Reader small image

You're reading from  Power BI Machine Learning and OpenAI

Product typeBook
Published inMay 2023
Reading LevelIntermediate
PublisherPackt
ISBN-139781837636150
Edition1st Edition
Languages
Concepts
Right arrow
Author (1)
Greg Beaumont
Greg Beaumont
author image
Greg Beaumont

Greg Beaumont is a data architect at Microsoft, where he enjoys identifying and solving complex problems backed by his experience in data architecture and a passion for innovation. Focusing on the healthcare industry, Greg works closely with customers to plan enterprise analytics strategies, evaluate new tools and products, conduct training sessions and hackathons, and architect solutions that improve the quality of care and reduce costs. He strives to be a trusted advisor to his customers and is always seeking new ways to drive progress and help organizations thrive. He is a veteran of the Microsoft data speaker network and has worked with hundreds of customers on their data management and analytics strategies.
Read more about Greg Beaumont

Right arrow

Applying Power BI ML Models

In Chapter 10, we reviewed the results of training and testing all three of your ML models. Your options for future iterations and plans for your ML models were reviewed and discussed. The Predict Damage ML and Predict Height ML models had promising testing results, while the Predict Size ML model had room for improvement. For all three of your models, the best next steps were to review the results with your stakeholders, and, if possible, meet with your data science team to determine whether more advanced tooling and techniques could improve upon your initial work.

For this chapter, you will apply the ML models that you built to new data from the FAA Wildlife Strike database. The data used up to this point in the book ended on October 16, 2022. The new data for this chapter will be reports that have been added to the publicly available data between that date and March 11, 2023. The purpose of this chapter will be to review the process through which you...

Technical requirements

As always, make sure you have access to the following:

  • The FAA Wildlife Strike data files from either the FAA website or the Packt GitHub site
  • A Power BI Pro license
  • One of the following Power BI licensing options for access to Power BI dataflows:
    • Power BI Premium
    • Power BI Premium Per User
  • One of the following options for getting data into the Power BI cloud service:
    • Microsoft OneDrive (with connectivity to the Power BI cloud service)
    • Microsoft Access + Power BI Gateway
    • Azure Data Lake (with connectivity to the Power BI cloud service)
  • Power BI Desktop April 2023 or later (no licenses required)

Bringing the new FAA Wildlife strike data into Power BI

Meetings with project stakeholders and data science teams will determine the best next steps for your Power BI ML models. In the meantime, you can apply these ML models to new data and then compare the predictions to real results. Taking these steps will help you learn how to add your ML models to an automated refresh process in Power BI.

Downloading and configuring the new FAA Wildlife Strike data

As in Chapter 1, you should begin by downloading a new copy of the FAA Wildlife Strike data. The copy you’ve been using to date for this book contained data through October 16, 2022. Now, you’ll pull in new data to score with the Power BI ML models that were trained and tested with historical data. The new file contains data through March 1, 2023. You can download a copy of the text file used for this part of the book at the Packt GitHub site here: https://github.com/PacktPublishing/Unleashing-Your-Data-with-Power...

Applying Power BI ML models to score new FAA Wildlife Strike data

After 11 chapters of work, you are finally ready to run new data through your Power BI ML models and evaluate the resulting predictions! You will run through the process of applying each ML model to the new data, and then browse the results of the scoring to compare predictions with the real results.

Applying the Predict Damage ML model in Power BI

You will now reference the Predict Damage ML Score data from the ML Queries dataflow against the Predict Damage ML model so that it can be scored. Figure 11.3 is a quick summary of the data that you have used to train, test, and now apply the Predict Damage ML Model:

Summary

In this chapter, you brought new FAA Wildlife Strike data into Power BI and transformed the data to match the design of your original architecture. You then transformed the data to meet the filtering and transformation requirements of the data used to train and test your Predict Damage ML, Predict Size ML, and Predict Height ML models. Then, you made predictions for the new data by applying the trained Power BI ML models. Finally, you reviewed the results of the predictions and compared them to the actual results.

Chapter 12 will add a special twist to your project! For those of you out in the real world, changing scope and expectations is a frequent occurrence with data projects. When this book was being written, OpenAI and Microsoft OpenAI were fast becoming media sensations. Your stakeholders have asked you to find some use cases for OpenAI in your project. It’s a scope change to your project, but it will be an exciting adventure! Chapter 12 will review the OpenAI...

lock icon
The rest of the chapter is locked
You have been reading a chapter from
Power BI Machine Learning and OpenAI
Published in: May 2023Publisher: PacktISBN-13: 9781837636150
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
undefined
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime

Author (1)

author image
Greg Beaumont

Greg Beaumont is a data architect at Microsoft, where he enjoys identifying and solving complex problems backed by his experience in data architecture and a passion for innovation. Focusing on the healthcare industry, Greg works closely with customers to plan enterprise analytics strategies, evaluate new tools and products, conduct training sessions and hackathons, and architect solutions that improve the quality of care and reduce costs. He strives to be a trusted advisor to his customers and is always seeking new ways to drive progress and help organizations thrive. He is a veteran of the Microsoft data speaker network and has worked with hundreds of customers on their data management and analytics strategies.
Read more about Greg Beaumont

Training

Testing

Apply (new)

Rows

10,165

4,326

653

Date Range

...