Artificial Intelligence with Power BI: Take your data analytics skills to the next level by leveraging the AI capabilities in Power BI

Cover
Title Page
Contributors
Table of Contents
Preface
Copyright and Credits
Part 1: AI Fundamentals
Chapter 1: Introducing AI in Power BI
	What do we expect from a data analyst?
		What is a data analyst?
		Connecting to data
		Visualizing data
	What is AI?
		Understanding the definition of AI
		Understanding machine learning
		Understanding deep learning
		Understanding supervised and unsupervised learning
		Understanding algorithms
		What is the data science process?
	Why should we use AI in Power BI?
		The problems with implementing AI
		Why AI in Power BI is the solution
	What are our options for AI in Power BI?
		Out-of-the-box options
		Creating your own models
	Summary
Chapter 2: Exploring Data in Power BI
	Technical requirements
		Using the sample dataset on world happiness
		How to interpret this dataset
		Importing the world happiness dataset into Power BI
	What to look for in your data
		Understanding data quantity
		Understanding data quality
	Using data profiling tools
		Column quality
		Column distribution
		Column profile
	Using visuals to explore your data
		Line charts
		Bar charts
		Histograms
		Scatter plots
		matplotlib
	Summary
Chapter 3: Data Preparation
	Fixing the structure of your data
		Working with structured data
		Fixing the structure of semi-structured data
		Fixing the structure when working with images
	Working with missing data
		How do you find missing data?
		What do you do with missing data?
	Mitigating bias
		How to find bias
		How to mitigate bias in your dataset
	Handling outliers
	Summary
Part 2: Out-of-the-Box AI Features
Chapter 4: Forecasting Time-Series Data
	Technical requirements
	Data requirements for forecasting
		Why use forecasting?
		Time-series data
		Using an example – tourism data
	Algorithms used for forecasting
		The benefit of using an out-of-the-box feature
		Understanding how forecasting is calculated in Power BI
		Optimizing forecasting accuracy in Power BI
	Using forecasting in Power BI
	Summary
	Further reading
Chapter 5: Detecting Anomalies in Your Data Using Power BI
	Technical requirements
	Which data is suitable for anomaly detection?
		Why use anomaly detection?
		Data requirements for anomaly detection
	Understanding the logic behind anomaly detection
		The algorithms behind Microsoft's anomaly detection feature
		No need to label your data
		Fast and powerful analysis
	Using anomaly detection in Power BI
		Importing the sample dataset into Power BI
		Enabling anomaly detection in Power BI
	Summary
	Further reading
Chapter 6: Using Natural Language to Explore Data with the Q&A Visual
	Technical requirements
	Understanding natural language processing
		Using natural language in programs
		Understanding natural language for data exploration
		Preparing data for natural language models
	Creating a Q&A visual in Power BI
		Adding a Q&A visual
		Using the Q&A visual
	Optimizing your Q&A visual
		Exploring the Q&A setup
		Improving the Q&A experience
		Using feedback to improve the model over time
	Summary
	Further reading
Chapter 7: Using Cognitive Services
	Technical requirements
	Understanding Azure's Cognitive Services
		Creating a Cognitive Services resource
	Using Cognitive Services for LU
		Using Azure's Text Analytics
		Creating question answering from a knowledge base
	Using Cognitive Services for CV
		Understanding Azure's Computer Vision
		Using Azure's Custom Vision
		Using the Face service
	Summary
Chapter 8: Integrating Natural Language Understanding with Power BI
	Technical requirements
	Using Language APIs in Power BI Desktop
		Using AI Insights
		Using Power Query Editor
	Visualizing insights from text in reports
		Visualizing text with a Word Cloud
	Summary
Chapter 9: Integrating an Interactive Question and Answering App into Power BI
	Technical requirements
	Creating a question answering service
		Understanding the application of question answering
		Configuring a question answering service
	Creating an FAQ app with Power Apps
		Creating a new app with Power Apps
		Adding Power Automate to call the question answering service
		Connecting Power Automate to Power Apps
	Integrating the FAQ app with Power BI
	Improving the question answering model
	Summary
Chapter 10: Getting Insights from Images with Computer Vision
	Technical requirements
	Getting insights with Computer Vision using AI Insights
		Using the Vision option of AI Insights
	Configuring Custom Vision
		Preparing the data for Custom Vision
		Training the model in Custom Vision
		Evaluating classification models
		Publishing your Custom Vision model
	Integrating Computer Vision or Custom Vision with Power BI
	Using visuals to show a reel of images in a report
		Storing data and ensuring it is anonymously accessible
		Improving the Custom Vision model
	Summary
Part 3: Create Your Own Models
Chapter 11: Using Automated Machine Learning with Azure and Power BI
	Technical requirements
	Understanding AutoML
		Understanding the ML process
		Improving the performance of an ML model
		When to use AutoML
	Creating an AutoML experiment in Azure ML
		Creating an Azure ML workspace and resources
		Configuring an AutoML run
	Deploying a model to an endpoint
	Integrating the model with Power BI
	Summary
Chapter 12: Training a Model with Azure Machine Learning
	Technical requirements
	Understanding how to train a model
		Understanding the machine learning process
	Working with Azure ML
		Creating Azure ML assets
	Training a model with Azure ML Designer
		Configuring an Azure ML Designer pipeline
	Deploying a model for batch or real-time predictions
		Generating batch predictions
		Generating real-time predictions
	Integrating an endpoint with Power BI to generate predictions
	Summary
Chapter 13: Responsible AI
	Understanding responsible AI
	Protecting privacy when using personal data
		Removing personally identifiable information
		Using differential privacy on personal data
	Creating transparent models
		Using algorithms that are transparent by design
		Explaining black-box models
	Creating fair models
		Identifying unfairness in models
		Mitigating unfairness in models
	Summary
Index
Other Books You May Enjoy