airflow-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] ashb commented on a change in pull request #4091: [AIRFLOW-2524] Update SageMaker hook, operator and sensor for training, tuning and transform
Date Wed, 31 Oct 2018 19:40:50 GMT
ashb commented on a change in pull request #4091: [AIRFLOW-2524] Update SageMaker hook, operator
and sensor for training, tuning and transform
URL: https://github.com/apache/incubator-airflow/pull/4091#discussion_r229840272
 
 

 ##########
 File path: airflow/contrib/operators/sagemaker_training_operator.py
 ##########
 @@ -0,0 +1,97 @@
+# -*- coding: utf-8 -*-
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License 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.
+
+from airflow.contrib.hooks.aws_hook import AwsHook
+from airflow.contrib.operators.sagemaker_base_operator import SageMakerBaseOperator
+from airflow.utils.decorators import apply_defaults
+from airflow.exceptions import AirflowException
+
+
+class SageMakerTrainingOperator(SageMakerBaseOperator):
+    """
+    Initiate a SageMaker training job.
+
+    This operator returns The ARN of the training job created in Amazon SageMaker.
+
+    :param config: The configuration necessary to start a training job (templated)
+    :type config: dict
+    :param aws_conn_id: The AWS connection ID to use.
+    :type aws_conn_id: str
+    :param wait_for_completion: if the operator should block until training job finishes
+    :type wait_for_completion: bool
+    :param print_log: if the operator should print the cloudwatch log during training
+    :type print_log: bool
+    :param check_interval: if wait is set to be true, this is the time interval
+        in seconds which the operator will check the status of the training job
+    :type check_interval: int
+    :param max_ingestion_time: if wait is set to be true, the operator will fail
+        if the training job hasn't finish within the max_ingestion_time in seconds
+        (Caution: be careful to set this parameters because training can take very long)
+        Setting it to None implies no timeout.
+    :type max_ingestion_time: int
+    """
+
+    integer_fields = [
+        ['ResourceConfig', 'InstanceCount'],
+        ['ResourceConfig', 'VolumeSizeInGB'],
+        ['StoppingCondition', 'MaxRuntimeInSeconds']
+    ]
+
+    @apply_defaults
+    def __init__(self,
+                 config,
+                 wait_for_completion=True,
+                 print_log=True,
+                 check_interval=30,
+                 max_ingestion_time=None,
+                 *args, **kwargs):
+        super(SageMakerTrainingOperator, self).__init__(config=config,
+                                                        *args, **kwargs)
+
+        self.wait_for_completion = wait_for_completion
+        self.print_log = print_log
+        self.check_interval = check_interval
+        self.max_ingestion_time = max_ingestion_time
+
+    def expand_role(self):
+        if 'RoleArn' in self.config:
+            hook = AwsHook()
 
 Review comment:
   This should have `self.aws_conn_id` passed to it:
   ```suggestion
               hook = AwsHook(self.aws_conn_id)
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message