def process_event(event):
if 'runId' not in event:
raise ValueError('Malformed Event. Run Id does not exits. Event: %s',
event)
logger.info(f'Event Details: {event}')
exp = Experiment(workspace=get_workspace(), name=event['experimentName'])
run = Run(exp, event['runId'])
run_details = run.get_details()
app_insight_connection = os.environ.get('APPINSIGHTS_CONNECTION_STRING')
if 'endTimeUtc' in run_details:
logger.info(f'Run details: {run_details}')
"""
Just for sample here we are saving metrics to Application Insight after collecting details from 'run_details'
& 'event'. You can store it to any other storage/database as well.
"""
save_to_app_insight(to_run_metrics(run_details, event),
app_insight_connection)
else:
logging.info(
'Ignoring event. As step/pipeline is still running. Event: %s',
event)
deploy_model = PythonScriptStep(script_name="src/deploy_model.py",
compute_target=compute_target,
runconfig=aml_run_config)
steps = [train_model, deploy_model]
step_seq = StepSequence(steps=steps)
pipeline = Pipeline(workspace=ws, steps=step_seq)
pp = pipeline.publish(
name="TitanicDeploymentPipeline",
description="Training and deployment pipeline for our titanic API.",
version="1.0")
# We can also set up a trigger based schedule using the Datastore class - https://docs.microsoft.com/en-us/azure/machine-learning/how-to-schedule-pipelines#create-a-time-based-schedule
recurrence = ScheduleRecurrence(frequency="Month",
interval=1,
start_time='2020-11-01T00:00:00')
recurring_schedule = Schedule.create(ws,
name="TitanicRetrainingSchedule",
description="Once a month training",
pipeline_id=pp.id,
experiment_name=exp_name,
recurrence=recurrence)
run = pp.submit(ws, experiment_name=exp_name)
run_id = run.id
exp = Experiment(ws, exp_name)
r = Run(exp, run_id)
r.get_details()
model_name = "model_n_estimators_" + str(n) + ".pkl"
filename = "outputs/" + model_name
joblib.dump(value=model, filename=filename)
run.upload_file(name=model_name, path_or_stream=filename)
run.complete()
###############
maximum_acc_runid = None
maximum_acc = None
for run in experiment.get_runs():
run_metrics = run.get_metrics()
run_details = run.get_details()
# each logged metric becomes a key in this returned dict
run_acc = run_metrics["acc"]
run_id = run_details["runId"]
if maximum_acc is None:
maximum_acc = run_acc
maximum_acc_runid = run_id
else:
if run_acc > maximum_acc:
maximum_acc = run_acc
maximum_acc_runid = run_id
print("Best run_id: " + maximum_acc_runid)
print("Best run_id acc: " + str(maximum_acc))
"""
Helper to get run details for debugging
"""
import os
from azureml.core import Workspace, Experiment, Run
from azureml.core.authentication import AzureCliAuthentication
# load workspace
ws = Workspace.from_config(
auth=AzureCliAuthentication(),
path=os.path.join(
os.path.dirname(os.path.realpath(__file__)),
'config.json'
)
)
experiment = Experiment(
workspace=ws,
name="multitask_ssd"
)
run = Run(
experiment,
run_id="a9858223-b3b7-4272-98a4-33bfee9f67e9"
)
print(run.get_details())
# print(run.get_metrics())