DP-100-Questions

1
DP-100 Designing and Implementing a Data Science
Solution on Azure Version 7.0
Topic 1, Define and prepare the development
environment
QUESTION NO 1 DRAG DROP You are planning to host
practical training to acquaint staff with Docker
for Windows. Staff devices must support the
installation of Docker. Which of the following
are requirements for this installation? Answer by
dragging the correct options from the list to
the answer area.
2
Answer ltmapgtltm x1"27" x2"316" y1"132"
y2"224" ss"0" a"0" /gtltm x1"26" x2"319"
y1"233" y2"316" ss"0" a"0" /gtltm x1"26"
x2"317" y1"323" y2"408" ss"0" a"0" /gtltm
x1"26" x2"318" y1"416" y2"500" ss"0" a"0"
/gtltm x1"27" x2"318" y1"509" y2"597" ss"0"
a"0" /gtltm x1"25" x2"319" y1"606" y2"696"
ss"0" a"0" /gtltm x1"388" x2"740" y1"131"
y2"226" ss"1" a"0" /gtltm x1"387" x2"742"
y1"235" y2"313" ss"1" a"0" /gtltm x1"387"
x2"741" y1"319" y2"406" ss"1" a"0" /gtltc
start"1" stop"0" /gtltc start"2" stop"1" /gtltc
start"4" stop"2" /gtlt/mapgt References
https//docs.docker.com/toolbox/toolbox_install_wi
ndows/ https//blogs.technet.microsoft.com/canitpr
o/2015/09/08/step-by-step-enabling-hyper-v-for-
use-on-windows-10/ https//docs.docker.com/docker-
for-windows/install/

• QUESTION NO 2
• You have been tasked with constructing an
  intelligent solution with machine learning
  models.
• You have to make sure that the environment allows
  for data scientists to build notebooks in a
  cloud environment, and enforce the use of
  automatic feature engineering and model building
  in machine learning pipelines. The environment
  should also allow for notebooks to be deployed
  to retrain via Spark instances with dynamic
  worker allocation. Furthermore, notebooks have to
  be exportable for local version control
  purposes.
• You have created an Azure HDInsight cluster that
  includes the Apache Spark Mlib library. Which of
  the following is the action you must take NEXT?
• Create and execute the Zeppelin notebooks on the
  cluster.
• Create and execute a Jupyter notebook on the
  cluster.
• Install the Microsoft Machine Learning SDK for
  Python on the cluster.
• Install Microsoft Machine Learning for Apache
  Spark.
• Answer D References
• https//docs.microsoft.com/en-us/azure/hdinsight/s
  park/apache-spark-zeppelin-notebook
  https//azuremlbuild.blob.core.windows.net/pyspark
  api/intro.html

QUESTION NO 3 DRAG DROP
3
You have been tasked with moving data into Azure
Blob Storage for the purpose of supporting Azure
Machine Learning. Which of the following can be
used to complete your task? Answer by dragging
the correct options from the list to the answer
area.
Answer ltmapgtltm x1"35" x2"323" y1"132"
y2"224" ss"0" a"0" /gtltm x1"32" x2"325"
y1"236" y2"315" ss"0" a"0" /gtltm x1"32"
x2"325" y1"325" y2"407" ss"0" a"0" /gtltm
x1"33" x2"323" y1"415" y2"501" ss"0" a"0"
/gtltm x1"32" x2"323" y1"510" y2"597" ss"0"
a"0" /gtltm x1"384" x2"725" y1"131" y2"224"
ss"1" a"0" /gtltm x1"385" x2"725" y1"232"
y2"316" ss"1" a"0" /gtltm x1"385" x2"725"
y1"322" y2"405" ss"1" a"0" /gtltc start"0"
stop"0" /gtltc start"2" stop"1" /gtltc start"4"
stop"2" /gtlt/mapgt References https//docs.micros
oft.com/en-us/azure/machine-learning/team-data-sci
ence-process/move- azure-blob
QUESTION NO 4 You create a real-time service
endpoint using Azure Machine Learning designer.
4

• After training the model and preparing the
  real-time pipeline for deployment into a
  designated Azure Machine Learning compute
  resource, you are required to publish the
  inference pipeline as a web service.
• You need to make use of the correct compute
  target to achieve your goal. Which of the
  following is the compute target you should use?
• Azure Container Instances
• Azure Kubernetes Service (AKS)
• Azure Machine Learning compute clusters
• Local web service
• Answer B References
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/concept-compute-target

• QUESTION NO 5
• After creating a multi-class image classification
  deep learning model, you are required to make
  sure that the model is retrained once-a-month
  with the new image data retrieved from a public
  web portal.
• You have created an Azure Machine Learning
  pipeline to retrieve new data, normalize the size
  of images, as well as retrain the model.
• To configure the schedule for the pipeline, you
  must mak use of the Azure Machine Learning SDK.
• Which of the following actions should you take
  FIRST?
• Define an Azure Machine Learning pipeline
  schedule.
• Retrieve the pipeline ID.
• Publish the pipeline.
• Create a ScheduleRecurrence.
• Answer C References
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/how-to-schedule-pipelines

5
Topic 2, Prepare data for modeling

• QUESTION NO 6
• You are planning to host practical training to
  acquaint learners with data visualization
  creation using Python. Learner devices are able
  to connect to the internet.
• Learner devices are currently NOT configured for
  Python development. Also, learners are unable to
  install software on their devices as they lack
  administrator permissions. Furthermore, they are
  unable to access Azure subscriptions.
• It is imperative that learners are able to
  execute Python-based data visualization code.
  Which of the following actions should you take?
• You should consider configuring the use of Azure
  Container Instance.
• You should consider configuring the use of Azure
  BatchAI.
• You should consider configuring the use of Azure
  Notebooks.
• You should consider configuring the use of Azure
  Kubernetes Service.
• Answer C References
• https//notebooks.azure.com/

• QUESTION NO 7
• Note The question is included in a number of
  questions that depicts the identical set-up.
  However, every question has a distinctive result.
  Establish if the solution satisfies the
  requirements.
• You have been tasked with evaluating your model
  on a partial data sample via k-fold cross-
  validation.
• You have already configured a k parameter as the
  number of splits. You now have to configure the
  k parameter for the cross-validation with the
  usual value choice.
• Solution You configure the use of the value k1.
  Does the solution meet the goal?
• Yes
• No

6
Answer B

• QUESTION NO 8
• You construct a machine learning experiment via
  Azure Machine Learning Studio. You would like to
  split data into two separate datasets.
• Which of the following actions should you take?
• You should make use of the Split Data module.
• You should make use of the Group Categorical
  Values module.
• You should make use of the Clip Values module.
• You should make use of the Group Data into Bins
  module.
• Answer D References
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/studio-module-reference/group-
• data-into-bins

• QUESTION NO 9
• You have been tasked with creating a new Azure
  pipeline via the Machine Learning designer.
• You have to makes sure that the pipeline trains a
  model using data in a comma-separated values
  (CSV) file that is published on a website. A
  dataset for the file for this file does not
  exist.
• Data from the CSV file must be ingested into the
  designer pipeline with the least amount of
  administrative effort as possible.
• Which of the following actions should you take?
• You should make use of the Convert to TXT module.
• You should add the Copy Data object to the
  pipeline.
• You should add the Import Data object to the
  pipeline.
• You should add the Dataset object to the
  pipeline.
• Answer D Example
• from azureml.core import Dataset

7
iris_tabular_dataset Dataset.Tabular.from_delimi
ted_files((def_blob_store, 'train-
dataset/iris.csv')) References https//docs.mic
rosoft.com/en-us/azure/machine-learning/how-to-cre
ate-your-first-pipeline
Topic 3, Perform Feature Engineering
QUESTION NO 10 DRAG DROP You are in the process
of constructing a regression model. You would
like to make it a Poisson regression model. To
achieve your goal, the feature values need to
meet certain conditions. Which of the following
are relevant conditions with regards to the label
data? Answer by dragging the correct options
from the list to the answer area.
8
Answer ltmapgtltm x1"45" x2"338" y1"131"
y2"223" ss"0" a"0" /gtltm x1"48" x2"339"
y1"234" y2"314" ss"0" a"0" /gtltm x1"46"
x2"339" y1"323" y2"407" ss"0" a"0" /gtltm
x1"46" x2"338" y1"416" y2"501" ss"0" a"0"
/gtltm x1"48" x2"340" y1"511" y2"599" ss"0"
a"0" /gtltm x1"401" x2"718" y1"131" y2"224"
ss"1" a"0" /gtltm x1"402" x2"719" y1"231"
y2"314" ss"1" a"0" /gtltc start"0" stop"0"
/gtltc start"4" stop"1" /gtlt/mapgt References http
s//docs.microsoft.com/en-us/azure/machine-learnin
g/studio-module-reference/poisson- regression
Topic 4, Develop models

• QUESTION NO 11
• You are making use of a two-class logistic
  regression model to create a binary
  classification.
• You want to evaluate the results of the model for
  disproportion. You need to configure the use of
  a suitable evaluation metric
• Which of the following is the metric you should
  choose?
• Recall
• Area Under the Curve (AUC) Curve
• Precision
• Root Mean Square Error
• Answer B References
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/studio/evaluate-model- performanceevaluati
  ng-a-binary-classification-model

QUESTION NO 12 You make use of Azure Machine
Learning Studio to develop a linear regression
model. You perform an experiment to assess
various algorithms. Which of the following is an
algorithm that reduces the variances between
actual and predicted values?
9

• Fast Forest Quantile Regression
• Poisson Regression
• Boosted Decision Tree Regression
• Linear Regression
• Answer C References
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/algorithm-module-
• reference/boosted-decision-tree-regression
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/studio-module-reference/evaluate- model
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/studio-module-reference/linear- regression

• QUESTION NO 13
• Note The question is included in a number of
  questions that depicts the identical set-up.
  However, every question has a distinctive result.
  Establish if the solution satisfies the
  requirements.
• You have been tasked with constructing a machine
  learning model that translates language text
  into a different language text.
• The machine learning model must be constructed
  and trained to learn the sequence of the.
  Solution You make use of Generative Adversarial
  Networks (GANs).
• Does the solution meet the goal?
• Yes
• No
• Answer B

QUESTION NO 14 DRAG DROP You have been tasked
with evaluating the performance of a binary
classification model that you created. You need
to choose evaluation metrics to achieve your goal.
10
Which of the following are the metrics you would
choose? Answer by dragging the correct options
from the list to the answer area.
Answer ltmapgtltm x1"33" x2"325" y1"131"
y2"225" ss"0" a"0" /gtltm x1"37" x2"325"
y1"234" y2"315" ss"0" a"0" /gtltm x1"35"
x2"327" y1"322" y2"407" ss"0" a"0" /gtltm
x1"33" x2"326" y1"417" y2"502" ss"0" a"0"
/gtltm x1"34" x2"324" y1"511" y2"598" ss"0"
a"0" /gtltm x1"378" x2"701" y1"133" y2"223"
ss"1" a"0" /gtltm x1"377" x2"699" y1"233"
y2"319" ss"1" a"0" /gtltc start"0" stop"0"
/gtltc start"1" stop"1" /gtlt/mapgt References http
s//docs.microsoft.com/en-us/azure/machine-learnin
g/studio/evaluate-model- performance
QUESTION NO 15 DRAG DROP You build a binary
classification model using the Azure Machine
Learning Studio Two-Class Neural Network module.
11
You are preparing to configure the Tune Model
Hyperparameters module for the purpose of tuning
accuracy for the model. Which of the following
are valid parameters for the Two-Class Neural
Network module? Answer by dragging the correct
options from the list to the answer area.
Answer ltmapgtltm x1"118" x2"406" y1"132"
y2"223" ss"0" a"0" /gtltm x1"117" x2"408"
y1"234" y2"314" ss"0" a"0" /gtltm x1"117"
x2"410" y1"323" y2"406" ss"0" a"0" /gtltm
x1"118" x2"410" y1"415" y2"501" ss"0" a"0"
/gtltm x1"117" x2"411" y1"508" y2"596" ss"0"
a"0" /gtltm x1"117" x2"410" y1"605" y2"693"
ss"0" a"0" /gtltm x1"118" x2"408" y1"708"
y2"799" ss"0" a"0" /gtltm x1"511" x2"830"
y1"130" y2"224" ss"1" a"0" /gtltm x1"511"
x2"829" y1"230" y2"318" ss"1" a"0"
/gtltm x1"511" x2"830" y1"326" y2"409" ss"1"
a"0" /gtltc start"1" stop"0" /gtltc start"3"
stop"1" /gtltc start"5" stop"2"
/gtlt/mapgt References
12
https//docs.microsoft.com/en-us/azure/machine-lea
rning/studio-module-reference/two-class-
neural-network

• QUESTION NO 16
• You make use of Azure Machine Learning Studio to
  create a binary classification model.
• You are preparing to carry out a parameter sweep
  of the model to tune hyperparameters. You have
  to make sure that the sweep allows for every
  possible combination of hyperparameters to be
  iterated. Also, the computing resources needed to
  carry out the sweep must be reduced.
• Which of the following actions should you take?
• You should consider making use of the Selective
  grid sweep mode
• You should consider making use of the Measured
  grid sweep mode
• You should consider making use of the Entire grid
  sweep mode
• You should consider making use of the Random grid
  sweep mode.
• Answer D References
• https//docs.microsoft.com/en-us/azure/machine-lea
  rning/studio-module-reference/tune-
  model-hyperparameters

• QUESTION NO 17
• You are in the process of constructing a deep
  convolutional neural network (CNN). The CNN will
  be used for image classification.
• You notice that the CNN model you constructed
  displays hints of overfitting.
• You want to make sure that overfitting is
  minimized, and that the model is converged to an
  optimal fit.
• Which of the following is TRUE with regards to
  achieving your goal?
• You have to add an additional dense layer with
  512 input units, and reduce the amount of
  training data.
• You have to add L1/L2 regularization, and reduce
  the amount of training data.
• You have to reduce the amount of training data
  and make use of training data augmentation.
• You have to add L1/L2 regularization, and make
  use of training data augmentation.
• You have to add an additional dense layer with
  512 input units, and add L1/L2 regularization.

13
Answer B References https//machinelearningmast
ery.com/how-to-reduce-overfitting-in-deep-learning
-with-weight- regularization/ https//en.wikipedi
a.org/wiki/Convolutional_neural_network