Sample Questions for DP-100 Certification Exam: Designing and Implementing Data Science Solutions on Microsoft Azure

Hello Readers! Here are some sample questions for Designing and Implementing Data Science Solutions on Microsoft Azure.

After going through the course material, answer the below sample questions, and test your knowledge. The correct answers are available at the end.

Here goes the Quiz:

1. Which of the following provides a web interface for managing assets in a workspace?
   a. Azure Machine Learning studio
   b. Azure Cognitive Services
   c. Azure Synapse Analytics
2. You want to use automated machine learning with car sales data to train a machine learning model that predicts the price of a car based on its make, model, engine size, and mileage. What task type should you select?
   a. Classification
   b. Regression
   c. Time-series
3. Riya is using the Azure Machine Learning Python SDK to write code for an experiment.
   She needs to record metrics from each run of the experiment and be able to retrieve them easily from each run.
   What should Riya do?
   a. Add print statements to the experiment code to print the metrics.
   b. Use the log methods of the Run class to record named metrics.
   c. Save the experiment data in the outputs folder.
4. Mahesh has a reference to a Workspace named ws.
   Which code retrieves the default datastore for the workspace?
   a. default_ds = ws.get_default_datastore()
   b. default_ds = Datastore.get(ws, ‘default’)
   c. default_ds = ws.Datastores[0]
5. Which ScriptRunConfig parameter causes the script to run on a compute cluster named train-cluster?
   a. environment=’train-cluster’
   b. compute_target=’train-cluster’
   c. arguments=[‘–AmlCluster’, ‘train-cluster’]
6. What type of object should you use to pass data between pipeline steps?
   a. Datastore
   b. Dataset
   c. PipelineData
7. You want to implement a batch inference pipeline that distributes scoring on multiple nodes.
   Which kind of pipeline step should you use?
   a. PythonScriptStep
   b. AdlaStep
   c. ParallelRunStep
8. You want to use automated machine learning to find the model with the best AUC_weighted metric.
   Which parameter of the AutoMLConfig object should you set?
   a. task=’AUC_weighted’
   b. label_column_name= ‘AUC_weighted’
   c. primary_metric=’AUC_weighted’
9. You are training a binary classification model to support admission approval decisions for a college degree program.
   How can you evaluate if the model is fair, and doesn’t discriminate based on ethnicity?
   a. Evaluate each trained model with a validation dataset and use the model with the highest accuracy score.
   b. Remove the ethnicity feature from the training dataset.
   c. Compare disparity between selection rates and performance metrics across ethnicities.
10. You previously trained a model using a training dataset. You want to detect any data drift in the new data collected since the model was trained.
    What should you do?
    a. Create a new dataset using the new data and a timestamp column and create a data drift monitor that uses the training dataset as a baseline and the new dataset as a target.
    b. Create a new version of the dataset using only the new data and retrain the model.
    c. Add the new data to the existing dataset and enable Application Insights for the service where the model is deployed.

Check the correct answers here:

1. a.
   Explanation: Azure Machine Learning Studio provides a web-based portal for managing resources in a workspace.
2. b.
   Explanation: Because the model must predict a numeric value with no time-series element, you should select the Regression task.
3. b
   Explanation: To record metrics in an experiment run, use the Run.log method
4. a.
   Explanation: To get the default datastore, use the Workspace.get_default_datasetore method.
5. b.
   Explanation: Use the compute_target parameter to set the compute target.
6. c.
   Explanation: Use a PipelineData to pass data between steps.
7. c.
   Explanation: You should use a ParallelRunStep step to run the scoring script in parallel.
8. c.
   Explanation: To specify the target metric, use the primary_metric parameter.
9. c.
   Explanation: By using ethnicity as a sensitive field, and comparing disparity between selection rates and performance metrics for each ethnicity value, you can evaluate the fairness of the model.
10. a.
    Explanation: To track changing data trends, create a data drift monitor that uses the training data as a baseline and the new data as a target.

More sample questions are coming up, so keep checking. Please share your feedback in the below comments section.

Check out the TestPrep material here.

Disclaimer:

These questions are NOT appearing in the certification exam. I personally or CloudThat do not have any official tie-up with Microsoft regarding the certification or the kind of questions asked. These are my best guesses for the kind of questions to expect with Microsoft in general and with the examination.

Enroll in the Designing and Implementing Data Science Solutions on Microsoft Azure: DP-100 course and grab your Microsoft Badge soon.

Feel free to drop any questions in the comment box, I would love to address them. I hope you enjoyed the article. Best of luck!