Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Power BI Machine Learning and OpenAI

You're reading from   Power BI Machine Learning and OpenAI Explore data through business intelligence, predictive analytics, and text generation

Arrow left icon
Product type Paperback
Published in May 2023
Publisher Packt
ISBN-13 9781837636150
Length 308 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Greg Beaumont Greg Beaumont
Author Profile Icon Greg Beaumont
Greg Beaumont
Arrow right icon
View More author details
Toc

Table of Contents (21) Chapters Close

Preface 1. Part 1: Data Exploration and Preparation
2. Chapter 1: Requirements, Data Modeling, and Planning FREE CHAPTER 3. Chapter 2: Preparing and Ingesting Data with Power Query 4. Chapter 3: Exploring Data Using Power BI and Creating a Semantic Model 5. Chapter 4: Model Data for Machine Learning in Power BI 6. Part 2: Artificial Intelligence and Machine Learning Visuals and Publishing to the Power BI Service
7. Chapter 5: Discovering Features Using Analytics and AI Visuals 8. Chapter 6: Discovering New Features Using R and Python Visuals 9. Chapter 7: Deploying Data Ingestion and Transformation Components to the Power BI Cloud Service 10. Part 3: Machine Learning in Power BI
11. Chapter 8: Building Machine Learning Models with Power BI 12. Chapter 9: Evaluating Trained and Tested ML Models 13. Chapter 10: Iterating Power BI ML models 14. Chapter 11: Applying Power BI ML Models 15. Part 4: Integrating OpenAI with Power BI
16. Chapter 12: Use Cases for OpenAI 17. Chapter 13: Using OpenAI and Azure OpenAI in Power BI Dataflows 18. Chapter 14: Project Review and Looking Forward 19. Index 20. Other Books You May Enjoy

Reviewing the requirements for the solution

Now that you’ve explored the FAA Wildlife Strike data, you have a better understanding of what data is available for your solution. The original assignment that you were given by your stakeholders was as follows:

  • Provide leadership with tools to do interactive analysis of the FAA Wildlife Strike data
  • Find insights about factors that influence the incidents
  • Make predictions about future wildlife strike incidents

Those requirements sound pretty vague! Now that you have a better understanding of the available data, it’s a good time to circle back with the stakeholders and clarify those requirements. You ask them questions such as the following:

  • What types of interactive analysis do you want to do?
  • Are you interested in the impact on endangered bird species?
  • Maybe you’d like to view trends due to wildlife strikes and compare airports and regions?
  • Perhaps you’d like to see the height and frequency of wildlife strikes at different times of the year?
  • Would understanding correlations to factors such as aircraft size, time of day, season, geography, and height be useful?
  • Are you interested in predicting specific risks or outcomes?

Entire books have been written about gathering requirements for data and analytics projects, and discussions on this particular topic could also be extensive. For the sake of keeping this book consumable, let’s assume that your discussions with the stakeholders led to prioritizing the following deliverables for the project:

  • Analytic report: Viewing trends over time such as number of incidents, location of incidents, height, and details such as types of aircraft and wildlife species
  • Predict damage: When a strike is reported, make a prediction as to whether there will be a cost associated with any damage
  • Predict size: When a strike is reported, make a prediction about the size of the wildlife that struck the aircraft
  • Predict height: For wildlife strikes, predict the height of the incidents

Now, you review the notes you took about the FAA Wildlife Strike data during your data exploration efforts. In doing so, you can think about how the data might match up to the use cases. Based on the requirements and your initial exploration of the data, you decide that the FAA Wildlife Strike data from the wildlife.accdb file and the tables from the read_me.xls file (Engine Codes, Aircraft Type, and Engine Position) are appropriate content to include during the initial phases of your project.

You have been reading a chapter from
Power BI Machine Learning and OpenAI
Published in: May 2023
Publisher: Packt
ISBN-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.
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 $19.99/month. Cancel anytime