations on your behalf on the AWS hardware that is managed by Amazon SageMaker.
+Amazon SageMaker can perform only operations that the user permits.
+You can read more about which permissions are necessary in the `AWS Documentation <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-roles.html>`__.
+
+The SageMaker Python SDK should not require any additional permissions aside from what is required for using SageMaker.
+However, if you are using an IAM role with a path in it, you should grant permission for ``iam:GetRole``.
+
+Licensing
+~~~~~~~~~
+SageMaker Python SDK is licensed under the Apache 2.0 License. It is copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. The license is available at:
+http://aws.amazon.com/apache2.0/
+
+Running tests
+~~~~~~~~~~~~~
+
+SageMaker Python SDK has unit tests and integration tests.
+
+You can install the libraries needed to run the tests by running :code:`pip install --upgrade .[test]` or, for Zsh users: :code:`pip install --upgrade .\[test\]`
+
+**Unit tests**
+
+We run unit tests with tox, which is a program that lets you run unit tests for multiple Python versions, and also make sure the
+code fits our style guidelines. We run tox with `all of our supported Python versions <#supported-python-versions>`_, so to run unit tests
+with the same configuration we do, you need to have interpreters for those Python versions installed.
+
+To run the unit tests with tox, run:
+
+::
+
+    tox tests/unit
+
+**Integrations tests**
+
+To run the integration tests, the following prerequisites must be met
+
+1. AWS account credentials are available in the environment for the boto3 client to use.
+2. The AWS account has an IAM role named :code:`SageMakerRole`.
+   It should have the AmazonSageMakerFullAccess policy attached as well as a policy with `the necessary permissions to use Elastic Inference <https://docs.aws.amazon.com/sagemaker/latest/dg/ei-setup.html>`__.
+
+We recommend selectively running just those integration tests you'd like to run. You can filter by individual test function names with:
+
+::
+
+    tox -- -k 'test_i_care_about'
+
+
+You can also run all of the integration tests by running the following command, which runs them in sequence, which may take a while:
+
+::
+
+    tox -- tests/integ
+
+
+You can also run them in parallel:
+
+::
+
+    tox -- -n auto tests/integ
+
+
+Building Sphinx docs
+~~~~~~~~~~~~~~~~~~~~
+
+Setup a Python environment, and install the dependencies listed in ``doc/requirements.txt``:
+
+::
+
+    # conda
+    conda create -n sagemaker python=3.7
+    conda activate sagemaker
+    conda install sphinx=3.1.1 sphinx_rtd_theme=0.5.0
+
+    # pip
+    pip install -r doc/requirements.txt
+
+
+Clone/fork the repo, and install your local version:
+
+::
+
+    pip install --upgrade .
+
+Then ``cd`` into the ``sagemaker-python-sdk/doc`` directory and run:
+
+::
+
+    make html
+
+You can edit the templates for any of the pages in the docs by editing the .rst files in the ``doc`` directory and then running ``make html`` again.
+
+Preview the site with a Python web server:
+
+::
+
+    cd _build/html
+    python -m http.server 8000
+
+View the website by visiting http://localhost:8000
+
+SageMaker SparkML Serving
+-------------------------
+
+With SageMaker SparkML Serving, you can now perform predictions against a SparkML Model in SageMaker.
+In order to host a SparkML model in SageMaker, it should be serialized with ``MLeap`` library.
+
+For more information on MLeap, see https://github.com/combust/mleap .
+
+Supported major version of Spark: 2.4 (MLeap version - 0.9.6)
+
+Here is an example on how to create an instance of  ``SparkMLModel`` class and use ``deploy()`` method to create an
+endpoint which can be used to perform prediction against your trained SparkML Model.
+
+.. code:: python
+
+    sparkml_model = SparkMLModel(model_data='s3://path/to/model.tar.gz', env={'SAGEMAKER_SPARKML_SCHEMA': schema})
+    model_name = 'sparkml-model'
+    endpoint_name = 'sparkml-endpoint'
+    predictor = sparkml_model.deploy(initial_instance_count=1, instance_type='ml.c4.xlarge', endpoint_name=endpoint_name)
+
+Once the model is deployed, we can invoke the endpoint with a ``CSV`` payload like this:
+
+.. code:: python
+
+    payload = 'field_1,field_2,field_3,field_4,field_5'
+    predictor.predict(payload)
+
+
+For more information about the different ``content-type`` and ``Accept`` formats as well as the structure of the
+``schema`` that SageMaker SparkML Serving recognizes, please see `SageMaker SparkML Serving Container`_.
+
+.. _SageMaker SparkML Serving Container: https://github.com/aws/sagemaker-sparkml-serving-container
+
+

sagemaker-2.54.1.dev0/VERSION

@@ -0,0 +1 @@
+2.54.1.dev0

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/automl/automl.py

@@ -328,6 +328,7 @@ class AutoML(object):
             predictor_cls=predictor_cls,
             name=name,
             vpc_config=vpc_config,
+            enable_network_isolation=enable_network_isolation,
             sagemaker_session=sagemaker_session or self.sagemaker_session,
         )
         return pipeline

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/feature_store/feature_group.py

@@ -207,7 +207,8 @@ class IngestionManagerPandas:
         for row in data_frame[start_index:end_index].itertuples():
             record = [
                 FeatureValue(
-                    feature_name=data_frame.columns[index - 1], value_as_string=str(row[index])
+                    feature_name=data_frame.columns[index - 1],
+                    value_as_string=str(row[index]),
                 )
                 for index in range(1, len(row))
                 if pd.notna(row[index])
@@ -270,13 +271,24 @@ class IngestionManagerPandas:
             timeout (Union[int, float]): ``concurrent.futures.TimeoutError`` will be raised
                 if timeout is reached.
         """
+        # pylint: disable=I1101
         batch_size = math.ceil(data_frame.shape[0] / self.max_processes)
+        # pylint: enable=I1101
 
         args = []
         for i in range(self.max_processes):
             start_index = min(i * batch_size, data_frame.shape[0])
             end_index = min(i * batch_size + batch_size, data_frame.shape[0])
-            args += [(data_frame[start_index:end_index], start_index, timeout)]
+            args += [
+                (
+                    self.max_workers,
+                    self.feature_group_name,
+                    self.sagemaker_fs_runtime_client_config,
+                    data_frame[start_index:end_index],
+                    start_index,
+                    timeout,
+                )
+            ]
 
         def init_worker():
             # ignore keyboard interrupts in child processes.
@@ -285,13 +297,21 @@ class IngestionManagerPandas:
         self._processing_pool = ProcessingPool(self.max_processes, init_worker)
         self._processing_pool.restart(force=True)
 
-        f = lambda x: self._run_multi_threaded(*x)  # noqa: E731
+        f = lambda x: IngestionManagerPandas._run_multi_threaded(*x)  # noqa: E731
         self._async_result = self._processing_pool.amap(f, args)
 
         if wait:
             self.wait(timeout=timeout)
 
-    def _run_multi_threaded(self, data_frame: DataFrame, row_offset=0, timeout=None) -> List[int]:
+    @staticmethod
+    def _run_multi_threaded(
+        max_workers: int,
+        feature_group_name: str,
+        sagemaker_fs_runtime_client_config: Config,
+        data_frame: DataFrame,
+        row_offset=0,
+        timeout=None,
+    ) -> List[int]:
         """Start the ingestion process.
 
         Args:
@@ -305,21 +325,23 @@ class IngestionManagerPandas:
         Returns:
             List of row indices that failed to be ingested.
         """
-        executor = ThreadPoolExecutor(max_workers=self.max_workers)
-        batch_size = math.ceil(data_frame.shape[0] / self.max_workers)
+        executor = ThreadPoolExecutor(max_workers=max_workers)
+        # pylint: disable=I1101
+        batch_size = math.ceil(data_frame.shape[0] / max_workers)
+        # pylint: enable=I1101
 
         futures = {}
-        for i in range(self.max_workers):
+        for i in range(max_workers):
             start_index = min(i * batch_size, data_frame.shape[0])
             end_index = min(i * batch_size + batch_size, data_frame.shape[0])
             futures[
                 executor.submit(
-                    self._ingest_single_batch,
-                    feature_group_name=self.feature_group_name,
+                    IngestionManagerPandas._ingest_single_batch,
+                    feature_group_name=feature_group_name,
                     data_frame=data_frame,
                     start_index=start_index,
                     end_index=end_index,
-                    client_config=self.sagemaker_fs_runtime_client_config,
+                    client_config=sagemaker_fs_runtime_client_config,
                 )
             ] = (start_index + row_offset, end_index + row_offset)
 

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/image_uri_config/model-monitor.json

@@ -7,6 +7,7 @@
                 "ap-east-1": "001633400207",
                 "ap-northeast-1": "574779866223",
                 "ap-northeast-2": "709848358524",
+                "ap-northeast-3": "990339680094",
                 "ap-south-1": "126357580389",
                 "ap-southeast-1": "245545462676",
                 "ap-southeast-2": "563025443158",

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/image_uri_config/pytorch.json

@@ -4,7 +4,8 @@
             "cpu"
         ],
         "version_aliases": {
-            "1.3": "1.3.1"
+            "1.3": "1.3.1",
+            "1.5": "1.5.1"
         },
         "versions": {
             "1.3.1": {
@@ -12,8 +13,6 @@
                     "py3"
                 ],
                 "registries": {
-                    "af-south-1": "626614931356",
-                    "ap-east-1": "871362719292",
                     "ap-northeast-1": "763104351884",
                     "ap-northeast-2": "763104351884",
                     "ap-northeast-3": "364406365360",
@@ -26,16 +25,22 @@
                     "eu-central-1": "763104351884",
                     "eu-north-1": "763104351884",
                     "eu-west-1": "763104351884",
-                    "eu-west-2": "763104351884",
-                    "eu-west-3": "763104351884",
-                    "eu-south-1": "692866216735",
-                    "me-south-1": "217643126080",
-                    "sa-east-1": "763104351884",
                     "us-east-1": "763104351884",
                     "us-east-2": "763104351884",
-                    "us-gov-west-1": "442386744353",
-                    "us-iso-east-1": "886529160074",
-                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "repository": "pytorch-inference-eia"
+            },
+            "1.5.1": {
+                "py_versions": [
+                    "py3"
+                ],
+                "registries": {
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
                     "us-west-2": "763104351884"
                 },
                 "repository": "pytorch-inference-eia"

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/lineage/association.py

@@ -15,11 +15,14 @@ from __future__ import absolute_import
 
 from typing import Optional, Iterator
 from datetime import datetime
+import logging
 
 from sagemaker.apiutils import _base_types
 from sagemaker.lineage import _api_types
 from sagemaker.lineage._api_types import AssociationSummary
 
+logger = logging.getLogger(__name__)
+
 
 class Association(_base_types.Record):
     """An Amazon SageMaker artifact, which is part of a SageMaker lineage.
@@ -73,6 +76,10 @@ class Association(_base_types.Record):
         Returns:
             list({str:str}): a list of key value pairs
         """
+        logger.warning(
+            "set_tag on Association is deprecated. Use set_tag on the source or destination\
+             entity instead."
+        )
         return self._set_tags(resource_arn=self.source_arn, tags=[tag])
 
     def set_tags(self, tags=None):
@@ -84,6 +91,10 @@ class Association(_base_types.Record):
         Returns:
             list({str:str}): a list of key value pairs
         """
+        logger.warning(
+            "set_tags on Association is deprecated. Use set_tags on the source or destination\
+            entity instead."
+        )
         return self._set_tags(resource_arn=self.source_arn, tags=tags)
 
     @classmethod

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/local/local_session.py

@@ -571,6 +571,21 @@ class LocalSession(Session):
         # on local mode.
         pass  # pylint: disable=unnecessary-pass
 
+    def logs_for_processing_job(self, job_name, wait=False, poll=10):
+        """A no-op method meant to override the sagemaker client.
+
+        Args:
+          job_name:
+          wait:  (Default value = False)
+          poll:  (Default value = 10)
+
+        Returns:
+
+        """
+        # override logs_for_job() as it doesn't need to perform any action
+        # on local mode.
+        pass  # pylint: disable=unnecessary-pass
+
 
 class file_input(object):
     """Amazon SageMaker channel configuration for FILE data sources, used in local mode."""

{sagemaker-2.53.0 → sagemaker-2.54.1.dev0}/src/sagemaker/utils.py

@@ -331,7 +331,7 @@ def create_tar_file(source_files, target=None):
     else:
         _, filename = tempfile.mkstemp()
 
-    with tarfile.open(filename, mode="w:gz") as t:
+    with tarfile.open(filename, mode="w:gz", dereference=True) as t:
         for sf in source_files:
             # Add all files from the directory into the root of the directory structure of the tar
             t.add(sf, arcname=os.path.basename(sf))