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 Apply Transformation module.
Does the solution meet the goal?
A. Yes
B. No
Show Answer
Correct Answer: B
Explanation: The goal is to create a single dataset that contains all rows from both input datasets with the same columns and header row (a union/append operation). The Apply Transformation module does not combine two datasets by appending rows; it applies an existing transformation to data. Therefore, it does not meet the goal.
Question 150
You are using Azure Machine Learning to monitor a trained and deployed model. You implement Event Grid to respond to Azure Machine Learning events.
Model performance has degraded due to model input data changes.
You need to trigger a remediation ML pipeline based on an Azure Machine Learning event.
Which event should you use?
A. RunStatusChanged
B. RunCompleted
C. DatasetDriftDetected
D. ModelDeployed
Show Answer
Correct Answer: C
Explanation: The issue is degraded model performance due to changes in input data, which indicates data drift. Azure Machine Learning emits the DatasetDriftDetected event when dataset drift is detected, and this event is specifically designed to trigger remediation actions such as retraining pipelines. The other events relate to run lifecycle or deployment changes and do not indicate data drift.
Question 151
HOTSPOT
-
You plan to use a curated environment to run Azure Machine Learning training experiments in a workspace.
You need to display all curated environments and their respective packages in the workspace.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: AzureML
python
Explanation: Curated Azure ML environments are identified by names starting with "AzureML". Package details are accessed through the environment’s Python section, where conda_dependencies can be serialized to list all installed packages.
Question 152
You create an Azure Machine Learning workspace. You train an MLflow-formatted regression model by using tabular structured data.
You must use a Responsible AI dashboard to access the model.
You need to use the Azure Machine Learning studio UI to generate the Responsible AI dashboard.
What should you do first?
A. Deploy the model to a managed online endpoint.
B. Register the model with the workspace.
C. Create the model explanations.
D. Convert the model from the MLflow format to a custom format.
Show Answer
Correct Answer: B
Explanation: To generate a Responsible AI dashboard in Azure Machine Learning studio, the model must first be registered in the workspace. The Responsible AI dashboard operates on registered models and associated datasets; deployment, explanations, or format conversion are not prerequisites for creating the dashboard.
Question 153
HOTSPOT
-
You train a machine learning model by using Azure Machine Learning.
You use the following training script in Python to log an accuracy value:
You must use a Python script to define a sweep job.
You need to provide the primary metric and goal you want hyperparameter tuning to optimize.
How should you complete the Python script? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Explanation: The training script logs a metric named "accuracy", so it must be used as the primary metric. Since higher accuracy is better, the sweep goal should be to maximize it.
Question 154
You use Azure Machine Learning studio to analyze a dataset containing a decimal column named column1.
You need to verify that the column1 values are normally distributed.
Which statistic should you use?
A. Max
B. Type
C. Profile
D. Mean
Show Answer
Correct Answer: C
Explanation: To verify whether a decimal column is normally distributed, you need to examine the shape of its distribution (for example via histograms and summary distribution metrics). In Azure Machine Learning Studio, the **Profile** statistic provides this distributional overview. Max, Type, and Mean alone do not indicate normality.
Question 155
HOTSPOT -
You create an Azure Machine Learning workspace and a dataset. The dataset includes age values for a large group of diabetes patients. You use the dp_mean function from the SmartNoise library to calculate the mean of the age value. You store the value in a variable named age_mean.
You must output the value of the interval rage of released mean values that will be returned 95 percent of the time.
You need to complete the code.
Which code values 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: get_accuracy
0.05
Explanation: To output the 95% interval range of released DP mean values, use the accuracy API. A 95% confidence interval corresponds to alpha = 0.05 (1 − 0.95). The dp_mean result exposes this via get_accuracy(alpha).
Question 156
You need to evaluate the potential risk of exposing personal information based on the values of epsilon and delta for differential privacy. You create a privacy report.
What does an epsilon value greater than one represent?
A. The privacy of data is preserved and there is limited impact on data accuracy.
B. There is a high risk of exposing the actual data that is uses to generate the report.
C. The data used in the report is very noisy.
Show Answer
Correct Answer: B
Explanation: In differential privacy, epsilon (ε) controls the privacy–utility tradeoff. Smaller epsilon values mean stronger privacy guarantees due to more noise being added. An epsilon value greater than one indicates weaker privacy protection, meaning the output is closer to the original data and therefore carries a higher risk of exposing sensitive or personal information used to generate the report.
Question 157
HOTSPOT
-
You create an Azure Machine Learning dataset. You use the Azure Machine Learning designer to transform the dataset by using an Execute Python Script component and custom code.
You must upload the script and associated libraries as a script bundle.
You need to configure the Execute Python Script component.
Which configurations 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: Input port: right
Script bundle format: zip
Explanation: The Execute Python Script component expects external scripts and libraries to be connected to the Script Bundle port, which is the right input port. Script bundles must be uploaded as a ZIP file to include custom code and dependencies.
Question 158
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 correctly obtain a reference to the Azure Machine Learning workspace. To uniquely reference an existing workspace, the Azure ML SDK requires sufficient identification details such as subscription ID and resource group, or loading them from a config.json file using Workspace.from_config(). Using Workspace.get with only a name (or incorrect parameters) is insufficient in this scenario, especially when multiple subscriptions or workspaces exist. Therefore, the solution does not meet the goal.
$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.
