Improved 70-774 Item Pool 2021

NEW QUESTION 1
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
You plan to create a predictive analytics solution for credit risk assessment and fraud prediction in Azure Machine Learning. The Machine Learning workspace for the solution will be shared with other users in your organization. You will add assets to projects and conduct experiments in the workspace.
The experiments will be used for training models that will be published to provide scoring from web services. The experiment for fraud prediction will use Machine Learning modules and APIs to train the models and will predict probabilities in an Apache Hadoop ecosystem.
You plan to configure the resources for part of a workflow that will be used to preprocess data from files stored in Azure Blob storage. You plan to use Python to preprocess and store the data in Hadoop.
You need to get the data into Hadoop as quickly as possible.
Which three actions should you perform? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

• A. Create an Azure virtual machine (VM), and then configure MapReduce on the VM.
• B. Create an Azure HDInsight Hadoop cluster.
• C. Create an Azure virtual machine (VM), and then install an IPython Notebook server.
• D. Process the files by using Python to store the data to a Hadoop instance.
• E. Create the Machine learning experiment, and then add an Execute Python Script module.

Answer: BDE

NEW QUESTION 2
You are building a classification experiment in Azure Machine Learning.
You need to ensure that you can use the Evaluate Model module the experiment.
Which two actions should you perform? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

• A. Connect the input of the Score Model modules to the output of the Evaluate Model module.
• B. Connect the input of the Score Model modules to the output of the Train Model modules and the output Split Data modules.
• C. Connect the output of the Score Model modules to the input of the Evaluate Model module.
• D. Connect the output of the Score Model modules to the input of the Train Model modules and the input of the Split Data modules.

Answer: AB

NEW QUESTION 3
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this scries.
Start of repeated scenario
You plan to create a predictive analytics solution for credit risk assessment and fraud prediction in Azure Machine Learning. The Machine Learning workspace for the solution will be shared with other users in your organization. You will add assets to projects and conduct experiments in the workspace.
The experiments will be used for training models that will be published to provide scoring from web services. The experiment for fraud prediction will use Machine Learning modules and APIs to train the models and will predict probabilities in an Apache Hadoop ecosystem.
End of repeated scenario.
You plan to share the Machine Learning workspace with the other users.
You are evaluating whether to assign the User role or the Owner role to several of the users.
Which three actions can be performed by the users who are assigned the User role? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.

• A. Create, open, modify, and delete datasets.
• B. Create, open, modify, and delete experiments.
• C. Invite users to the workspace.
• D. Delete users from the workspace.
• E. Create, open, modify, and delete web services.
• F. Access notebooks.

Answer: CDF

NEW QUESTION 4
The manager of a call center reports that staffing the center is difficult because the number of calls is unpredictable. You have historical data that contains information about the calls.
You need to build an Azure Machine Learning experiment to predict the number of total calls each hour. Which model should you use?

• A. Multiclass Logistic Regression
• B. Boosted Decision Tree Regression
• C. Decision Forest Regression
• D. Poisson Regression

Answer: D

NEW QUESTION 5
You have an Azure Machine Learning experiment.
You discover that a model causes many errors in a production dataset. The model causes only few errors in the training data.
What is the cause of the errors?

• A. overfitting
• B. generalization
• C. underfitting
• D. a simple predictor

Answer: A

NEW QUESTION 6
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
Start of repeated scenario
You plan to use Azure platform tools to detect and analyze food items in smart refrigerators. To provide families with an integrated experience for grocery shopping and cooking, the refrigerators will connect to other smart appliances, such as stoves and microwave ovens, on a LAN.
You plan to build an object recognition model by using the Microsoft Cognitive Toolkit. The object recognition model will receive input from the connected devices and send results to applications.
The training data will be derived from more than 10 TB of images. You will convert the raw images to the sparse format.
End of repeated scenario.
You need to deploy a multiple-service solution that was developed already and published by other users in the Microsoft development community.
What should you use?

• A. the edX Data Science Learning Dashboard
• B. the Data Science Virtual Machine
• C. an Azure Machine Learning experiment
• D. Cortana Intelligence Gallery

Answer: C

NEW QUESTION 7
You need to integrate code and formatted text into an Azure Machine Learning experiment that enables interactive execution.
What should you use?

• A. a Jupyter notebook
• B. Azure Stream Analytics
• C. an Execute Python Script module
• D. an Execute R Script module

Answer: A

NEW QUESTION 8
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 sections, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You are working on an Azure Machine Learning experiment. You have the dataset configured as shown in the following table.

You need to ensure that you can compare the performance of the models and add annotations to the results. Solution: You save the output of the Score Model modules as a combined set, and then use the Project Columns module to select the MAE.
Does this meet the goal?

• A. Yes
• B. No

Answer: AExplanation:References:

Explanation:
https://msdn.microsoft.com/en-us/library/azure/dn905915.aspx

NEW QUESTION 9
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 an Azure ML experiment that contains an intermediate dataset. You need to explore data from the intermediate dataset by using Jupyter.
Solution: You add a web service input to retrieve the data for the data source, and then add the Execute R Script module.
Does this meet the goal?

• A. Yes
• B. No

Answer: B

NEW QUESTION 10
You have an Apache Spark cluster in Azure HDinsight. The cluster includes 200 TB in five Apache Hive tables that have multiple foreign key relationships.
You have an Azure Machine Learning model that was built by using SPARK Accelerated Failure Time (AFT) Survival Regression Model (spark-survreg).
You need to prepare the Hive data into a single table as input for the Machine Learning model. The Hive data must be prepared in the least amount of time possible.
What should you use to prepare the data?

• A. a Hive user-defined function (UDF)
• B. Spark SQL
• C. the GPU
• D. Java Mapreduce jobs

Answer: A

NEW QUESTION 11
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
A travel agency named Margie’s Travel sells airline tickets to customers in the United States.
Margie’s Travel wants you to provide insights and predictions on flight delays. The agency is considering implementing a system that will communicate to its customers as the flight departure nears about possible delays due to weather conditions. The flight data contains the following attributes:
The weather data contains the following attributes: AirportID, ReadingDate (YYYY/MM/DD HH), SkyConditionVisibility, WeatherType, WindSpeed, StationPressure, PressureChange, and HourlyPrecip.
You need to use historical data about on-time flight performance and the weather data to predict whether the departure of a scheduled flight will be delayed by more than 30 minutes.
Which method should you use?

• A. clustering
• B. linear regression
• C. classification
• D. anomaly detection

Answer: C

Explanation:
References:
https://gallery.cortanaintelligence.com/Experiment/Binary-Classification-Flight-delay-prediction-3

NEW QUESTION 12
Note: This question is part of a series of questions that use the same or similar answer choices. An answer choice may be correct for more than one question in the series. Each question is independent of the other questions in this series. Information and details provided in a question apply only to that question.
You process some data by using Azure Machine Learning Studio. You have an intermediate dataset. The dataset has a column that contains date values stored in a format of MM/DD/YYYY.
ft You need to split the column into three separate columns by year, month, and day.
Which module should you use?

• A. Edit Metadata
• B. Normalize Data
• C. Clean Missing Data
• D. Import Data
• E. Execute Python Script
• F. Clip Values
• G. Clip Values
• H. Execute Python Script

Answer: A

NEW QUESTION 13
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 an Azure ML experiment that contains an intermediate dataset. You need to explore data from the intermediate dataset by using Jupyter.
Solution: You add a Convert to ARFF module, and then add the Execute R Script module. Does this meet the goal?

• A. Yes
• B. No

Answer: B

NEW QUESTION 14
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
You plan to create a predictive analytics solution for credit risk assessment and fraud prediction in Azure Machine Learning. The Machine Learning workspace for the solution will be shared with other users in your organization. You will add assets to projects and conduct experiments in the workspace.
The experiments will be used for training models that will be published to provide scoring from web services. The experiment for fraud prediction will use Machine Learning modules and APIs to train the models and will predict probabilities in an Apache Hadoop ecosystem.
End of repeated scenario.
You need to alter the list of columns that will be used for predicting fraud for an input web service endpoint. The columns from the original data source must be retained while running the Machine Learning experiment.
Which module should you add after the web service input module and before the prediction module?

• A. Edit Metadata
• B. Import Data
• C. SMOTE
• D. Select Columns in Dataset

Answer: D

NEW QUESTION 15
Note: This question is part of a series of questions that use the same or similar answer choices. An answer choice may be correct for more than one question in the series. Each question is independent of the other questions in this series. Information and details provided in a question apply only to that question.
You need to remove rows that have an empty value in a specific column. The solution must use a native module.
Which module should you use?

• A. Execute Python Script
• B. Tune Model Hyperparameters
• C. Normalize Data
• D. Select Columns in Dataset
• E. Import Data
• F. Edit Metadata
• G. Clip Values
• H. Clean Missing Data

Answer: H

Explanation:
References:
https://blogs.msdn.microsoft.com/azuredev/2021/05/27/data-cleansing-tools-in-azure-machine-learning/

NEW QUESTION 16
You have the following three training datasets for a restaurant:
You must recommend restaurant to a particular user based only on the users features. You need to use a Matchbox Recommender to make recommendations.
How many input parameters should you specify?

• A. 1
• B. 2
• C. 3
• D. 4

Answer: B

Explanation:
References:
https://msdn.microsoft.com/en-us/library/azure/dn905987.aspx

NEW QUESTION 17
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
Start of repeated scenario
You plan to use Azure platform tools to detect and analyze food items in smart refrigerators. To provide families with an integrated experience for grocery shopping and cooking, the refrigerators will connect to other smart appliances, such as stoves and microwave ovens, on a LAN.
You plan to build an object recognition model by using the Microsoft Cognitive Toolkit. The object recognition model will receive input from the connected devices and send results to applications.
The training data will be derived from more than 10 TB of images. You will convert the raw images to the sparse format.
End of repeated scenario.
You need to preprocess the training data by using a Principal Component Analysis (PCA) algorithm in the least amount of time possible. Which implementation method should you use?

• A. Azure HDInsight using HiveML
• B. Azure Machine Learning Studio and a custom Execute Python Script module
• C. Azure HDInsight using Microsoft R Server
• D. Azure Machine Learning Studio with a custom Execute R Script module

Answer: C

NEW QUESTION 18
Note: This question is part of a series of questions that use the same or similar answer choices. An
answer choice may be correct for more than one question in the series. Each question is independent of the other questions in this series. Information and details provided in a question apply only to that question.
You need to change a column name to a friendly name. The solution must use a native module. Which module should you use?

• A. Normalize Data
• B. Select Columns in Dataset
• C. Import Data
• D. Edit Metadata
• E. Tune Model Hyperparameters
• F. Clean Missing Data
• G. Clip Values
• H. Execute Python Script

Answer: D

NEW QUESTION 19
You have an Execute R Script module that has one input from either a Partition and Sample module or a Web service input module.
You need to preprocess tweets by using R. The solution must meet the following requirements:
How should you complete the R code? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar panes or scroll to view content.
NOTE: Each correct selection is worth one point.

• A. Mastered
• B. Not Mastered

Answer: A

Explanation:

NEW QUESTION 20
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 sections, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You are working on an Azure Machine Learning experiment. You have the dataset configured as shown in the following table.

You need to ensure that you can compare the performance of the models and add annotations to the results. Solution: You consolidate the output of the Score Model modules by using the Add Rows module, and then
use the Execute R Script module.
Does this meet the goal?

• A. Yes
• B. No

Answer: A

Explanation:
References:
https://msdn.microsoft.com/en-us/library/azure/dn905915.aspx

NEW QUESTION 21
......