Unleashing Your Data with Power BI Machine Learning and OpenAI: Embark on a data adventure and turn your raw data into meaningful insights

Cover
Title Page
Copyright & Credits
Contributors
Table of Contents
Preface
Part 1: Data Exploration and Preparation
Chapter 1: Requirements, Data Modeling, and Planning
	Technical requirements
	Reviewing the source data
		Accessing the data
		Exploring the FAA Wildlife Strike report data
	Reviewing the requirements for the solution
	Designing a preliminary data model
		Flattening the data
		Star schema
		Hybrid design
	Considerations for ML
	Summary
Chapter 2: Preparing and Ingesting Data with Power Query
	Technical requirements
	Preparing the primary table of data
		Grouping the raw data
		Designing a curated table of the primary STRIKE_REPORTS data
	Building a curated table of the primary STRIKE_REPORTS data
		Referencing the raw table to create a new query
		Keeping only the columns that you need
		Data type changes
		Column name changes
	Building curated versions of the Aircraft Type, Engine Codes, and Engine Position queries
		The Aircraft Type Info query
		The Engine Position Info query
		The Engine Codes Info query
	Building a curated query to populate a Date table
	Summary
Chapter 3: Exploring Data Using Power BI and Creating a Semantic Model
	Technical requirements
	Designing relationships between tables
		Date table
		Aircraft Type Info
		Engine Codes Info
		Engine Position Info
	Building a Power BI dataset
		Importing and processing the Wildlife Strike data queries from Power Query
		Creating relationships between fact and dimension tables
		Cleaning up the metadata and adjusting settings
	Adding measures to your Power BI dataset
	Summary
Chapter 4: Model Data for Machine Learning in Power BI
	Technical requirements
	Choosing features via data exploration
		Adding Power Query tables to your architecture for ML training and testing
		Building an analytic report to discover and choose initial features for the Predict Damage ML model
		Building an analytic report to discover and choose initial features for the Predict Size ML model
		Building an analytic report to discover and choose initial features for the Predict Height ML model
	Creating flattened tables in Power Query for ML in Power BI
		Modifying the Predict Damage table in Power Query
		Modifying the Predict Size table in Power Query
		Modifying the Predict Height table in Power Query
	Summary
Part 2: Artificial Intelligence and Machine Learning Visuals and Publishing to the Power BI Service
Chapter 5: Discovering Features Using Analytics and AI Visuals
	Technical requirements
	Identifying features in Power BI using a report
		Number Struck
		Aircraft Mass Code
		Month Num (Number)
		Number of Engines
		Percentage of engines struck, ingested wildlife, and were damaged
	Identifying additional features using the key influencers visual in Power BI
	Adding new features to the ML queries in Power Query
	Summary
Chapter 6: Discovering New Features Using R and Python Visuals
	Technical requirements
	Exploring data with R visuals
		Preparing the data for the R correlation plot
		Building the R correlation plot visualization and adding it to your report
		Identifying new features for your Power BI ML queries
	Exploring data with Python visuals
		Preparing the data for the Python histogram
		Building the Python histogram visualization and add it to your report
		Identifying new features for Power BI ML queries
	Adding new features to the ML queries
	Summary
Chapter 7: Deploying Data Ingestion and Transformation Components to the Power BI Cloud Service
	Technical requirements
	Creating a Power BI workspace
	Publishing your Power BI Desktop dataset and report to the Power BI cloud service
	Creating Power BI dataflows with connections to source data
		Dataflow 1 – reference data from the read_me.xls file
		Dataflow 2 – Wildlife Strike data from the database.accdb file
		Dataflow 3 – the Date table
		Dataflow 4 – data to populate a Power BI dataset
	Adding a dataflow for ML queries
		Adding the Predict Damage ML query to a dataflow
		Adding the Predict Size ML query to a dataflow
		Adding the Predict Height ML query to a dataflow
	Summary
Part 3: Machine Learning in Power BI
Chapter 8: Building Machine Learning Models with Power BI
	Technical requirements
	Building and training a binary prediction ML model in Power BI
	Building and training a general classification ML model in Power BI
	Building and training a regression ML model in Power BI
	Summary
Chapter 9: Evaluating Trained and Tested ML Models
	Technical requirements
	Evaluating test results for the Predict Damage ML model in Power BI
		Model performance for Predict Damage ML Model
		Accuracy report for Predict Damage ML
		Training Details for Predict Damage ML
	Evaluating test results for Predict Size ML Model in Power BI
		Model performance for Predict Size ML
		Training details for Predict Size ML
	Evaluating test results for the Predict Height ML model in Power BI
		Model performance for Predict Height ML
		Training details for Predict Height ML
	Summary
Chapter 10: Iterating Power BI ML models
	Technical requirements
	Considerations for ML model iterations
		Inaccurate data
		Features with low predictive value
		Data volumes
		Data characteristics
	Assessing the Predict Damage binary prediction ML model
	Assessing the Predict Size ML classification model
	Assessing the Predict Height ML regression model
	Summary
Chapter 11: Applying Power BI ML Models
	Technical requirements
	Bringing the new FAA Wildlife strike data into Power BI
		Downloading and configuring the new FAA Wildlife Strike data
		Adding new FAA Wildlife Strike data to the Strike Reports dataflow
		Transforming the new data to prep it for scoring with Power BI ML queries
	Applying Power BI ML models to score new FAA Wildlife Strike data
		Applying the Predict Damage ML model in Power BI
		Applying the Predict Size ML model in Power BI
		Applying the Predict Height ML model in Power BI
	Summary
Part 4: Integrating OpenAI with Power BI
Chapter 12: Use Cases for OpenAI
	Technical requirements
	Brief overview and reference links for OpenAI and Azure OpenAI
	Generating descriptions with OpenAI
	Summarizing data with OpenAI
	Choosing GPT models for your use cases
	Summary
Chapter 13: Using OpenAI and Azure OpenAI in Power BI Dataflows
	Technical requirements
	Configuring OpenAI and Azure OpenAI for use in your Power BI solution
		Configuring OpenAI
		Configuring Microsoft Azure OpenAI
	Preparing a Power BI dataflow for OpenAI and Azure OpenAI
	Creating OpenAI and Azure OpenAI functions in Power BI dataflows
		OpenAI and Azure OpenAI functions
		Creating OpenAI and Azure OpenAI functions for Power BI dataflows
	Using OpenAI and Azure OpenAI functions in Power BI dataflows
	Adding a Cognitive Services function to the solution
	Summary
Chapter 14: Project Review and Looking Forward
	Lessons learned from the book and workshop
		Exploring the intersection of BI, ML, AI, and OpenAI
		ML within Power BI
	Looking forward
		Next steps for the FAA Wildlife Strike data solution
		Next steps with Power BI and ML
		Next steps for your career
	Summary
Index
Other Books You May Enjoy