Exam DP-100 topic 4 question 3 discussion

Actual exam question from Microsoft's DP-100

Question #: 3
Topic #: 4

You create a batch inference pipeline by using the Azure ML SDK. You run the pipeline by using the following code: from azureml.pipeline.core import Pipeline from azureml.core.experiment import Experiment pipeline = Pipeline(workspace=ws, steps=[parallelrun_step]) pipeline_run = Experiment(ws, 'batch_pipeline').submit(pipeline)
You need to monitor the progress of the pipeline execution.
What are two possible ways to achieve this goal? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.

A. Run the following code in a notebook:
B. Use the Inference Clusters tab in Machine Learning Studio.
C. Use the Activity log in the Azure portal for the Machine Learning workspace.
D. Run the following code in a notebook:
E. Run the following code and monitor the console output from the PipelineRun object:

Show Suggested Answer

Suggested Answer: DE 🗳️
A batch inference job can take a long time to finish. This example monitors progress by using a Jupyter widget. You can also manage the job's progress by using:
✑ Azure Machine Learning Studio.
✑ Console output from the PipelineRun object.
from azureml.widgets import RunDetails
RunDetails(pipeline_run).show()
pipeline_run.wait_for_completion(show_output=True)
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-use-parallel-run-step#monitor-the-parallel-run-job

by JTWang at Oct. 21, 2022, 7:35 a.m.

Comments

Submit Cancel

Arend78

Highly Voted 1 year ago

After a lot of searching I have found examples of both D and E. If I understand correctly, both types of logging point to the Portal with a link, where the run details can be inspected D: from azureml.widgets import RunDetails RunDetails(pipeline_run).show() https://github.com/Azure/azureml-examples/blob/main/v1/python-sdk/tutorials/automl-with-azureml/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb E: pipeline = Pipeline(workspace=ws, steps=[batch_score_step]) pipeline_run = Experiment(ws, "Tutorial-Batch-Scoring").submit(pipeline) # This will output information of the pipeline run, including the link to the details page of **portal**. Wait the run for completion and show output log to console pipeline_run.wait_for_completion(show_output=True) https://github.com/Azure/MachineLearningNotebooks/blob/master/tutorials/machine-learning-pipelines-advanced/tutorial-pipeline-batch-scoring-classification.ipynb

upvoted 9 times

Arend78

1 year ago

The solution under D uses a Widget in a Notebook to track the Pipeline progress

upvoted 2 times

Arend78

1 year ago

https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/machine-learning-pipelines/parallel-run show the use of both answers together

upvoted 1 times

...

JTWang

Most Recent 1 year, 2 months ago

E is correct. https://learn.microsoft.com/zh-tw/python/api/azureml-pipeline-core/azureml.pipeline.core.run.pipelinerun?view=azure-ml-py D can show status but seems for training model. Question request is batch inference pipleline. But in doc "A widget is asynchronous and provides updates until training finishes." https://learn.microsoft.com/en-us/python/api/azureml-widgets/azureml.widgets.rundetails?view=azure-ml-py

upvoted 1 times

BTAB

11 months, 4 weeks ago

E & D correct. Since it is a batch inference model D will work.

upvoted 1 times

...