DP-100 Exam Study Guide (Designing And Implementing A Data Science Solution On Azure)
You can access DP-100 Exam Microsoft official page here
Preparing for DP-100 Designing and Implementing a Data Science Solution on the Azure Certificate exam? Don’t know where to start? This post is the DP-100 Certificate Study Guide (with links to each exam objective).
I have curated a list of articles from Microsoft documentation for each objective of the DP-100 exam. I hope this article will help you to prepare for the DP-100 Certification exam. Also, please share the post within your circles so it helps them to prepare for the exam.
Skills Measured
- Set up an Azure Machine Learning Workspace (30-35%)
- Run Experiments and Train Models (25-30%)
- Optimize and Manage Models (20-25%)
- Deploy and Consume Models (20-25%)
DP-100 Exam Free Study Guide
For each test objective, I’ve compiled a thorough collection of articles from Microsoft documentation. Please feel free to forward this page to your friends and coworkers in order to assist them in preparing for the test .
Set up an Azure Machine Learning Workspace (30-35%)
Create an Azure Machine Learning Workspace
- Create an Azure Machine Learning workspace
- Create & manage Azure Machine Learning workspaces
- Configure workspace settings
- Azure security workspace setting
- Manage a workspace by using Azure Machine Learning Studio
- Manage an Azure Machine Learning Studio workspace
Manage Data Objects in an Azure Machine Learning Workspace
- Register and maintain datastores
- Create & register datastores
- Create and manage datasets
- Create datasets
Manage Experiment Compute Contexts
- Create a compute instance
- What is an Azure Machine Learning compute instance?
- Determine appropriate compute specifications for a training workload
- Configure & submit training runs
- Create compute targets for experiments and training
- What are compute targets in Azure Machine Learning?
- Set up compute targets for model training & deployment
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
- Retrain models with Azure Machine Learning designer
- Ingest data in a designer pipeline
- Data ingestion options for Azure Machine Learning workflows
- Use designer modules to define a pipeline data flow
- Predict automobile price with the designer
- Use custom code modules in the designer
- Define custom R modules for Machine Learning Studio (classic)
Run Training Scripts in an Azure Machine Learning Workspace
- Create and run an experiment by using the Azure Machine Learning SDK
- Azure Machine Learning in Jupyter Notebooks
- Configure run settings for a script
- Configure and submit training runs
- Script Run Config class
- Consume data from a dataset in an experiment by using the Azure Machine Learning SDK
- Create and register datastores
- Consume data from a dataset in an experiment by using the Azure Machine Learning SDK
- Create datasets
Generate Metrics from an Experiment Run
- Log metrics from an experiment run
- Enable logging in Azure ML training runs
- Retrieve and view experiment outputs
- Evaluate machine learning experiment results
- Set input & output directories
- Use logs to troubleshoot experiment run errors
- Collect ML pipeline log files in Application Insights for alerts & debugging
Automate the Model Training Process
- Create a pipeline by using the SDK
- Use automated machine learning to predict taxi fares
- Pass data between steps in a pipeline
- Pass data between pipeline steps
- Run a pipeline
- Running automated machine learning experiments
- Monitor pipeline runs
- Monitoring Azure Machine Learning
Optimize and Manage Models (20-25%)
Use Automated ML to Create Optimal Models
- Use the Automated ML interface in Azure Machine Learning studio
- Forecast demand with automated machine learning
- Use Automated ML from the Azure Machine Learning SDK
- Configure automated ML experiments in Python
- Select pre-processing options
- Preprocessing Data in Azure Machine Learning Studio
- What is automated machine learning (AutoML)?
- Determine algorithms to be searched
- How to select algorithms for Azure Machine Learning
- Define a primary metric
- The primary metric
- Get data for an Automated ML run
- Explore the results
- Retrieve the best model
- Retrieve the best model
Use Hyperdrive to Tune Hyperparameters
- Select a sampling method
- Sampling the hyperparameter space
- Define the search space
- Tune hyperparameters for your model with Azure ML
- Define the primary metric
- Primary metric in Azure Machine Learning
- Specify primary metric
- Choosing a primary metric to handle imbalanced data
- Define early termination options
- Specify early termination policy
- Bandit policy
- Median stopping policy
- Truncation selection policy
- No termination policy
- Find the model that has optimal hyperparameter values
- Find the best model
Use Model Explainers to Interpret Models
- Select a model interpreter
- Interpretability with Azure Machine Learning
- Generate feature importance data
- Generate feature importance value on your personal machine
Manage Models
- Register a trained model
- Register your model (optional)
- Monitor model usage
- Monitor Azure Machine Learning
- Monitoring data from Azure Machine Learning
- Monitor data drift
- Detect data drift (preview) on datasets
- Data Drift Monitoring for Azure ML Datasets
Deploy and Consume Models (20-25%)
Create Production Compute Targets
- Consider security for deployed services
- Use TLS to secure a web service through Azure ML
- Evaluate compute options for the deployment
- Deploy models with Azure Machine Learning
Deploy a Model as a Service
- Configure deployment settings
- Deploy models with Azure Machine Learning
- Consume a deployed service
- Consume an Azure ML model deployed as a web service
- Troubleshoot deployment container issues
- Troubleshoot docker deployment of models with AKS & ACI
Create a Pipeline for Batch Inferencing
- Publish a batch inferencing pipeline
- Run batch predictions using Azure ML designer
- Run a batch inferencing pipeline and obtain outputs
- Build an Azure ML pipeline for batch scoring
Publish a Designer Pipeline as a Web Service
- Create a target compute resource
- Deploy models with Azure Machine Learning
- Configure an Inference pipeline
- Deploy a machine learning model with the designer
- Consume a deployed endpoint
- Deploy models with Azure Machine Learning
This brings us to the end of the DP-100 Designing And Implementing A Data Science Solution On Azure Study Guide.
Follow Me to Receive Updates on DP-100 Exam
Share the DP-100 Study Guide in Your Network
Share on facebook
Share on twitter
Share on linkedin
