Smart Data Discovery Using SAS Viya

Powerful Techniques for Deeper Insights
 
 
SAS Institute (Verlag)
  • erschienen am 11. August 2020
  • |
  • 178 Seiten
 
E-Book | PDF mit Adobe-DRM | Systemvoraussetzungen
978-1-63526-726-6 (ISBN)
 

Gain Powerful Insights with SAS Viya!

Whether you are an executive, departmental decision maker, or analyst, the need to leverage data and analytical techniques in order make critical business decisions is now crucial to every part of an organization. Smart Data Discovery with SAS Viya: Powerful Techniques for Deeper Insights provides you with the necessary knowledge and skills to conduct a smart discovery process and empower you to ask more complex questions using your data. The book highlights key components of a smart data discovery process utilizing advanced machine learning techniques, powerful capabilities from SAS Viya, and finally brings it all together using real examples and applications.

With its step-by-step approach and integrated examples, the book provides a relevant and practical guide to insight discovery that goes beyond traditional charts and graphs. By showcasing the powerful visual modeling capabilities of SAS Viya, it also opens up the world of advanced analytics and machine learning techniques to a much broader set of audiences.

  • Englisch
  • Cary, NC
  • |
  • USA
  • 11,07 MB
978-1-63526-726-6 (9781635267266)
weitere Ausgaben werden ermittelt
Felix Liao is a manager within the customer advisory team at SAS and is also responsible for the analytics platform product portfolio for SAS Australia and New Zealand. He has over 15 years of experience working in the Australian and New Zealand analytics market. Felix was responsible for the regional launch of SAS Viya and was also responsible for the successful launch of SAS Visual Analytics in Australia and New Zealand in 2012. He is a regular speaker and blogger on the topic of analytics, data visualization, and machine learning. A computer engineer from his undergraduate study, Felix obtained his MBA in 2009 from Macquarie University, and he is also a SAS certified data scientist. His diverse background allows him to bring a wide set of views and perspectives, which are critical in modern analytics and machine learning projects and initiatives.
  • Intro
  • Contents
  • Preface
  • About This Book
  • What Does This Book Cover?
  • Is This Book for You?
  • What Are the Prerequisites for This Book?
  • What Should You Know about the Examples?
  • Software Used to Develop the Book's Content
  • Example Code and Data
  • We Want to Hear from You
  • About The Author
  • Acknowledgments
  • Why Smart Data Discovery?
  • Introduction
  • Figure 1.1: Smart Data Discovery Requirements
  • Why Smart Data Discovery Now?
  • Figure 1.2: From Reactive to Forward-Looking and Proactive
  • Who Is This Book For?
  • Chapter Overview
  • The Role of The Citizen Data Scientist
  • The Rise of the Citizen Data Scientist
  • Bring an Interesting Question
  • Accelerate the Analytics Life Cycle
  • Figure 2.1: Analytics Life Cycle
  • Communicate and Collaborate
  • SAS Visual Analytics Overview
  • Introduction
  • Figure 3.1: Visual Analytics and Visual Statistics Capabilities
  • The User Interface
  • Figure 3.2: Main Visual Analytics User Interface
  • Panes in Visual Analytics
  • Figure 3.3: Data Pane
  • Figure 3.4: Objects Pane
  • Figure 3.5: Options Pane
  • Canvas
  • Experiment and Explore
  • Experimentation
  • Figure 3.6: Press and Hold to Undo Multiple Steps
  • Maximized View
  • Figure 3.7: Maximized View with Tabular Data
  • Figure 3.8: Transition to Different Visualization Types
  • Actions
  • Figure 3.9: Configuring Object Links Action
  • Figure 3.10: Linked Selection Interaction
  • Actions Diagram
  • Figure 3.11: Actions Diagram
  • Figure 3.12: Automatic Actions Configuration
  • Sharing and Collaboration
  • Sharing
  • Figure 3.13: Sharing Report
  • Figure 3.14: Link Generation Option for Individual Objects
  • Collaborating
  • Figure 3.15: Commenting in Viewer Mode
  • Data Preparation
  • Introduction
  • Importing and Profiling Your Data
  • Data Importing
  • Figure 4.1: Accessing Data Studio via Application Menu
  • Figure 4.2: Summary of Imported Data
  • Data Profiling
  • Figure 4.3: Summary Data Profile Report
  • Figure 2.4: Detailed Profile Report for Region
  • Figure 4.5: Detailed Profile Report for Child Mortality Rate Column
  • Data Transformation
  • Figure 4.6: Data Studio Design Environment
  • Data Plan
  • Figure 4.7: Comparing Source and Result Tables
  • Get Your Data Right During Exploration
  • Join
  • Calculated Item
  • Figure 4.8: Histogram of Child Mortality Rate Variable
  • Figure 4.9: New Calculated Item Window
  • Figure 4.10: Transformed Variable - Child Mortality Rate
  • Custom Category
  • Figure 4.11: Bar Chart of Income Group Variable
  • Figure 4.12: New Custom Category Design Window
  • Figure 4.13: Income Group (High - Low) Custom Variable
  • Define Variable Classification
  • Figure 4.14: Re-assigning Classification Type for Year
  • Figure 4.15: Saving Data View
  • Beyond Basic Visualizations
  • Introduction
  • Figure 5.1: Examples of More Analytical Charts
  • Histogram
  • Figure 5.2: Life Expectancy Histogram
  • Figure 5.3: Histogram with Customized Bins
  • Box Plot
  • Figure 5.4: Parts of a Box Plot
  • Figure 5.5: Life Expectancy Box Plot
  • Figure 5.6: Box Plot with Average and Outliers
  • Figure 5.7: Life Expectancy Box Plot Grouped by Region
  • Scatter Plot and Heat Map
  • Scatter Plot
  • Figure 5.8: Scatter Plot of Life Expectancy and Urban Population (% of Total)
  • Figure 5.9: Scatter Plot with Linear Fit Line
  • Figure 5.10: Scatter Plot with Region Variable
  • Heat Map
  • Figure 5.11: Heat Map of Life Expectancy and Degree of Urbanization
  • Figure 5.12: Heat Map with Population Variable
  • Bubble Plot
  • Figure 5.13: Bubble Plot of Life Expectancy and Degree of Urbanization
  • Figure 5.14: Animated Bubble Plot
  • Understand Relationships Using Correlation Analysis
  • Introduction
  • Figure 6.1: Example Linear Correlation Between Ice Cream Sales and Daily Temperature
  • Correlation and Causation
  • Correlation Matrix
  • Figure 6.2: Correlation Coefficient Color Shading
  • Example: Explore Child Mortality Rate
  • Table 6.1: Variables Supporting Correlation Analysis of Child Mortality Rate
  • Figure 6.3: Changing Aggregation Type of Child Mortality Rate to Average
  • Figure 6.4: Histogram of Child Mortality Rate Variable
  • Figure 6.5: Box Plot of Child Mortality Rate Grouped by Region
  • Figure 6.6: Correlation Matrix of Child Mortality and Related Health Measures
  • Figure 6.2: High Degree of Correlation Between Child Mortality Rate and Rate of Access to Improved Water Source
  • Figure 6.8: Simplifying the Correlation Matrix
  • Figure 6.9: Correlation Matrix Centered Around Child Mortality Rate
  • Figure 6.10: Correlation Matrix Tabular View
  • Scatter Plot and Fit Line
  • Figure 6.11: Linear Fit Line with Residual or Error Bars
  • Example: Child Mortality Rate Scatter Plot
  • Figure 6.12: Scatter Plot of Child Mortality Versus Rate of Access to Improved Water Source
  • Figure 6.13: Linear Fit Line Generated by SAS Visual Analytics
  • Figure 6.14: Additional Regression Line Information
  • Table 6.1: Key Regression Model Properties
  • Figure 6.15: Excluding Outliers Using Selected Data Points
  • Figure 6.16: Cubic Fit Line Generated by SAS Visual Analytics
  • Figure 6.17: Cubic Fit Line Model Information
  • Figure 6.18: Scatter Plot with Region as Grouping Variable
  • Machine Learning and Visual Modeling
  • Introduction
  • Why Visual Modeling
  • Approaches and Techniques
  • Figure 7.1: Prediction Given a Set of Input Variables
  • Overall approach
  • Techniques and Algorithms
  • Table 7.1: Predictive Modeling Algorithms
  • Preparing the Data for Modeling
  • Data Partitioning
  • Figure 7.2: Assigning Partition Variable
  • Figure 7.3: Creating New Partition Variable
  • Dealing with Missing Data
  • Figure 7.4: Informative Missingness Option
  • Feature Engineering
  • Outlier Processing
  • Binning
  • Figure 7.5: Example of Variable Binning
  • Log Transform
  • Splitting/extracting features
  • Normalize/standardize variables
  • Model Assessment
  • Variable Importance
  • Figure 7.6: Variable Importance Chart using Information Gain Criterion Value
  • Figure 7.7: P-Value-based Variable Importance Chart
  • Model Fit Statistics
  • Figure 7.8: Changing the Overall Fit Statistic
  • Misclassification Chart
  • Figure 7.9: Confusion Matrix
  • Figure 7.10: Misclassification Plot
  • ROC Chart
  • Figure 7.11: ROC Chart
  • Lift Chart
  • Figure 7.12: Cumulative Lift Chart
  • Figure 7.13: Model Comparison Object
  • Improving Your Model
  • Avoid Underfitting and Overfitting
  • Figure 7.14: How to Fit a Model
  • Figure 7.15: Assessing Your Model Using the Validation Data Set
  • Adding a Group-By Variable
  • Figure 7.16: Adding a Group Variable During Modeling
  • Using Better Hyperparameters
  • Figure 7.17: Autotuning Modeling Hyperparameters
  • Using Your Model
  • Figure 7.18: Export Model as SAS Score Code
  • Predictive Modeling Using Decision Trees
  • Overview
  • Figure 8.1: A Decision Tree Model Predicting Color of Leaf
  • Model Building and Assessment
  • Data Preparation
  • Figure 8.2: Creating a New Custom Category
  • Figure 8.3: Bar Chart of New Custom Target Variable
  • Figure 8.4: Creating Data Partitions
  • Predictor Variables Selection
  • Building the Decision Tree Model
  • Figure 8.5: Selecting the Target Event
  • Figure 8.6: Decision Tree Model Predicting Child Mortality Level
  • Tree Window
  • Figure 8.7: Tree Window from Decision Tree Model Build
  • Figure 8.8: Activating and Using the Tree Overview Tool
  • Figure 8.9: Changing the Layout of the Decision Tree Model Object
  • Interpreting the Model
  • Figure 8.10: Interpreting the First Split of the Decision Tree
  • Figure 8.11: Interpreting the Leaf Node
  • Overall Fit and Assessment Plots
  • Figure 8.12: Switching Overall Model Fit Statistics
  • Misclassification Plot
  • Figure 8.13: Misclassification Plot
  • Variable Importance Chart
  • Figure 8.14: Variable Importance Chart
  • Lift Chart
  • Figure 8.15: Cumulative Lift Chart
  • Tuning and Improving the Model
  • Adding and Removing Predictor Variables
  • Figure 8.16: New Variable Importance Chart
  • Dealing with Missing Values
  • Figure 8.17: Missing Value Assignment Strategy
  • Tuning the Hyperparameters
  • Figure 8.18: Default Hyperparameter Values for Decision Tree
  • Figure 8.19: Configuring Hyperparameter Autotuning
  • Figure 8.20: Improved Cumulative Lift Chart
  • Figure 8.21: New Decision Tree Based on Autotuning
  • Tree Pruning
  • Figure 8.22: Pruning the Tree Using Automated Options
  • Figure 8.23: Simpler Tree After Automated Pruning
  • Predictive Modeling Using Linear Regression
  • Overview
  • Model Building and Assessment
  • Figure 9.1: Duplicating an Existing Modeling Object
  • Data Preparation
  • Building the Linear Regression Model
  • Figure 9.2: Linear Regression Model
  • Overall Fit Statistics
  • Fit Summary Window
  • Figure 9.3: Model Fit Summary Window
  • Residual Plot
  • Figure 9.4: Residual Plot
  • Figure 9.5: Details Window from Residual Plot
  • Figure 9.6: Residual Plot Histogram
  • Details Table
  • Figure 9.7: Fit Statistics Details Table
  • Figure 9.8: Parameter Estimates Details Table
  • Interpreting the Model
  • Tuning and Improving the Model
  • Adjust Input Variables
  • Removing Outliers
  • Figure 9.9: Selecting Multiple Points on the Residual Plot
  • Figure 9.10: Showing Selected Points from Residual Plot
  • Figure 9.11: Excluding Points from the Residual Plot
  • Figure 9.12: New Residual Plot with Outliers Removed
  • Figure 9.13: New Residual Plot Histogram with Outliers Removed
  • Adding Group-By Variables
  • Figure 9.14: Adding Region as a Group-By Variable
  • Figure 9.15: New Linear Regression with Group-By Variable
  • Figure 9.16: Selecting a Model Grouped by Region
  • Bring It All Together
  • Combine and Experiment
  • Combining Visualizations
  • Figure 10.1: Linking the Decision Tree and Bar Chart Using a Filter Action
  • Figure 10.2: A Page with a Linked Bar Chart and Decision Tree Model
  • Figure 10.3: Interacting and Applying Filter to the Visualization Objects
  • Experimenting
  • Share and Communicate
  • Report Sharing
  • Figure 10.4: Submitting Comments at Multiple Levels
  • Mobile App
  • Figure 10.5: SAS Visual Analytics Mobile App
  • Figure 10.6: Interaction Within the SAS Visual Analytics Mobile App
  • Production and Deployment
  • Pipeline Modeling
  • Figure 10.7: Creating a Model Pipeline from a Visual Modeling Object
  • Figure 10.8: Developing Pipeline Model Using SAS Model Studio
  • Model Management and Deployment
  • Where to Go from Here
  • Ongoing Learning and Valuable Resources

Dateiformat: PDF
Kopierschutz: Adobe-DRM (Digital Rights Management)

Systemvoraussetzungen:

Computer (Windows; MacOS X; Linux): Installieren Sie bereits vor dem Download die kostenlose Software Adobe Digital Editions (siehe E-Book Hilfe).

Tablet/Smartphone (Android; iOS): Installieren Sie bereits vor dem Download die kostenlose App Adobe Digital Editions (siehe E-Book Hilfe).

E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nicht Kindle)

Das Dateiformat PDF zeigt auf jeder Hardware eine Buchseite stets identisch an. Daher ist eine PDF auch für ein komplexes Layout geeignet, wie es bei Lehr- und Fachbüchern verwendet wird (Bilder, Tabellen, Spalten, Fußnoten). Bei kleinen Displays von E-Readern oder Smartphones sind PDF leider eher nervig, weil zu viel Scrollen notwendig ist. Mit Adobe-DRM wird hier ein "harter" Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.

Bitte beachten Sie bei der Verwendung der Lese-Software Adobe Digital Editions: wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!

Weitere Informationen finden Sie in unserer E-Book Hilfe.


Download (sofort verfügbar)

20,49 €
inkl. 5% MwSt.
Download / Einzel-Lizenz
PDF mit Adobe-DRM
siehe Systemvoraussetzungen
E-Book bestellen