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_r229663263
##########
File path: airflow/contrib/hooks/sagemaker_hook.py
##########
@@ -16,299 +16,793 @@
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
-import copy
+import tarfile
+import tempfile
import time
+import os
+import collections
+import functools
+from datetime import datetime
+
+import botocore.config
from botocore.exceptions import ClientError
from airflow.exceptions import AirflowException
from airflow.contrib.hooks.aws_hook import AwsHook
from airflow.hooks.S3_hook import S3Hook
+class LogState(object):
+ STARTING = 1
+ WAIT_IN_PROGRESS = 2
+ TAILING = 3
+ JOB_COMPLETE = 4
+ COMPLETE = 5
+
+
+# Position is a tuple that includes the last read timestamp and the number of
items that were read
+# at that time. This is used to figure out which event to start with on the
next read.
+Position = collections.namedtuple('Position', ['timestamp', 'skip'])
+
+
+def argmin(arr, f):
+ """Return the index, i, in arr that minimizes f(arr[i])"""
+ m = None
+ i = None
+ for idx, item in enumerate(arr):
+ if item is not None:
+ if m is None or f(item) < m:
+ m = f(item)
+ i = idx
+ return i
+
+
+def some(arr):
+ """Return True iff there is an element, a, of arr such that a is not
None"""
+ return functools.reduce(lambda x, y: x or (y is not None), arr, False)
+
+
+def secondary_training_status_changed(current_job_description,
prev_job_description):
+ """
+ Returns true if training job's secondary status message has changed.
+
+ :param current_job_description: Current job description, returned from
DescribeTrainingJob call.
+ :type current_job_description: dict
+ :param prev_job_description: Previous job description, returned from
DescribeTrainingJob call.
+ :type prev_job_description: dict
+
+ :return: Whether the secondary status message of a training job changed or
not.
+ """
+ current_secondary_status_transitions =
current_job_description.get('SecondaryStatusTransitions')
+ if current_secondary_status_transitions is None or
len(current_secondary_status_transitions) == 0:
+ return False
+
+ prev_job_secondary_status_transitions =
prev_job_description.get('SecondaryStatusTransitions') \
+ if prev_job_description is not None else None
+
+ last_message = prev_job_secondary_status_transitions[-1]['StatusMessage'] \
+ if prev_job_secondary_status_transitions is not None \
+ and len(prev_job_secondary_status_transitions) > 0 else ''
+
+ message =
current_job_description['SecondaryStatusTransitions'][-1]['StatusMessage']
+
+ return message != last_message
+
+
+def secondary_training_status_message(job_description, prev_description):
+ """
+ Returns a string contains start time and the secondary training job status
message.
+
+ :param job_description: Returned response from DescribeTrainingJob call
+ :type job_description: dict
+ :param prev_description: Previous job description from DescribeTrainingJob
call
+ :type prev_description: dict
+
+ :return: Job status string to be printed.
+ """
+
+ if job_description is None or
job_description.get('SecondaryStatusTransitions') is None\
+ or len(job_description.get('SecondaryStatusTransitions')) == 0:
+ return ''
+
+ prev_description_secondary_transitions =
prev_description.get('SecondaryStatusTransitions')\
+ if prev_description is not None else None
+ prev_transitions_num = len(prev_description['SecondaryStatusTransitions'])\
+ if prev_description_secondary_transitions is not None else 0
+ current_transitions = job_description['SecondaryStatusTransitions']
+
+ transitions_to_print = current_transitions[-1:] if
len(current_transitions) == prev_transitions_num else \
+ current_transitions[prev_transitions_num - len(current_transitions):]
+
+ status_strs = []
+ for transition in transitions_to_print:
+ message = transition['StatusMessage']
+ time_str = datetime.utcfromtimestamp(
+
time.mktime(job_description['LastModifiedTime'].timetuple())).strftime('%Y-%m-%d
%H:%M:%S')
Review comment:
Local as in in what ever timezone of the system this code is running on?
I'll find a better way.
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
