Merge branch 'master' into master

Author: ahsan-z-khan

CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## v2.52.2 (2021-08-10)
+
+### Bug Fixes and Other Changes
+
+ * sklearn integ tests, remove swallowing exception on feature group delete attempt
+ * sklearn integ test for custom bucket
+
+### Documentation Changes
+
+ * Fix dataset_definition links
+ * Document LambdaModel and LambdaPredictor classes
+
 ## v2.52.1 (2021-08-06)
 
 ### Bug Fixes and Other Changes

VERSION

@@ -1 +1 @@
-2.52.2.dev0
+2.52.3.dev0

src/sagemaker/clarify.py

@@ -48,12 +48,17 @@ def __init__(
             headers (list[str]): A list of column names in the input dataset.
             features (str): JSONPath for locating the feature columns for bias metrics if the
                 dataset format is JSONLines.
-            dataset_type (str): Format of the dataset. Valid values are "text/csv" for CSV
-                and "application/jsonlines" for JSONLines.
+            dataset_type (str): Format of the dataset. Valid values are "text/csv" for CSV,
+                "application/jsonlines" for JSONLines, and "application/x-parquet" for Parquet.
             s3_data_distribution_type (str): Valid options are "FullyReplicated" or
                 "ShardedByS3Key".
             s3_compression_type (str): Valid options are "None" or "Gzip".
         """
+        if dataset_type not in ["text/csv", "application/jsonlines", "application/x-parquet"]:
+            raise ValueError(
+                f"Invalid dataset_type '{dataset_type}'."
+                f" Please check the API documentation for the supported dataset types."
+            )
         self.s3_data_input_path = s3_data_input_path
         self.s3_output_path = s3_output_path
         self.s3_data_distribution_type = s3_data_distribution_type
@@ -508,7 +513,7 @@ def run_pre_training_bias(
         kms_key=None,
         experiment_config=None,
     ):
-        """Runs a ProcessingJob to compute the requested bias 'methods' of the input data.
+        """Runs a ProcessingJob to compute the pre-training bias methods of the input data.
 
         Computes the requested methods that compare 'methods' (e.g. fraction of examples) for the
         sensitive group vs the other examples.
@@ -517,14 +522,14 @@ def run_pre_training_bias(
             data_config (:class:`~sagemaker.clarify.DataConfig`): Config of the input/output data.
             data_bias_config (:class:`~sagemaker.clarify.BiasConfig`): Config of sensitive groups.
             methods (str or list[str]): Selector of a subset of potential metrics:
-                ["`CI <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-ci.html>`_",
-                "`DPL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-dpl.html>`_",
-                "`KL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-kl.html>`_",
-                "`JS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-js.html>`_",
-                "`LP <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-lp.html>`_",
-                "`TVD <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-tvd.html>`_",
-                "`KS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-ks.html>`_",
-                "`CDDL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-cdd.html>`_"].
+                ["`CI <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-bias-metric-class-imbalance.html>`_",
+                "`DPL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-true-label-imbalance.html>`_",
+                "`KL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-kl-divergence.html>`_",
+                "`JS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-jensen-shannon-divergence.html>`_",
+                "`LP <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-lp-norm.html>`_",
+                "`TVD <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-total-variation-distance.html>`_",
+                "`KS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-kolmogorov-smirnov.html>`_",
+                "`CDDL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-cddl.html>`_"].
                 Defaults to computing all.
             wait (bool): Whether the call should wait until the job completes (default: True).
             logs (bool): Whether to show the logs produced by the job.
@@ -538,7 +543,7 @@ def run_pre_training_bias(
             experiment_config (dict[str, str]): Experiment management configuration.
                 Dictionary contains three optional keys:
                 'ExperimentName', 'TrialName', and 'TrialComponentDisplayName'.
-        """
+        """  # noqa E501
         analysis_config = data_config.get_config()
         analysis_config.update(data_bias_config.get_config())
         analysis_config["methods"] = {"pre_training_bias": {"methods": methods}}
@@ -562,7 +567,7 @@ def run_post_training_bias(
         kms_key=None,
         experiment_config=None,
     ):
-        """Runs a ProcessingJob to compute the requested bias 'methods' of the model predictions.
+        """Runs a ProcessingJob to compute the post-training bias methods of the model predictions.
 
         Spins up a model endpoint, runs inference over the input example in the
         's3_data_input_path' to obtain predicted labels. Computes a the requested methods that
@@ -633,12 +638,11 @@ def run_bias(
         kms_key=None,
         experiment_config=None,
     ):
-        """Runs a ProcessingJob to compute the requested bias 'methods' of the model predictions.
+        """Runs a ProcessingJob to compute the requested bias methods.
 
-        Spins up a model endpoint, runs inference over the input example in the
-        's3_data_input_path' to obtain predicted labels. Computes a the requested methods that
-        compare 'methods' (e.g. accuracy, precision, recall) for the sensitive group vs the other
-        examples.
+        It computes the metrics of both the pre-training methods and the post-training methods.
+        To calculate post-training methods, it needs to spin up a model endpoint, runs inference
+        over the input example in the 's3_data_input_path' to obtain predicted labels.
 
         Args:
             data_config (:class:`~sagemaker.clarify.DataConfig`): Config of the input/output data.
@@ -648,14 +652,14 @@ def run_bias(
             model_predicted_label_config (:class:`~sagemaker.clarify.ModelPredictedLabelConfig`):
                 Config of how to extract the predicted label from the model output.
             pre_training_methods (str or list[str]): Selector of a subset of potential metrics:
-                ["`CI <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-ci.html>`_",
-                "`DPL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-dpl.html>`_",
-                "`KL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-kl.html>`_",
-                "`JS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-js.html>`_",
-                "`LP <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-lp.html>`_",
-                "`TVD <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-tvd.html>`_",
-                "`KS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-ks.html>`_",
-                "`CDDL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-cdd.html>`_"].
+                ["`CI <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-bias-metric-class-imbalance.html>`_",
+                "`DPL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-true-label-imbalance.html>`_",
+                "`KL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-kl-divergence.html>`_",
+                "`JS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-jensen-shannon-divergence.html>`_",
+                "`LP <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-lp-norm.html>`_",
+                "`TVD <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-total-variation-distance.html>`_",
+                "`KS <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-kolmogorov-smirnov.html>`_",
+                "`CDDL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-data-bias-metric-cddl.html>`_"].
                 Defaults to computing all.
             post_training_methods (str or list[str]): Selector of a subset of potential metrics:
                 ["`DPPL <https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-post-training-bias-metric-dppl.html>`_"
@@ -682,7 +686,7 @@ def run_bias(
             experiment_config (dict[str, str]): Experiment management configuration.
                 Dictionary contains three optional keys:
                 'ExperimentName', 'TrialName', and 'TrialComponentDisplayName'.
-        """
+        """  # noqa E501
         analysis_config = data_config.get_config()
         analysis_config.update(bias_config.get_config())
         analysis_config["predictor"] = model_config.get_predictor_config()

src/sagemaker/dataset_definition/inputs.py

@@ -99,9 +99,9 @@ class DatasetDefinition(ApiObject):
             Definition inputs to run a processing job. LocalPath is an absolute path to the input
             data. This is a required parameter when `AppManaged` is False (default).
         redshift_dataset_definition
-            (:class:`~sagemaker.dataset_definition.RedshiftDatasetDefinition`): Redshift
+            (:class:`~sagemaker.dataset_definition.inputs.RedshiftDatasetDefinition`): Redshift
             dataset definition.
-        athena_dataset_definition (:class:`~sagemaker.dataset_definition.AthenaDatasetDefinition`):
+        athena_dataset_definition (:class:`~sagemaker.dataset_definition.inputs.AthenaDatasetDefinition`):
             Configuration for Athena Dataset Definition input.
     """
 

src/sagemaker/processing.py

@@ -1065,9 +1065,9 @@ def __init__(
             s3_data_distribution_type (str): Valid options are "FullyReplicated"
                 or "ShardedByS3Key".
             s3_compression_type (str): Valid options are "None" or "Gzip".
-            s3_input (:class:`~sagemaker.dataset_definition.S3Input`)
+            s3_input (:class:`~sagemaker.dataset_definition.inputs.S3Input`)
                 Metadata of data objects stored in S3
-            dataset_definition (:class:`~sagemaker.dataset_definition.DatasetDefinition`)
+            dataset_definition (:class:`~sagemaker.dataset_definition.inputs.DatasetDefinition`)
                 DatasetDefinition input
             app_managed (bool): Whether the input are managed by SageMaker or application
         """

src/sagemaker/session.py

@@ -357,6 +357,8 @@ def list_s3_files(self, bucket, key_prefix):
     def default_bucket(self):
         """Return the name of the default bucket to use in relevant Amazon SageMaker interactions.
 
+        This function will create the s3 bucket if it does not exist.
+
         Returns:
             str: The name of the default bucket, which is of the form:
                 ``sagemaker-{region}-{AWS account ID}``.

tests/integ/test_feature_store.py

@@ -312,4 +312,4 @@ def cleanup_feature_group(feature_group: FeatureGroup):
         try:
             feature_group.delete()
         except Exception:
-            pass
+            raise RuntimeError(f"Failed to delete feature group with name {feature_group.name}")

tests/integ/test_processing.py

@@ -162,6 +162,7 @@ def test_sklearn_with_customizations(
     sklearn_processor = SKLearnProcessor(
         framework_version=sklearn_latest_version,
         role=ROLE,
+        command=["python3"],
         instance_type=cpu_instance_type,
         instance_count=1,
         volume_size_in_gb=100,
@@ -287,10 +288,6 @@ def test_sklearn_with_custom_default_bucket(
 
     assert job_description["ProcessingInputs"][0]["InputName"] == "dummy_input"
     assert custom_bucket_name in job_description["ProcessingInputs"][0]["S3Input"]["S3Uri"]
-
-    assert job_description["ProcessingInputs"][2]["InputName"] == "entrypoint"
-    assert custom_bucket_name in job_description["ProcessingInputs"][2]["S3Input"]["S3Uri"]
-
     assert job_description["ProcessingJobName"].startswith("test-sklearn-with-customizations")
 
     assert job_description["ProcessingJobStatus"] == "Completed"
@@ -680,6 +677,7 @@ def test_sklearn_with_network_config(sagemaker_session, sklearn_latest_version,
     sklearn_processor = SKLearnProcessor(
         framework_version=sklearn_latest_version,
         role=ROLE,
+        command=["python3"],
         instance_type=cpu_instance_type,
         instance_count=1,
         sagemaker_session=sagemaker_session,

tests/unit/test_clarify.py

@@ -68,6 +68,15 @@ def test_data_config():
     assert "FullyReplicated" == data_config.s3_data_distribution_type
 
 
+def test_invalid_data_config():
+    with pytest.raises(ValueError, match=r"^Invalid dataset_type"):
+        DataConfig(
+            s3_data_input_path="s3://bucket/inputpath",
+            s3_output_path="s3://bucket/outputpath",
+            dataset_type="whatnot_type",
+        )
+
+
 def test_data_bias_config():
     label_values = [1]
     facet_name = "F1"