Machine Learning with SAS Viya

Chapter 2: Preparing Your Data: Introduction

Introduction

Explore the Data

Model Studio: Data Preprocessing

Demo 2.1: Exploring Source Data

Divide the Data

Honest Assessment

Address Rare Events

Model Studio

Demo 2.2: Modifying the Data Partition

Data Preparation Best Practices

Model Studio: Feature Engineering Template

Demo 2.3: Running the Feature Engineering Pipeline Template

Quiz

Introduction

Trash in—trash out! To be effective, machine learning models need to be built from well-prepared data. It is often said that 80% of the time spent in building a successful machine learning application is spent in data preparation (Dasu and Johnson 2003). Data preparation is not strictly about correctly transforming and cleaning existing data. It also ...