Scribd
Upload
403 views6 pages

Exam DP 100 Data Science Solution On Azure Skills Measured

The document is an exam guide that outlines the skills measured for the DP-100 exam on designing and implementing data science solutions on Azure. The exam focuses on setting up Azure Machine Learning workspaces, running experiments and training models, optimizing and managing models, and deploying and consuming models. Key skills include creating ML pipelines and workflows, using automated ML and hyperparameter tuning, deploying models as web services, and monitoring model performance and data drift.

Uploaded by

Adil Hussain
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
403 views6 pages

Exam DP 100 Data Science Solution On Azure Skills Measured

The document is an exam guide that outlines the skills measured for the DP-100 exam on designing and implementing data science solutions on Azure. The exam focuses on setting up Azure Machine Learning workspaces, running experiments and training models, optimizing and managing models, and deploying and consuming models. Key skills include creating ML pipelines and workflows, using automated ML and hyperparameter tuning, deploying models as web services, and monitoring model performance and data drift.

Uploaded by

Adil Hussain
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Exam DP-100: Designing and Implementing a Data

Science Solution on Azure – Skills Measured


This exam was updated on December 8, 2020. Following the current exam guide, we have
included a version of the exam guide with Track Changes set to “On,” showing the
changes that were made to the exam on that date.

Audience Profile

The Azure Data Scientist applies their knowledge of data science and machine learning to
implement and run machine learning workloads on Azure; in particular, using Azure Machine
Learning Service. This entails planning and creating a suitable working environment for data
science workloads on Azure, running data experiments and training predictive models,
managing and optimizing models, and deploying machine learning models into production.

Skills Measured

NOTE: The bullets that appear below each of the skills measured are intended to illustrate how
we are assessing that skill. This list is NOT definitive or exhaustive.

NOTE: Most questions cover features that are General Availability (GA). The exam may contain
questions on Preview features if those features are commonly used.

Set up an Azure Machine Learning Workspace (30-35%)


Create an Azure Machine Learning workspace

 create an Azure Machine Learning workspace


 configure workspace settings
 manage a workspace by using Azure Machine Learning studio

Manage data objects in an Azure Machine Learning workspace

 register and maintain datastores


 create and manage datasets

Manage experiment compute contexts

 create a compute instance


 determine appropriate compute specifications for a training workload
 create compute targets for experiments and training
Run Experiments and Train Models (25-30%)
Create models by using Azure Machine Learning Designer

 create a training pipeline by using Azure Machine Learning designer


 ingest data in a designer pipeline
 use designer modules to define a pipeline data flow
 use custom code modules in designer

Run training scripts in an Azure Machine Learning workspace

 create and run an experiment by using the Azure Machine Learning SDK
 configure run settings for a script
 consume data from a dataset in an experiment by using the Azure Machine Learning
SDK

Generate metrics from an experiment run

 log metrics from an experiment run


 retrieve and view experiment outputs
 use logs to troubleshoot experiment run errors

Automate the model training process

 create a pipeline by using the SDK


 pass data between steps in a pipeline
 run a pipeline
 monitor pipeline runs

Optimize and Manage Models (20-25%)


Use Automated ML to create optimal models

 use the Automated ML interface in Azure Machine Learning studio


 use Automated ML from the Azure Machine Learning SDK
 select pre-processing options
 determine algorithms to be searched
 define a primary metric
 get data for an Automated ML run
 retrieve the best model

Use Hyperdrive to tune hyperparameters

 select a sampling method


 define the search space
 define the primary metric
 define early termination options
 find the model that has optimal hyperparameter values

Use model explainers to interpret models

 select a model interpreter


 generate feature importance data

Manage models

 register a trained model


 monitor model usage
 monitor data drift

Deploy and Consume Models (20-25%)


Create production compute targets

 consider security for deployed services


 evaluate compute options for deployment

Deploy a model as a service

 configure deployment settings


 consume a deployed service
 troubleshoot deployment container issues

Create a pipeline for batch inferencing

 publish a batch inferencing pipeline


 run a batch inferencing pipeline and obtain outputs

Publish a designer pipeline as a web service

 create a target compute resource


 configure an Inference pipeline
 consume a deployed endpoint

The exam guide below shows the changes that were implemented on December 8, 2020.
Skills Measured

NOTE: The bullets that appear below each of the skills measured are intended to illustrate how
we are assessing that skill. This list is NOT definitive or exhaustive.

NOTE: Most questions cover features that are General Availability (GA). The exam may contain
questions on Preview features if those features are commonly used.

Set up an Azure Machine Learning Workspace (30-35%)


Create an Azure Machine Learning workspace

 create an Azure Machine Learning workspace


 configure workspace settings
 manage a workspace by using Azure Machine Learning studio

Manage data objects in an Azure Machine Learning workspace

 register and maintain datastores


 create and manage datasets

Manage experiment compute contexts

 create a compute instance


 determine appropriate compute specifications for a training workload
 create compute targets for experiments and training

Run Experiments and Train Models (25-30%)


Create models by using Azure Machine Learning Designer

 create a training pipeline by using Azure Machine Learning designer


 ingest data in a designer pipeline
 use designer modules to define a pipeline data flow
 use custom code modules in designer

Run training scripts in an Azure Machine Learning workspace

 create and run an experiment by using the Azure Machine Learning SDK
 configure run settings for a script
 consume data from a dataset in an experiment by using the Azure Machine Learning
SDK
 choose an estimator for a training experiment
Generate metrics from an experiment run

 log metrics from an experiment run


 retrieve and view experiment outputs
 use logs to troubleshoot experiment run errors

Automate the model training process

 create a pipeline by using the SDK


 pass data between steps in a pipeline
 run a pipeline
 monitor pipeline runs

Optimize and Manage Models (20-25%)


Use Automated ML to create optimal models

 use the Automated ML interface in Azure Machine Learning studio


 use Automated ML from the Azure Machine Learning SDK
 select scaling functions and pre-processing options
 determine algorithms to be searched
 define a primary metric
 get data for an Automated ML run
 retrieve the best model

Use Hyperdrive to tune hyperparameters

 select a sampling method


 define the search space
 define the primary metric
 define early termination options
 find the model that has optimal hyperparameter values

Use model explainers to interpret models

 select a model interpreter


 generate feature importance data

Manage models

 register a trained model


 monitor model historyusage
 monitor data drift
Deploy and Consume Models (20-25%)
Create production compute targets

 consider security for deployed services


 evaluate compute options for deployment

Deploy a model as a service

 configure deployment settings


 consume a deployed service
 troubleshoot deployment container issues

Create a pipeline for batch inferencing

 publish a batch inferencing pipeline


 run a batch inferencing pipeline and obtain outputs

Publish a designer pipeline as a web service

 create a target compute resource


 configure an Inference pipeline
 consume a deployed endpoint

You might also like