Remove MetricDefinition lookup via tuning job in TrainingJobAnalytics (#485)

Author: apacker

CHANGELOG.rst

@@ -21,7 +21,8 @@ CHANGELOG
 * enhancement: Frameworks: update warning for not setting framework_version as we aren't planning a breaking change anymore
 * enhancement: Session: remove hardcoded 'training' from job status error message
 * bug-fix: Updated Cloudwatch namespace for metrics in TrainingJobsAnalytics
-
+* bug-fix: Changes to use correct s3 bucket and time range for dataframes in TrainingJobAnalytics.
+* enhancement: Remove MetricDefinition lookup via tuning job in TrainingJobAnalytics
 
 1.14.1
 ======

src/sagemaker/analytics.py

@@ -20,7 +20,7 @@
 from six import with_metaclass
 
 from sagemaker.session import Session
-from sagemaker.utils import DeferredError, extract_name_from_job_arn
+from sagemaker.utils import DeferredError
 
 try:
     import pandas as pd
@@ -310,18 +310,9 @@ def _add_single_metric(self, timestamp, metric_name, value):
     def _metric_names_for_training_job(self):
         """Helper method to discover the metrics defined for a training job.
         """
-        # First look up the tuning job
         training_description = self._sage_client.describe_training_job(TrainingJobName=self._training_job_name)
-        tuning_job_arn = training_description.get('TuningJobArn', None)
-        if not tuning_job_arn:
-            raise ValueError(
-                "No metrics available. Training Job Analytics only available through Hyperparameter Tuning Jobs"
-            )
-        tuning_job_name = extract_name_from_job_arn(tuning_job_arn)
-        tuning_job_description = self._sage_client.describe_hyper_parameter_tuning_job(
-            HyperParameterTuningJobName=tuning_job_name
-        )
-        training_job_definition = tuning_job_description['TrainingJobDefinition']
-        metric_definitions = training_job_definition['AlgorithmSpecification']['MetricDefinitions']
+
+        metric_definitions = training_description['AlgorithmSpecification']['MetricDefinitions']
         metric_names = [md['Name'] for md in metric_definitions]
+
         return metric_names

tests/unit/test_estimator.py

@@ -824,28 +824,21 @@ def test_generic_training_job_analytics(sagemaker_session):
     sagemaker_session.sagemaker_client.describe_training_job = Mock(name='describe_training_job', return_value={
         'TuningJobArn': 'arn:aws:sagemaker:us-west-2:968277160000:hyper-parameter-tuning-job/mock-tuner',
         'TrainingStartTime': 1530562991.299,
-    })
-    sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(
-        name='describe_hyper_parameter_tuning_job',
-        return_value={
-            'TrainingJobDefinition': {
-                "AlgorithmSpecification": {
-                    "TrainingImage": "some-image-url",
-                    "TrainingInputMode": "File",
-                    "MetricDefinitions": [
-                        {
-                            "Name": "train:loss",
-                            "Regex": "train_loss=([0-9]+\\.[0-9]+)"
-                        },
-                        {
-                            "Name": "validation:loss",
-                            "Regex": "valid_loss=([0-9]+\\.[0-9]+)"
-                        }
-                    ]
+        "AlgorithmSpecification": {
+            "TrainingImage": "some-image-url",
+            "TrainingInputMode": "File",
+            "MetricDefinitions": [
+                {
+                    "Name": "train:loss",
+                    "Regex": "train_loss=([0-9]+\\.[0-9]+)"
+                },
+                {
+                    "Name": "validation:loss",
+                    "Regex": "valid_loss=([0-9]+\\.[0-9]+)"
                 }
-            }
-        }
-    )
+            ]
+        },
+    })
 
     e = Estimator(IMAGE_NAME, ROLE, INSTANCE_COUNT, INSTANCE_TYPE, output_path=OUTPUT_PATH,
                   sagemaker_session=sagemaker_session)