Knowledge Check - Post

Question 1

Which of the following descriptions accurately describes Azure Machine Learning?

Accepted Answer

A cloud-based platform for operating machine learning solutions at scale.

Answer

A Python library that you can use as an alternative to common machine learning frameworks like Scikit-Learn, PyTorch, and Tensorflow.

Answer

An application for Microsoft Windows that enables you to create machine learning models by using a drag and drop interface

Question 2

Which edition of Azure Machine Learning workspace should you provision if you only plan to use the graphical Designer tool to train machine learning models?

Accepted Answer

Enterprise

Answer

Basic

Question 3

You need a cloud-based development environment that you can use to run Jupyter notebooks that are stored in your workspace. The notebooks must remain in your workspace at all times.
What should you do?

Accepted Answer

Create a Compute Instance compute target in your workspace.

Answer

Install Visual Studio Code on your local computer.

Answer

Create a Training Cluster compute target in your workspace.

Question 4

You plan to use the Workspace.from_config() method to connect to your Azure Machine Learning workspace from a Python environment on your local workstation. You have already used pip to install the
azureml-sdk package.
What else should you do?

Accepted Answer

Download the config.json file for your workspace to the folder containing your local Python code files

Answer

Run pip install azureml-sdk['notebooks'] to install the notebooks extra

Answer

Create a Compute Instance compute target in your workspace.

Question 5

You need to ingest data from a CSV file into a pipeline in Designer. What should you do?

Accepted Answer

Create a Dataset by uploading the file, and drag the dataset to the canvas

Answer

Add a Convert to CSV module to the canvas.

Answer

Add an Enter Data Manually module to the canvas.

Question 6

You have created a pipeline that includes multiple modules to define a dataflow and train a model.
Now you want to run the pipeline.
What must you do first?

Accepted Answer

Create a Training Cluster in your workspace, and select it as the compute target for the pipeline.

Answer

Add comments to each of the modules on the pipeline canvas.

Answer

Rename the pipeline to include the date and time.

Question 7

You have created and run a pipeline to train a model using the Designer tool. Now you want to publish it as a real-time service.
What must you do first?

Accepted Answer

Create an inference pipeline from your training pipeline.

Answer

Clone the training pipeline with a different name.

Answer

Change the compute target of the training pipeline to an Azure Kubernetes Services (AKS) cluster.

Question 8

You have published a pipeline as a real-time service on an Azure Kubernetes Services (AKS) cluster.
An application developer plans to call the service from a REST-based client.
What information does the application developer require?

Accepted Answer

The endoint URL and key for the published service.

Answer

The name of the inference pipeline in designer

Answer

The name of the AKS compute target in the workspace.

Question 9

You are using the Azure Machine Learning Python SDK to write code for an experiment. You need to record metrics from each run of the experiment, and be able to retrieve them easily from
each run.
What should you do?

Accepted Answer

Use the log methods of the Run class to record named metrics.

Answer

Add print statements to the experiment code to print the metrics.

Answer

Save the experiment data in the outputs folder

Question 10

You want to run a script as an experiment.
You have already created a RunConfig object to define the Python runtime context for the experiment.
What other object should you create to associate the script with the runtime context?

Accepted Answer

A ScriptRunConfig object.

Answer

A Pipeline object.

Answer

A ComputeTarget object.

Question 11

You have written a script that uses the Scikit-Learn framework to train a model.
Which framework-specific estimator should you use to run the script as an experiment?

Accepted Answer

SKLearn

Answer

PyTorch

Answer

Tensorflow

Question 12

You have run an experiment to train a model.
You want the model to be stored in the workspace, and available to other experiments and published
services.
What should you do?

Accepted Answer

Register the model in the workspace.

Answer

Save the model as a file in a Compute Instance.

Answer

Save the experiment script as a notebook.

Question 13

You are using the Azure Machine Learning Python SDK, and you need to create a reference to the default
datastore in your workspace.
You have written the following code:
--
from azureml.core import Workspace
#Get the workspace
ws = Workspace.from_config()
#Get the default datastore
--
Which line of code should you add?

Accepted Answer

default_ds = ws.get_default_datastore()

Answer

default_ds = ws.set_default_datastore()

Answer

default_ds = ws.datastores.get('default')

Question 14

You have uploaded some data files to a folder in a blob container, and registered the blob container as a
datastore in your Azure Machine Learning workspace.
You want to run a script as an experiment that loads the data files and trains a model.
What should you do?

Accepted Answer

Create a data reference for the datastore location and pass it to the script as a parameter.

Answer

Save the experiment script in the same blob folder as the data files.

Answer

Create global variables for the Azure Storage account name and key in the experiment script.

Question 15

You have a CSV file containing structured data that you want to use to train a model.
You upload the file to a folder in an Azure Storage blob container, for which a datastore is defined in your
workspace. Now you want to create a dataset for the data so that it can be easily used as a Pandas
dataframe.
Which kind of dataset should you create?

Accepted Answer

A tabular dataset

Answer

A file dataset

Question 16

You have registered a dataset in your workspace.
You want to use the dataset in an experiment script that is run using an estimator.
What should you do?

Accepted Answer

Pass the dataset as a named input to the estimator.

Answer

Create a data reference for the datastore location where the dataset data is stored, and pass it to the
script as a parameter.

Answer

Use the dataset to save the data as a CSV file in the experiment script folder before running the
experiment.

Question 17

You are using the Azure Machine Learning Python SDK to run experiments. You need to create an environment from a Conda configuration (.yml) file.
Which method of the Environment class should you use?

Accepted Answer

create_from_conda_specification

Answer

create

Answer

create_from_existing_conda_environment

Question 18

You have registered an environment in your workspace, and retrieved it using the following code:
--
from azureml.core import Environment, Estimator
env = Environment.get(workspace=ws, name='my_environment')
estimator = Estimator(entry_script='training_script.py', ...)
--
You want to use the environment as the Python context for an experiment script that is run using an estimator.
Which property of the estimator should you set to assign the environment?

Accepted Answer

environment_definition = env

Answer

compute_target = env

Answer

source_directory = env

Question 19

You need to create a compute target for training experiments that require a graphical processing unit
(GPU).
You want to be able to scale the compute so that multiple nodes are started automatically as required.
Which kind of compute target should you create.

Accepted Answer

Training Cluster

Answer

Compute Instance

Answer

Inference Cluster

Question 20

You are using an estimator to run an experiment, and you want to run it on a compute instance named
training-cluster-1.
Which property of the estimator should you set to run the experiment on training-cluster-1?

Accepted Answer

compute_target = 'training-cluster-1

Answer

environment_definition = 'training-cluster-1'

Answer

source_directory = 'training-cluster-1'

Question 21

You are creating a pipeline that includes a step to train a model using an estimator.
Which kind of step should you define in the pipeline for this task.

Accepted Answer

EstimatorStep

Answer

DatabricksStep

Answer

PythonScriptStep

Question 22

You are creating a pipeline that includes two steps.
Step 1 preprocesses some data, and step 2 uses the preprocessed data to train a model.
What type of object should you use to pass data from step 1 to step 2 and create a dependency between
these steps?

Accepted Answer

PipelineData

Answer

Datastore

Answer

Data Reference

Question 23

You have used the Python SDK for Azure Machine Learning to create a pipeline that trains a model.
What do you need to do to before publishing the pipeline?

Accepted Answer

Run the pipeline as an experiment.

Answer

Rename the pipeline to pipeline_name-production.

Answer

Create an inference cluster compute target.

Question 24

You have published a pipeline that you want to run every week.
You plan to use the Schedule.create method to create the schedule.
What kind of object must you create first to configure how frequently the pipeline runs?

Accepted Answer

ScheduleRecurrance

Answer

Datastore

Answer

PipelineParameter

Question 25

You have trained a model using the Python SDK for Azure Machine Learning.
You want to deploy the model as a containerized real-time service with high scalability and security.
What kind of compute should you create to host the service?

Accepted Answer

An Azure Kubernetes Services (AKS) inferencing cluster.

Answer

A compute instance with GPUs.

Answer

A training cluster with multiple nodes.

Question 26

You are deploying a model as a real-time inferencing service.
What functions must the entry script for the service include?

Accepted Answer

init() and run(raw_data)

Answer

main() and predict(raw_data)

Answer

load() and score(raw_data)

Question 27

You are creating a batch inferencing pipeline that you want to use to predict new values for a large
volume of data files?
You want the pipeline to run the scoring script on multiple nodes and collate the results.
What kind of step should you include in the pipeline?

Accepted Answer

ParallelRunStep

Answer

PythonScriptStep

Answer

AdlaStep

Question 28

You have configured the step in your batch inferencing pipeline with an output_action="append_row"
property.
In which file should you look for the batch inferencing results?

Accepted Answer

parallel_run_step.txt

Answer

output.txt

Answer

stdoutlogs.txt

Question 29

You plan to use hyperparameter tuning to find optimal discrete values for a set of hyperparameters.
You want to try every possible combination of a set of specified discrete values.
Which kind of sampling should you use?

Accepted Answer

Grid Sampling

Answer

Random Sampling

Answer

Bayesian Sampling

Question 30

You are using hyper parameter tuning to train an optimal model.
Your training script calculates the area under the curve (AUC) metric for the trained model like this:
--
y_scores = model.predict_proba(X_test)
auc = roc_auc_score(y_test,y_scores[:,1])
--
You define the hyperdrive configuration like this:
--
hyperdrive = HyperDriveConfig(estimator=sklearn_estimator,
hyperparameter_sampling=grid_sampling,
policy=None,
primary_metric_name='AUC',
primary_metric_goal=PrimaryMetricGoal.MAXIMIZE,
max_total_runs=6,
max_concurrent_runs=4)
--
Which code should you add to the training script?

Accepted Answer

run.log('AUC', np.float(auc))

Answer

run.log('Accuracy', np.float(auc))

Answer

print(auc)

Question 31

You are using automated machine learning to train a model that predicts the species of an iris based on
its petal and sepal measurements.
Which kind of task should you specify for automated machine learning?

Accepted Answer

Classification

Answer

Regression

Answer

Forecasting

Question 32

You have submitted an automated machine learning run using the Python SDk for Azure Machine
Learning.
When the run completes, which method of the run object should you use to retrieve the best model?

Accepted Answer

get_output()

Answer

load_model()

Answer

get_metrics()

Question 33

You have trained a model, and you want to quantify the influence of each feature on a specific individual
prediction.
What kind of feature importance should you examine?

Accepted Answer

Local feature importance

Answer

Global feature importance

Question 34

You are using automated machine learning, and you want to determine the influence of features on the
predictions made by the best model produced by the automated machine learning experiment.
What must you do when configuring the automated machine learning experiment?

Accepted Answer

Enable model explainability.

Answer

Whitelist only tree-based algorithms.

Answer

Enable featurization.

Question 35

You want to create an explainer that applies the most appropriate SHAP model explanation algorithm
based on the type of model.
What kind of explainer should you create?

Accepted Answer

Tabular

Answer

Mimic

Answer

Permutation Feature Importance

Question 36

You want to include model explanations in the logged details of your training experiment.
What must you do in your training script?

Accepted Answer

Use the ExplanationClient.upload_model_explanation method to upload the explanation created by an
Explainer.

Answer

Use the Run.log_table method to log feature importance for each feature.

Answer

Save the the explanation created by an Explainer in the ./outputs folder.

Question 37

You have deployed a model as a real-time inferencing service in an Azure Kubernetes Service (AKS)
cluster.
What must you do to capture and analyze telemetry for this service?

Accepted Answer

Enable application insights.

Answer

Implement inference-time model interpretability.

Answer

Move the AKS cluster to the same region as the Azure Machine Learning workspace.

Question 38

You want to include custom information in the telemetry for your inferencing service, and analyze it using
Application Insights.
What must you do in your service's entry script?

Accepted Answer

Use a print statement to write the metrics in the STDOUT log.

Answer

Use the Run.log method to log the custom metrics

Answer

Save the custom metrics in the ./outputs folder.

Question 39

You have trained a model using a dataset containing data that was collected last year. As this year
progresses, you will collect new data.
You want to track any changing data trends that might affect the performance of the model.
What should you do?

Accepted Answer

Collect the new data in a separate dataset and create a Data Drift Monitor with the training dataset as
a baseline and the new dataset as a target.

Answer

Collect the new data in a new version of the existing training dataset, and profile both datasets.

Answer

Replace the training dataset with a new dataset that contains both the original training data and the
new data

Question 40

You are creating a data drift monitor.
You want to automatically notify the data science team if a significant change in data distribution is
detected.
What must you do?

Accepted Answer

Define an AlertConfiguration and set a drift_threshold value

Answer

Set the latency of the data drift monitor to allow time for data scientists to review the new data.

Answer

Register the training dataset with the model, including the email address of the data science team as a
tag

Knowledge Check - Post

Perguntas do quiz (40)

Informações

Fale Conosco

O que você acha do novo visual?