Tree-Based Machine Learning Methods in SAS® Viya®
- Length: 364 pages
- Edition: 1
- Language: English
- Publisher: SAS Institute
- Publication Date: 2022-02-22
- ISBN-10: 1954846630
- ISBN-13: 9781954846630
- Sales Rank: #0 (See Top 100 Books)
Discover how to build decision trees using SAS® Viya®!
Tree-Based Machine Learning Methods in SAS® Viya® covers everything from using a single tree to more advanced bagging and boosting ensemble methods. The book includes discussions of tree-structured predictive models and the methodology for growing, pruning, and assessing decision trees, forests, and gradient boosted trees. Each chapter introduces a new data concern and then walks you through tweaking the modeling approach, modifying the properties, and changing the hyperparameters, thus building an effective tree-based machine learning model. Along the way, you will gain experience making decision trees, forests, and gradient boosted trees that work for you.
By the end of this book, you will know how to:
- build tree-structured models, including classification trees and regression trees.
- build tree-based ensemble models, including forest and gradient boosting.
- run isolation forest and Poisson and Tweedy gradient boosted regression tree models.
- implement open source in SAS and SAS in open source.
- use decision trees for exploratory data analysis, dimension reduction, and missing value imputation.
Cover Copyright Page Contents About This Book About These Authors Acknowledgments Foreword Chapter 1: Introduction to Tree-Structured Models Introduction Decision Tree – What Is It? Types of Decision Trees Tree-Based Models in SAS Viya Analytics Platform from SAS SAS Visual Data Mining and Machine Learning The Decision Tree Action Set TREESPLIT, FOREST, and GRADBOOST Procedures Decision Tree, Forest, and Gradient Boosting Tasks and Objects Introducing Model Studio Demo 1.1: Model Studio Introductory Flow Quiz Chapter 2: Classification and Regression Trees Classification Trees Decision Regions Posterior Probabilities Demo 2.1: Building a Default Classification Tree Model Scoring Demo 2.2: Scoring a Decision Tree Model in Model Studio Regression Trees Predicted Values and Partitioned Input Space Demo 2.3: Building a Regression Tree Pipeline from SAS Visual Statistics Quiz Chapter 3: Growing a Decision Tree Recursive Partitioning Root-Node Split and One-Deep Space Depth Two and Two-Deep Space Alternatives to Recursive Partitioning Constructing Decision Trees Interactively Demo 3.1: Interactively Building a Regression Tree in SAS Visual Statistics Feature Selection Using Split Search Split Points Splitting on a Nominal Input Splitting on an Ordinal Input Splitting on an Interval Input Demo 3.2: Exploring Split Search Tree Growth Options Splitting Criteria Splitting Criteria Based on Impurity Splitting Criteria Based on Statistical Tests Demo 3.3: Experimenting with the Splitting Criteria Quiz Chapter 4: Decision Trees: Strengths, Weaknesses, and Uses Missing Values in Decision Trees A Simple Example Missing Values in Ordinal Inputs Variable Importance Methods for Computing Variable Importance Introducing the TREESPLIT Procedure Demo 4.1: Handling Missing Values and Determining Important Variables Strengths and Weaknesses of Decision Trees Secondary Uses of Decision Trees Initial Data Analysis (IDA) and Exploratory Data Analysis (EDA) Interaction Detection Identifying Important Variables Model Interpretation Variable Selection Nominal Levels Consolidation Discretizing Interval Inputs Missing Value Imputation Stratified Modeling Interactive Training Quiz Chapter 5: Tuning a Decision Tree Model Complexity and Generalization Pruning: Getting the Right-Sized Tree Pre-Pruning Options Post-Pruning Options Pruning Requirements Honest Assessment Model Selection Criteria Demo 5.1: Pruning Decision Trees Using Validation Data Cross Validation Demo 5.2: Performing Cross Validation in a Regression Tree Autotuning Demo 5.3: Comparing Various Tree Settings and Performance Quiz Chapter 6: Ensemble of Trees: Bagging, Boosting, and Forest Instability in a Decision Tree Perturb and Combine (P&C) Ensemble Models Bagging Boosting Comparison of Tree-Based Models Forest Models Combining Trees in a Forest Perturbing Trees in a Forest Splitting Options You Already Know Measuring Variable Importance Demo 6.1: Building a Default Forest Model Tuning a Forest Model Tuning Parameters Manually Autotuning Hyperparameters The FOREST Procedure Demo 6.2: Tuning a Forest Model Quiz Chapter 7: Additional Forest Models Open-Source Random Forest Models Open Source Code Node Demo 7.1: Executing Open-Source Models in SAS Viya Isolation Forest Models Detecting Fraud Using Tree-Based Methods What Is an Isolation Forest? How Do Isolation Forests Detect Anomalies? Fraud Example Demo 7.2: Detecting Fraud Using an Isolation Forest in SAS Studio Introduction to Deep Forest Models Deep Forest Actions in SAS Viya Quiz Chapter 8: Tree-Based Gradient Boosting Machines Gradient Boosting Models Key Components of Gradient Boosting Weak Learner Model Tree-Splitting Options You Already Know Loss Function Numerical Optimization Method Additive Ensemble Model Avoiding Overfitting in Gradient Boosting Demo 8.1: Building a Default Gradient Boosting Model in Model Studio and Scoring Using ASTORE in SAS Studio Comparison of Gradient Boosted Decision Trees with Other Tree-Based Models Tuning a Gradient Boosting Model Tuning Parameters Manually Autotuning Hyperparameters Demo 8.2: Modifying and Autotuning a Gradient Boosting Model Quiz Chapter 9: Additional Gradient Boosting Models Gradient Boosting for Transfer Learning Transfer Learning Using the GRADBOOST Procedure Demo 9.1: Transfer Learning Using Gradient Boosting Transfer Learning and Autotuning Gradient Boosted Poisson and Tweedie Regression Trees Demo 9.2: Building a Gradient Tree-Boosted Tweedie Compound Poisson Model SAS Gradient Boosting Using Open Source Demo 9.3: Training and Scoring a SAS Gradient Boosting Model Using Python Quiz Appendix A: Practice Case Study References
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.