Merge from master

Author: sreedes

CHANGELOG.md

@@ -1,5 +1,36 @@
 # Changelog
 
+## v2.49.2 (2021-07-21)
+
+### Bug Fixes and Other Changes
+
+ * order of populating container list
+ * upgrade Adobe Analytics cookie to 3.0
+
+## v2.49.1 (2021-07-19)
+
+### Bug Fixes and Other Changes
+
+ * Set flag when debugger is disabled
+ * KMS Key fix for kwargs
+ * Update BiasConfig to accept multiple facet params
+
+### Documentation Changes
+
+ * Update huggingface estimator documentation
+
+## v2.49.0 (2021-07-15)
+
+### Features
+
+ * Adding serial inference pipeline support to RegisterModel Step
+
+### Documentation Changes
+
+ * add tuning step get_top_model_s3_uri and callback step to doc
+ * links for HF in sdk
+ * Add Clarify module to Model Monitoring API docs
+
 ## v2.48.2 (2021-07-12)
 
 ### Bug Fixes and Other Changes

VERSION

@@ -1 +1 @@
-2.48.3.dev0
+2.49.3.dev0

doc/_static/aws-ux-shortbread/index.js

@@ -0,0 +1,34 @@
+(function (w) {
+w.URLSearchParams = w.URLSearchParams || function (searchString) {
+  var self = this;
+  self.searchString = searchString;
+  self.get = function (name) {
+    var results = new RegExp('[\?&]' + name + '=([^&#]*)').exec(self.searchString);
+    if (results === null) {
+      return null;
+    }
+    else {
+      return decodeURI(results[1]) || 0;
+    }
+  };
+}
+})(window);
+
+const queryString = window.location.search;
+const urlParams = new URLSearchParams(queryString);
+const lang = urlParams.get('lang')
+window.onload = function () {
+var domainName = window.location.hostname;
+
+// remove an instance of shortbread if already exists
+var existingShortbreadEl = document.getElementById("awsccc-sb-ux-c");
+existingShortbreadEl && existingShortbreadEl.remove();        
+
+var shortbread = AWSCShortbread({
+  domain: domainName,
+  language: lang,
+  //queryGeolocation: function (geolocatedIn) { geolocatedIn("EU") },
+});
+
+shortbread.checkForCookieConsent();
+}

doc/_static/aws-ux-shortbread/init.js

@@ -68,7 +68,12 @@
 
 htmlhelp_basename = "%sdoc" % project
 
-html_js_files = ["https://a0.awsstatic.com/s_code/js/1.0/awshome_s_code.js", "js/analytics.js"]
+# For Adobe Analytics
+html_js_files = [
+    "https://a0.awsstatic.com/s_code/js/3.0/awshome_s_code.js",
+    "aws-ux-shortbread/index.js",
+    "aws-ux-shortbread/init.js",
+]
 
 html_context = {"css_files": ["_static/theme_overrides.css"]}
 

doc/conf.py

@@ -88,21 +88,34 @@ def __init__(
         Args:
             label_values_or_threshold (Any): List of label values or threshold to indicate positive
                 outcome used for bias metrics.
-            facet_name (str): Sensitive attribute in the input data for which we like to compare
-                metrics.
+            facet_name (str or [str]): String or List of strings of sensitive attribute(s) in the
+            input data for which we like to compare metrics.
             facet_values_or_threshold (list): Optional list of values to form a sensitive group or
                 threshold for a numeric facet column that defines the lower bound of a sensitive
                 group. Defaults to considering each possible value as sensitive group and
                 computing metrics vs all the other examples.
+                If facet_name is a list, this needs to be None or a List consisting of lists or None
+                with the same length as facet_name list.
             group_name (str): Optional column name or index to indicate a group column to be used
                 for the bias metric 'Conditional Demographic Disparity in Labels - CDDL' or
                 'Conditional Demographic Disparity in Predicted Labels - CDDPL'.
         """
-        facet = {"name_or_index": facet_name}
-        _set(facet_values_or_threshold, "value_or_threshold", facet)
+        if isinstance(facet_name, str):
+            facet = {"name_or_index": facet_name}
+            _set(facet_values_or_threshold, "value_or_threshold", facet)
+            facet_list = [facet]
+        elif facet_values_or_threshold is None or len(facet_name) == len(facet_values_or_threshold):
+            facet_list = []
+            for i, single_facet_name in enumerate(facet_name):
+                facet = {"name_or_index": single_facet_name}
+                if facet_values_or_threshold is not None:
+                    _set(facet_values_or_threshold[i], "value_or_threshold", facet)
+                facet_list.append(facet)
+        else:
+            raise ValueError("Wrong combination of argument values passed")
         self.analysis_config = {
             "label_values_or_threshold": label_values_or_threshold,
-            "facet": [facet],
+            "facet": facet_list,
         }
         _set(group_name, "group_variable", self.analysis_config)
 

src/sagemaker/clarify.py

@@ -15,6 +15,7 @@
 
 from sagemaker.debugger.debugger import (  # noqa: F401
     CollectionConfig,
+    DEBUGGER_FLAG,
     DebuggerHookConfig,
     framework_name,
     get_default_profiler_rule,

src/sagemaker/debugger/__init__.py

@@ -32,6 +32,7 @@
 from sagemaker.utils import build_dict
 
 framework_name = "debugger"
+DEBUGGER_FLAG = "USE_SMDEBUG"
 
 
 def get_rule_container_image_uri(region):

src/sagemaker/debugger/debugger.py

@@ -29,6 +29,7 @@
 from sagemaker.analytics import TrainingJobAnalytics
 from sagemaker.debugger import TensorBoardOutputConfig  # noqa: F401 # pylint: disable=unused-import
 from sagemaker.debugger import (
+    DEBUGGER_FLAG,
     DebuggerHookConfig,
     FrameworkProfile,
     get_default_profiler_rule,
@@ -2269,6 +2270,11 @@ def _validate_and_set_debugger_configs(self):
                     )
                     self.debugger_hook_config = False
 
+        if self.debugger_hook_config is False:
+            if self.environment is None:
+                self.environment = {}
+            self.environment[DEBUGGER_FLAG] = "0"
+
     def _stage_user_code_in_s3(self):
         """Upload the user training script to s3 and return the location.
 

src/sagemaker/estimator.py

@@ -70,10 +70,10 @@ def __init__(
                 ``image_uri`` is provided. The current supported version is ``4.6.1``.
             tensorflow_version (str): TensorFlow version you want to use for
                 executing your model training code. Defaults to ``None``. Required unless
-                ``pytorch_version`` is provided. The current supported version is ``1.6.0``.
+                ``pytorch_version`` is provided. The current supported version is ``2.4.1``.
             pytorch_version (str): PyTorch version you want to use for
                 executing your model training code. Defaults to ``None``. Required unless
-                ``tensorflow_version`` is provided. The current supported version is ``2.4.1``.
+                ``tensorflow_version`` is provided. The current supported versions are ``1.7.1`` and ``1.6.0``.
             source_dir (str): Path (absolute, relative or an S3 URI) to a directory
                 with any other training source code dependencies aside from the entry
                 point file (default: None). If ``source_dir`` is an S3 URI, it must

src/sagemaker/huggingface/estimator.py

@@ -13,6 +13,7 @@
 """Placeholder docstring"""
 from __future__ import absolute_import
 
+import abc
 import json
 import logging
 import os
@@ -29,6 +30,7 @@
     git_utils,
 )
 from sagemaker.deprecations import removed_kwargs
+from sagemaker.predictor import PredictorBase
 from sagemaker.transformer import Transformer
 
 LOGGER = logging.getLogger("sagemaker")
@@ -38,7 +40,23 @@
 )
 
 
-class Model(object):
+class ModelBase(abc.ABC):
+    """An object that encapsulates a trained model.
+
+    Models can be deployed to compute services like a SageMaker ``Endpoint``
+    or Lambda. Deployed models can be used to perform real-time inference.
+    """
+
+    @abc.abstractmethod
+    def deploy(self, *args, **kwargs) -> PredictorBase:
+        """Deploy this model to a compute service."""
+
+    @abc.abstractmethod
+    def delete_model(self, *args, **kwargs) -> None:
+        """Destroy resources associated with this model."""
+
+
+class Model(ModelBase):
     """A SageMaker ``Model`` that can be deployed to an ``Endpoint``."""
 
     def __init__(

src/sagemaker/model.py

@@ -13,6 +13,9 @@
 """Placeholder docstring"""
 from __future__ import print_function, absolute_import
 
+import abc
+from typing import Any, Tuple
+
 from sagemaker.deprecations import (
     deprecated_class,
     deprecated_deserialize,
@@ -51,7 +54,29 @@
 from sagemaker.lineage.context import EndpointContext
 
 
-class Predictor(object):
+class PredictorBase(abc.ABC):
+    """An object that encapsulates a deployed model."""
+
+    @abc.abstractmethod
+    def predict(self, *args, **kwargs) -> Any:
+        """Perform inference on the provided data and return a prediction."""
+
+    @abc.abstractmethod
+    def delete_endpoint(self, *args, **kwargs) -> None:
+        """Destroy resources associated with this predictor."""
+
+    @property
+    @abc.abstractmethod
+    def content_type(self) -> str:
+        """The MIME type of the data sent to the inference server."""
+
+    @property
+    @abc.abstractmethod
+    def accept(self) -> Tuple[str]:
+        """The content type(s) that are expected from the inference server."""
+
+
+class Predictor(PredictorBase):
     """Make prediction requests to an Amazon SageMaker endpoint."""
 
     def __init__(

src/sagemaker/predictor.py

@@ -0,0 +1,15 @@
+# Copyright 2017-2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""Classes for performing machine learning on serverless compute."""
+from sagemaker.serverless.model import LambdaModel  # noqa: F401
+from sagemaker.serverless.predictor import LambdaPredictor  # noqa: F401

src/sagemaker/serverless/__init__.py

@@ -0,0 +1,90 @@
+# Copyright 2017-2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""Models that can be deployed to serverless compute."""
+from __future__ import absolute_import
+
+import time
+from typing import Optional
+
+import boto3
+import botocore
+
+from sagemaker.model import ModelBase
+
+from .predictor import LambdaPredictor
+
+
+class LambdaModel(ModelBase):
+    """A model that can be deployed to Lambda."""
+
+    def __init__(
+        self, image_uri: str, role: str, client: Optional[botocore.client.BaseClient] = None
+    ) -> None:
+        """Initialize instance attributes.
+
+        Arguments:
+            image_uri: URI of a container image in the Amazon ECR registry. The image
+                should contain a handler that performs inference.
+            role: The Amazon Resource Name (ARN) of the IAM role that Lambda will assume
+                when it performs inference
+            client: The Lambda client used to interact with Lambda.
+        """
+        self._client = client or boto3.client("lambda")
+        self._image_uri = image_uri
+        self._role = role
+
+    def deploy(
+        self, function_name: str, timeout: int, memory_size: int, wait: bool = True
+    ) -> LambdaPredictor:
+        """Create a Lambda function using the image specified in the constructor.
+
+        Arguments:
+            function_name: The name of the function.
+            timeout: The number of seconds that the function can run for before being terminated.
+            memory_size: The amount of memory in MB that the function has access to.
+            wait: If true, wait until the deployment completes (default: True).
+
+        Returns:
+            A LambdaPredictor instance that performs inference using the specified image.
+        """
+        response = self._client.create_function(
+            FunctionName=function_name,
+            PackageType="Image",
+            Role=self._role,
+            Code={
+                "ImageUri": self._image_uri,
+            },
+            Timeout=timeout,
+            MemorySize=memory_size,
+        )
+
+        if not wait:
+            return LambdaPredictor(function_name, client=self._client)
+
+        # Poll function state.
+        polling_interval = 5
+        while response["State"] == "Pending":
+            time.sleep(polling_interval)
+            response = self._client.get_function_configuration(FunctionName=function_name)
+
+        if response["State"] != "Active":
+            raise RuntimeError("Failed to deploy model to Lambda: %s" % response["StateReason"])
+
+        return LambdaPredictor(function_name, client=self._client)
+
+    def delete_model(self) -> None:
+        """Destroy resources associated with this model.
+
+        This method does not delete the image specified in the constructor. As
+        a result, this method is a no-op.
+        """