You are profiling data by using Azure Machine Learning studio.
You need to detect columns with odd or missing values.
Which statistic should you analyze?
A. Profile
B. Std deviation
C. Error count
D. Type
Show Answer
Correct Answer: C
Explanation: In Azure Machine Learning Studio data profiling, the Error count statistic shows how many values in each column are missing, null, or malformed. This directly helps identify columns with odd or missing values. Other statistics like standard deviation, type, or profile summaries do not specifically highlight missing or invalid data.
Question 211
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You have the following Azure subscriptions and Azure Machine Learning service workspaces:
You need to obtain a reference to the ml-project workspace.
Solution: Run the following Python code:
Does the solution meet the goal?
A. Yes
B. No
Show Answer
Correct Answer: B
Explanation: The proposed Python code does not meet the goal because obtaining a reference to an existing Azure ML workspace requires either calling Workspace.get(...) or using the Workspace constructor with the required parameters. The constructor requires at least subscription_id, resource_group, and workspace_name. Since the shown solution omits required parameters (or uses an incorrect method), it would fail to correctly reference the ml-project workspace.
Question 212
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You use Azure Machine Learning designer to load the following datasets into an experiment:
Dataset1 -
Dataset2 -
You need to create a dataset that has the same columns and header row as the input datasets and contains all rows from both input datasets.
Solution: Use the Execute Python Script module.
Does the solution meet the goal?
A. Yes
B. No
Show Answer
Correct Answer: A
Explanation: The Execute Python Script module in Azure Machine Learning designer can accept multiple input datasets and use Python (for example, pandas concat) to combine them into a single output dataset. This allows creating a dataset with the same columns and header row and containing all rows from both input datasets. Therefore, the solution does meet the stated goal, even if simpler modules (such as Add Rows) could also achieve it.
Question 213
HOTSPOT
-
You must use an Azure Data Science Virtual Machine (DSVM) as a compute target.
You need to attach an existing DSVM to the workspace by using the Azure Machine Learning SDK for Python.
How should you complete the following code segment? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: attach_configuration
attach
Explanation: To attach an existing Azure DSVM, you first create a RemoteCompute attach configuration using attach_configuration with the VM resource ID and SSH details, then attach it to the workspace using ComputeTarget.attach.
Question 215
You use differential privacy to ensure your reports are private.
The calculated value of the epsilon for your data is 1.8.
You need to modify your data to ensure your reports are private.
Which epsilon value should you accept for your data?
A. between 0 and 1
B. between 2 and 3
C. between 3 and 10
D. more than 10
Show Answer
Correct Answer: A
Explanation: In differential privacy, smaller epsilon values provide stronger privacy guarantees. Since the current epsilon is 1.8 and you need to ensure privacy, you should reduce epsilon to a stricter range. An epsilon between 0 and 1 is generally considered to provide strong privacy, whereas larger values weaken privacy.
Question 216
You are implementing hyperparameter tuning by using Bayesian sampling for a model training from a notebook. The notebook is in an Azure Machine Learning workspace that uses a compute cluster with 20 nodes.
The code implements Bandit termination policy with slack factor set to 0.2 and the HyperDriveConfig class instance with max_concurrent_runs set to 10.
You must increase effectiveness of the tuning process by improving sampling convergence.
You need to select which sampling convergence to use.
What should you select?
A. Set the value of slack factor of early_termination_policy to 09.
B. Set the value of max_concurrent_runs of HyperDriveConfig to 4.
C. Set the value of slack factor of early_termination_policy to 0.1.
D. Set the value of max_concurrent_runs of HyperDriveConfig to 20.
Show Answer
Correct Answer: B
Explanation: Bayesian sampling improves convergence by learning from the results of completed runs. Running too many experiments in parallel reduces this benefit because many runs start before prior results are available. Reducing max_concurrent_runs allows each new trial to leverage more prior information, improving sampling convergence. Changing the slack factor affects early termination behavior, not Bayesian convergence.
Question 217
HOTSPOT
-
You use Azure Machine Learning to implement hyperparameter tuning.
Training runs must terminate when the primary metric is lowered by 25 percent or more compared to the best performing run.
You need to configure an early termination policy to terminate training jobs.
Which values should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Explanation: The Bandit early termination policy compares each run’s primary metric to the best performing run. Using a slack_factor allows terminating runs whose metric drops by a specified ratio. A 25% or greater reduction relative to the best run corresponds to using a slack_factor (e.g., 0.75).
Question 218
You are developing a two-step Azure Machine Learning pipeline by using the Azure Machine Learning SDK for Python.
You need to register the output of the pipeline as a new version of a named dataset after the run has been completed.
What should you implement?
A. the as_input method of the OutputDatasetConfig class
B. the register_on_complete method of the OutputDatasetConfig class
C. the as_mount method of the DatasetConsumptionConfig class
D. the as_download method of the DatasetConsumptionConfig class
Show Answer
Correct Answer: B
Explanation: To register the output of an Azure Machine Learning pipeline as a new version of a named dataset after the run completes, you must use OutputDatasetConfig.register_on_complete(). This method explicitly registers the pipeline output as a dataset upon successful run completion. The other options relate to consuming datasets (as_input, as_mount, as_download) rather than registering outputs.
Question 219
HOTSPOT
-
You create a list of movie descriptions in text data format.
You must analyze the movie descriptions with automated machine learning.
You need to use the Azure Machine Learning for Python SDK v1 to configure a job with the specific natural language processing (NLP) task function for AutoML jobs.
Which functions should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Classify as either comedy or romantic:
text_classification()
Classify as comedy, romantic, or both:
text_classification_multilabel()
Extract locations:
text_ner()
Explanation: Binary labels use standard text classification, multiple simultaneous labels require multilabel classification, and extracting entities like locations uses named entity recognition (NER).
Question 221
You are authoring a notebook in Azure Machine Learning studio.
You must install packages from the notebook into the currently running kernel. The installation must be limited to the currently running kernel only.
You need to install the packages.
Which magic function should you use?
A. !pip
B. %pip
C. !conda
D. %load
Show Answer
Correct Answer: B
Explanation: In Azure Machine Learning and Jupyter-based notebooks, the %pip magic installs packages into the currently running kernel and ensures they are immediately available to that kernel only. This is the recommended approach for kernel-scoped installations. Using !pip or !conda runs a shell command that may target a different Python environment, and %load is unrelated to package installation.
$19
Get all 477 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
