Knowledge Check - Post

Which of the following descriptions accurately describes Azure Machine Learning?

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?

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?

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?

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

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?

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?

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?

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?

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?

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?

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?

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?

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?

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?

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?

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?

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?

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.

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?

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.

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?

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?

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?

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?

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

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?

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?

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?

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?

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?

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?

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?

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?

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?

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

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?

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?

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?

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?