Fundamental

Question 1

You are developing a hands-on workshop to introduce Docker for Windows to attendees.

You need to ensure that workshop attendees can install Docker on their devices.

Which two prerequisite components should attendees install on the devices? Each correct answer presents part of the solution.

A. Microsoft Hardware-Assisted Virtualization Detection Tool
B. Kitematic
C. BIOS-enabled virtualization
D. VirtualBox
E. Windows 10 64-bit Professional

Answer 1

C. BIOS-enabled virtualization

E. Windows 10 64-bit Professional

Question 2

Your team is building a data engineering and data science development environment.
The environment must support the following requirements:
- support Python and Scala
- compose data storage, movement, and processing services into automated data pipelines
- the same tool should be used for the orchestration of both data engineering and data science
- support workload isolation and interactive workloads
- enable scaling across a cluster of machines
You need to create the environment.
What should you do?

A. Build the environment in Apache Hive for HDInsight and use Azure Data Factory for orchestration.
B. Build the environment in Azure Databricks and use Azure Data Factory for orchestration.
C. Build the environment in Apache Spark for HDInsight and use Azure Container Instances for orchestration.
D. Build the environment in Azure Databricks and use Azure Container Instances for orchestration.

Answer 2

B. Build the environment in Azure Databricks and use Azure Data Factory for orchestration.

In Azure Databricks, we can create two different types of clusters.
- Standard, these are the default clusters and can be used with Python, R, Scala and SQL
- High-concurrency
Azure Databricks is fully integrated with Azure Data Factory.

Question 3

You are building an intelligent solution using machine learning models.
The environment must support the following requirements:
✑ Data scientists must build notebooks in a cloud environment
✑ Data scientists must use automatic feature engineering and model building in machine learning pipelines.
✑ Notebooks must be deployed to retrain using Spark instances with dynamic worker allocation.
✑ Notebooks must be exportable to be version controlled locally.
You need to create the environment.
Which four actions should you perform in sequence?

Answer 3

Step 1: Create an Azure HDInsight cluster to include the Apache Spark Mlib library

Step 2: Install Microsot Machine Learning for Apache Spark
You install AzureML on your Azure HDInsight cluster.
Microsoft Machine Learning for Apache Spark (MMLSpark) provides a number of deep learning and data science tools for Apache Spark, including seamless integration of Spark Machine Learning pipelines with Microsoft Cognitive Toolkit (CNTK) and OpenCV, enabling you to quickly create powerful, highly-scalable predictive and analytical models for large image and text datasets.

Step 3: Create and execute the Zeppelin notebooks on the cluster

Step 4: When the cluster is ready, export Zeppelin notebooks to a local environment.
Notebooks must be exportable to be version controlled locally.

Question 4

You plan to build a team data science environment. Data for training models in machine learning pipelines will be over 20 GB in size.
You have the following requirements:
✑ Models must be built using Caffe2 or Chainer frameworks.
✑ Data scientists must be able to use a data science environment to build the machine learning pipelines and train models on their personal devices in both connected and disconnected network environments.
Personal devices must support updating machine learning pipelines when connected to a network.
You need to select a data science environment.
Which environment should you use?
A. Azure Machine Learning Service
B. Azure Machine Learning Studio
C. Azure Databricks
D. Azure Kubernetes Service (AKS)

Answer 4

A. Azure Machine Learning Service
The Data Science Virtual Machine (DSVM) is a customized VM image on Microsoft’s Azure cloud built specifically for doing data science. Caffe2 and Chainer are supported by DSVM.
DSVM integrates with Azure Machine Learning.

Question 5

You are implementing a machine learning model to predict stock prices.
The model uses a PostgreSQL database and requires GPU processing.
You need to create a virtual machine that is pre-configured with the required tools.
What should you do?

A. Create a Data Science Virtual Machine (DSVM) Windows edition.
B. Create a Geo Al Data Science Virtual Machine (Geo-DSVM) Windows edition.
C. Create a Deep Learning Virtual Machine (DLVM) Linux edition.
D. Create a Deep Learning Virtual Machine (DLVM) Windows edition.

Answer 5

A. Create a Data Science Virtual Machine (DSVM) Windows edition.

In the DSVM, your training models can use deep learning algorithms on hardware that’s based on graphics processing units (GPUs).
PostgreSQL is available for the following operating systems: Linux (all recent distributions), 64-bit installers available for macOS (OS X) version 10.6 and newer ג€”
Windows (with installers available for 64-bit version; tested on latest versions and back to Windows 2012 R2.

Question 6

You are developing deep learning models to analyze semi-structured, unstructured, and structured data types.
You have the following data available for model building:
✑ Video recordings of sporting events
✑ Transcripts of radio commentary about events
✑ Logs from related social media feeds captured during sporting events
You need to select an environment for creating the model.
Which environment should you use?
A. Azure Cognitive Services
B. Azure Data Lake Analytics
C. Azure HDInsight with Spark MLib
D. Azure Machine Learning Studio

Answer 6

A.
Azure Cognitive Services expand on Microsoft’s evolving portfolio of machine learning APIs and enable developers to easily add cognitive features ג€” such as emotion and video detection; facial, speech, and vision recognition; and speech and language understanding ג€” into their applications. The goal of Azure Cognitive
Services is to help developers create applications that can see, hear, speak, understand, and even begin to reason. The catalog of services within Azure Cognitive
Services can be categorized into five main pillars - Vision, Speech, Language, Search, and

Question 7

You must store data in Azure Blob Storage to support Azure Machine Learning.
You need to transfer the data into Azure Blob Storage.
What are three possible ways to achieve the goal? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A. Bulk Insert SQL Query
B. AzCopy
C. Python script
D. Azure Storage Explorer
E. Bulk Copy Program (BCP)

Answer 7

BCD 🗳️
You can move data to and from Azure Blob storage using different technologies:
✑ Azure Storage-Explorer
✑ AzCopy
✑ Python
✑ SSIS

Question 8

You are moving a large dataset from Azure Machine Learning Studio to a Weka environment.
You need to format the data for the Weka environment.
Which module should you use?
A. Convert to CSV
B. Convert to Dataset
C. Convert to ARFF
D. Convert to SVMLight

Answer 8

C. Convert to ARFF
Use the Convert to ARFF module in Azure Machine Learning Studio, to convert datasets and results in Azure Machine Learning to the attribute-relation file format used by the Weka toolset. This format is known as ARFF.
The ARFF data specification for Weka supports multiple machine learning tasks, including data preprocessing, classification, and feature selection. In this format, data is organized by entites and their attributes, and is contained in a single text file.

Question 9

You plan to create a speech recognition deep learning model.
The model must support the latest version of Python.
You need to recommend a deep learning framework for speech recognition to include in the Data Science Virtual Machine (DSVM).
What should you recommend?
A. Rattle
B. TensorFlow
C. Weka
D. Scikit-learn

Answer 9

B. TensorFlow
TensorFlow is an open-source library for numerical computation and large-scale machine learning. It uses Python to provide a convenient front-end API for building applications with the framework
TensorFlow can train and run deep neural networks for handwritten digit classification, image recognition, word embeddings, recurrent neural networks, sequence- to-sequence models for machine translation, natural language processing, and PDE (partial differential equation) based simulations.

Question 10

You plan to use a Deep Learning Virtual Machine (DLVM) to train deep learning models using Compute Unified Device Architecture (CUDA) computations.
You need to configure the DLVM to support CUDA.
What should you implement?
A. Solid State Drives (SSD)
B. Computer Processing Unit (CPU) speed increase by using overclocking
C. Graphic Processing Unit (GPU)
D. High Random Access Memory (RAM) configuration
E. Intel Software Guard Extensions (Intel SGX) technology

Answer 10

C. Graphic Processing Unit (GPU)

A Deep Learning Virtual Machine is a pre-configured environment for deep learning using GPU instances.

Question 11

You plan to use a Data Science Virtual Machine (DSVM) with the open source deep learning frameworks Caffe2 and PyTorch.
You need to select a pre-configured DSVM to support the frameworks.
What should you create?
A. Data Science Virtual Machine for Windows 2012
B. Data Science Virtual Machine for Linux (CentOS)
C. Geo AI Data Science Virtual Machine with ArcGIS
D. Data Science Virtual Machine for Windows 2016
E. Data Science Virtual Machine for Linux (Ubuntu)

Answer 11

E. Data Science Virtual Machine for Linux (Ubuntu)
Caffe2 and PyTorch is supported by Data Science Virtual Machine for Linux.
Microsoft offers Linux editions of the DSVM on Ubuntu 16.04 LTS and CentOS 7.4.
Only the DSVM on Ubuntu is preconfigured for Caffe2 and PyTorch.

Question 12

You are performing sentiment analysis using a CSV file that includes 12,000 customer reviews written in a short sentence format. You add the CSV file to Azure
Machine Learning Studio and configure it as the starting point dataset of an experiment. You add the Extract N-Gram Features from Text module to the experiment to extract key phrases from the customer review column in the dataset.
You must create a new n-gram dictionary from the customer review text and set the maximum n-gram size to trigrams.
What should you select?

Answer 12

Vocabulary mode: Create -
For Vocabulary mode, select Create to indicate that you are creating a new list of n-gram features.

N-Grams size: 3 -
For N-Grams size, type a number that indicates the maximum size of the n-grams to extract and store. For example, if you type 3, unigrams, bigrams, and trigrams will be created.

Weighting function: Leave blank -
The option, Weighting function, is required only if you merge or update vocabularies. It specifies how terms in the two vocabularies and their scores should be weighted against each other.

Question 13

You are developing a data science workspace that uses an Azure Machine Learning service.
You need to select a compute target to deploy the workspace.
What should you use?
A. Azure Data Lake Analytics
B. Azure Databricks
C. Azure Container Service
D. Apache Spark for HDInsight

Answer 13

C. Azure Container Service
Azure Container Instances can be used as compute target for testing or development. Use for low-scale CPU-based workloads that require less than 48 GB of
RAM.

Question 14

You are solving a classification task.
The dataset is imbalanced.
You need to select an Azure Machine Learning Studio module to improve the classification accuracy.
Which module should you use?

A. Permutation Feature Importance
B. Filter Based Feature Selection
C. Fisher Linear Discriminant Analysis
D. Synthetic Minority Oversampling Technique (SMOTE)

Answer 14

D. Synthetic Minority Oversampling Technique (SMOTE)

Use the SMOTE module in Azure Machine Learning Studio (classic) to increase the number of underrepresented cases in a dataset used for machine learning.
SMOTE is a better way of increasing the number of rare cases than simply duplicating existing cases.
You connect the SMOTE module to a dataset that is imbalanced. There are many reasons why a dataset might be imbalanced: the category you are targeting might be very rare in the population, or the data might simply be difficult to collect. Typically, you use SMOTE when the class you want to analyze is under- represented.

Question 15

You configure a Deep Learning Virtual Machine for Windows.
You need to recommend tools and frameworks to perform the following:
✑ Build deep neural network (DNN) models
✑ Perform interactive data exploration and visualization

Answer 15

Box 1: Vowpal Wabbit -
Use the Train Vowpal Wabbit Version 8 module in Azure Machine Learning Studio (classic), to create a machine learning model by using Vowpal Wabbit.

Box 2: PowerBI Desktop -
Power BI Desktop is a powerful visual data exploration and interactive reporting tool
BI is a name given to a modern approach to business decision making in which users are empowered to find, explore, and share insights from data across the enterprise.

Question 16

You use Azure Machine Learning Studio to build a machine learning experiment.
You need to divide data into two distinct datasets.
Which module should you use?
A. Assign Data to Clusters
B. Load Trained Model
C. Partition and Sample
D. Tune Model-Hyperparameters

Answer 16

C. Partition and Sample

Partition and Sample with the Stratified split option outputs multiple datasets, partitioned using the rules you specified.

Question 17

You are creating an experiment by using Azure Machine Learning Studio.
You must divide the data into four subsets for evaluation. There is a high degree of missing values in the data. You must prepare the data for analysis.
You need to select appropriate methods for producing the experiment.

Answer 17

1. Import data
2. Clean missing data
3. partition and sample

The Clean Missing Data module in Azure Machine Learning Studio, to remove, replace, or infer missing values.

Question 18

You are retrieving data from a large datastore by using Azure Machine Learning Studio.
You must create a subset of the data for testing purposes using a random sampling seed based on the system clock.
You add the Partition and Sample module to your experiment.

Answer 18

Box 1: Sampling -

Create a sample of data -
This option supports simple random sampling or stratified random sampling. This is useful if you want to create a smaller representative sample dataset for testing.
1. Add the Partition and Sample module to your experiment in Studio, and connect the dataset.
2. Partition or sample mode: Set this to Sampling.
3. Rate of sampling. See box 2 below.

Box 2: 0 -
3. Rate of sampling. Random seed for sampling: Optionally, type an integer to use as a seed value.
This option is important if you want the rows to be divided the same way every time. The default value is 0, meaning that a starting seed is generated based on the system clock. This can lead to slightly different results each time you run the experiment.

Question 19

You are creating a machine learning model. You have a dataset that contains null rows.
You need to use the Clean Missing Data module in Azure Machine Learning Studio to identify and resolve the null and missing data in the dataset.
Which parameter should you use?
A. Replace with mean
B. Remove entire column
C. Remove entire row
D. Hot Deck
E. Custom substitution value
F. Replace with mode

Answer 19

C. Remove entire row

Remove entire row: Completely removes any row in the dataset that has one or more missing values. This is useful if the missing value can be considered randomly missing.

Question 20

The finance team asks you to train a model using data in an Azure Storage blob container named finance-data.
You need to register the container as a datastore in an Azure Machine Learning workspace and ensure that an error will be raised if the container does not exist.

Answer 20

Box 1: register_azure_blob_container
Register an Azure Blob Container to the datastore.
Box 2: create_if_not_exists = False
Create the file share if it does not exist, defaults to False.

Question 21

You plan to provision an Azure Machine Learning Basic edition workspace for a data science project.
You need to identify the tasks you will be able to perform in the workspace.
Which three tasks will you be able to perform? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A. Create a Compute Instance and use it to run code in Jupyter notebooks.
B. Create an Azure Kubernetes Service (AKS) inference cluster.
C. Use the designer to train a model by dragging and dropping pre-defined modules.
D. Create a tabular dataset that supports versioning.
E. Use the Automated Machine Learning user interface to train a model.

Answer 21

B. Create an Azure Kubernetes Service (AKS) inference cluster.
A. Create a Compute Instance and use it to run code in Jupyter notebooks.
D. Create a tabular dataset that supports versioning.

Question 22

You need to write code to access the datastore from a notebook.

Answer 22

Box 1: DataStore -
To get a specific datastore registered in the current workspace, use the get() static method on the Datastore class:
# Get a named datastore from the current workspace
datastore = Datastore.get(ws, datastore_name='your datastore name')

Box 2: ws -

Box 3: demo_datastore -

Question 23

A set of CSV files contains sales records. All the CSV files have the same data schema.
Each CSV file contains the sales record for a particular month and has the filename sales.csv. Each file is stored in a folder that indicates the month and year when the data was recorded. The folders are in an Azure blob container for which a datastore has been defined in an Azure Machine Learning workspace. The folders are organized in a parent folder named sales to create the following hierarchical structure:

/sales
  /01-2019
    /sales.csv
  /02-2019
    /sales.csv
  /03-2019
    /sales.csv

At the end of each month, a new folder with that month’s sales file is added to the sales folder.
You plan to use the sales data to train a machine learning model based on the following requirements:

✑ You must define a dataset that loads all of the sales data to date into a structure that can be easily converted to a dataframe.
✑ You must be able to create experiments that use only data that was created before a specific previous month, ignoring any data that was added after that month.
✑ You must register the minimum number of datasets possible.

You need to register the sales data as a dataset in Azure Machine Learning service workspace.

What should you do?

A. Create a tabular dataset that references the datastore and explicitly specifies each ‘sales/mm-yyyy/sales.csv’ file every month. Register the dataset with the name sales_dataset each month, replacing the existing dataset and specifying a tag named month indicating the month and year it was registered. Use this dataset for all experiments.
B. Create a tabular dataset that references the datastore and specifies the path ‘sales/*/sales.csv’, register the dataset with the name sales_dataset and a tag named month indicating the month and year it was registered, and use this dataset for all experiments.
C. Create a new tabular dataset that references the datastore and explicitly specifies each ‘sales/mm-yyyy/sales.csv’ file every month. Register the dataset with the name sales_dataset_MM-YYYY each month with appropriate MM and YYYY values for the month and year. Use the appropriate month-specific dataset for experiments.
D. Create a tabular dataset that references the datastore and explicitly specifies each ‘sales/mm-yyyy/sales.csv’ file. Register the dataset with the name sales_dataset each month as a new version and with a tag named month indicating the month and year it was registered. Use this dataset for all experiments, identifying the version to be used based on the month tag as necessary.

Answer 23

B 🗳️
Specify the path.
Example:
The following code gets the workspace existing workspace and the desired datastore by name. And then passes the datastore and file locations to the path parameter to create a new TabularDataset, weather_ds. from azureml.core import Workspace, Datastore, Dataset datastore_name = ‘your datastore name’
# get existing workspace
workspace = Workspace.from_config()
# retrieve an existing datastore in the workspace by name
datastore = Datastore.get(workspace, datastore_name)
# create a TabularDataset from 3 file paths in datastore
datastore_paths = [(datastore, ‘weather/2018/11.csv’),
(datastore, ‘weather/2018/12.csv’),
(datastore, ‘weather/2019/*.csv’)]
weather_ds = Dataset.Tabular.from_delimited_files(path=datastore_paths)

Question 24

An organization uses Azure Machine Learning service and wants to expand their use of machine learning.
You have the following compute environments. The organization does not want to create another compute environment.

nb_server - compute instance
aks_cluster - Azure Kubernetes Service
mlc - Machine Learning Compute

Box1 - Run an azure machines learning designer training pipeline.
Box2 - Deploying a web service from the azure machine learning designer.

Answer 24

Box 1: nb_server -
Box 2: mlc_cluster -
With Azure Machine Learning, you can train your model on a variety of resources or environments, collectively referred to as compute targets. A compute target can be a local machine or a cloud resource, such as an Azure Machine Learning Compute, Azure HDInsight or a remote virtual machine.