Microsoft DP-100 Online Practice Questions and Exam Preparation

Microsoft DP-100 Online Questions & Answers

• Question 461:

  You have a Jupyter Notebook that contains Python code that is used to train a model.

  You must create a Python script for the production deployment. The solution must minimize code maintenance.

  Which two actions should you perform? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. Refactor the Jupyter Notebook code into functions
  B. Save each function to a separate Python file
  C. Define a main() function in the Python script
  D. Remove all comments and functions from the Python script
  A. Refactor the Jupyter Notebook code into functions
  C. Define a main() function in the Python script

  ---

  Explanation

  C: Python main function is a starting point of any program. When the program is run, the python interpreter runs the code sequentially. Main function is executed only when it is run as a Python program.

  A: Refactoring, code style and testing

  The first step is to modularise the notebook into a reasonable folder structure, this effectively means to convert files from .ipynb format to .py format, ensure each script has a clear distinct purpose and organise these files in a coherent way.

  Once the project is nicely structured we can tidy up or refactor the code.

  https://www.guru99.com/learn-python-main-function-with-examples-understand-main.html

  https://towardsdatascience.com/from-jupyter-notebook-to-deployment-a-straightforward-example-1838c203a437

• Question 462:

  You are in the process of creating a machine learning model. Your dataset includes rows with null and missing values.

  You plan to make use of the Clean Missing Data module in Azure Machine Learning Studio to detect and fix the null and missing values in the dataset.

  Recommendation: You make use of the Custom substitution value option.

  Will the requirements be satisfied?

  A. Yes
  B. No
  A. Yes

• Question 463:

  DRAG DROP

  You provision an Azure Machine Learning workspace in a new Azure subscription.

  You need to attach Azure Databricks as a compute resource from the Azure Machine Learning workspace.

  Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

  Select and Place:

  

  

  ---

  Explanation:

  Step 1: From Azure Portal, create an Azure Databricks service.

  Use the portal to create an Azure Databricks workspace 1. In the Azure portal, select Create a resource > Analytics > Azure Databricks.

  2. Under Azure Databricks Service, provide the values to create a Databricks workspace. (Step 1) 3. Select Review + Create, and then Create. The workspace creation takes a few minutes. (Step 2)

  Step 2: From Azure portal, launch an Azure Databricks workspace.

  Azure Databricks

  Azure Databricks is an Apache Spark-based environment in the Azure cloud. It can be used as a compute target with an Azure Machine Learning pipeline.

  Azure Machine Learning cannot create an Azure Databricks compute target. Instead, you must create an Azure Databricks workspace, and then attach it to your Azure Machine Learning workspace.

  Step 3: From the an Azure Databricks workspace, generate a personal access token.

  Step 4: From Azure portal, add an attached compute resource.

  To attach Azure Databricks as a compute target, provide the following information:

  Databricks compute name: The name you want to assign to this compute resource.

  Databricks workspace name: The name of the Azure Databricks workspace.

  Databricks access token: The access token used to authenticate to Azure Databricks. (Step 2)

  Incorrect:

  * From Azure Machine Learning Studio, add an inference cluster

  https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-attach-compute-targets

  https://learn.microsoft.com/en-us/azure/databricks/getting-started/

• Question 464:

  You manage an Azure Machine Learning workspace by using the Azure CLI ml extension v2.

  You need to define a YAML schema to create a compute cluster.

  Which schema should you use?

  A. https://azuremlschemas.azureedge.net/latest/computdnstarKeichema.json
  B. https://azuremlschemas.azureedge.net/latest/amlCompute.schemajson
  C. https://azuremlschemas.azureedge.net/latest/vmCompute.schema.json
  D. https://azuremlschemas.azureedge.net/latest/kubernetesCompute.schema.json
  B. https://azuremlschemas.azureedge.net/latest/amlCompute.schemajson

• Question 465:

  HOTSPOT

  You are using the Azure Machine Learning designer to transform a dataset containing the census data of all nations.

  You must use the Split Data component to separate the dataset into two datasets. The first dataset must contain the census data of the United States. The second dataset must include the census data of the remaining nations.

  You need to configure the component to create the datasets.

  Which configuration values should you use? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

• Question 466:

  You need to implement a new cost factor scenario for the ad response models as illustrated in the performance curve exhibit.

  Which technique should you use?

  A. Set the threshold to 0.5 and retrain if weighted Kappa deviates +/- 5% from 0.45.
  B. Set the threshold to 0.05 and retrain if weighted Kappa deviates +/- 5% from 0.5.
  C. Set the threshold to 0.2 and retrain if weighted Kappa deviates +/- 5% from 0.6.
  D. Set the threshold to 0.75 and retrain if weighted Kappa deviates +/- 5% from 0.15.
  A. Set the threshold to 0.5 and retrain if weighted Kappa deviates +/- 5% from 0.45.

  ---

  Explanation

  Scenario:

  Performance curves of current and proposed cost factor scenarios are shown in the following diagram:

  

  The ad propensity model uses a cut threshold is 0.45 and retrains occur if weighted Kappa deviated from 0.1 +/- 5%.

• Question 467:

  You train and publish a machine learning model.

  You need to run a pipeline that retrains the model based on a trigger from an external system.

  What should you configure?

  A. Azure Data Catalog
  B. Azure Batch
  C. Azure Logic App
  C. Azure Logic App

  ---

  Explanation

  An Azure Logic App allows for more complex triggering logic or behavior.

  To use an Azure Logic App to trigger a Machine Learning pipeline, you'll need the REST endpoint for a published Machine Learning pipeline. Create and publish your pipeline. Then find the REST endpoint of your PublishedPipeline by using the pipeline ID.

  # You can find the pipeline ID in Azure Machine Learning studio published_pipeline = PublishedPipeline.get(ws, id="<pipeline-id-here>") published_pipeline.endpoint

  Note: Azure Logic Apps is a cloud platform where you can create and run automated workflows with little to no code. By using the visual designer and selecting from prebuilt operations, you can quickly build a workflow that integrates and manages your apps, data, services, and systems.

  Azure Logic Apps simplifies the way that you connect legacy, modern, and cutting-edge systems across cloud, on premises, and hybrid environments and provides low-code-no-code tools for you to develop highly scalable integration solutions for your enterprise and business-to-business (B2B) scenarios.

  https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-trigger-published-pipeline

  https://learn.microsoft.com/en-us/azure/logic-apps/logic-apps-overview

• Question 468:

  HOTSPOT

  You have machine learning models produce unfair predictions across sensitive features.

  You must use a post-processing technique to apply a constraint to the models to mitigate their unfairness.

  You need to select a post-processing technique and model type.

  What should you use? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

• Question 469:

  You are creating a new Azure Machine Learning pipeline using the designer.

  The pipeline must train a model using data in a comma-separated values (CSV) file that is published on a website. You have not created a dataset for this file.

  You need to ingest the data from the CSV file into the designer pipeline using the minimal administrative effort.

  Which module should you add to the pipeline in Designer?

  A. Convert to CSV
  B. Enter Data Manually
  C. Import Data
  D. Dataset
  C. Import Data

  ---

  Explanation

  https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-your-first-pipeline

• Question 470:

  HOTSPOT

  You create multiple machine learning models by using automated machine learning.

  You need to configure a primary metric for each use case.

  Which metrics should you configure? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  Explanation:

  Box 1: r2_score

  Bug resolution time in regression task r2_score, example use case(s): Airline delay, Salary estimation, Bug resolution time

  Incorrect:

  AUC_weighted, example use case(s): Fraud detection, Image classification, Anomaly detection/spam detection

  Box 2: accuracy

  Sentiment analysis in a classification task accuracy, example use case(s): Image classification, Sentiment analysis, Churn prediction

  Incorrect:

  Spearman_correlation

  If the rank, instead of the exact value is of interest, spearman_correlation can be a better choice.

  https://learn.microsoft.com/en-us/azure/machine-learning/how-to-configure-auto-train