Book Image

Spark for Data Science

By : Srinivas Duvvuri, Bikramaditya Singhal
Book Image

Spark for Data Science

By: Srinivas Duvvuri, Bikramaditya Singhal

Overview of this book

This is the era of Big Data. The words ‘Big Data’ implies big innovation and enables a competitive advantage for businesses. Apache Spark was designed to perform Big Data analytics at scale, and so Spark is equipped with the necessary algorithms and supports multiple programming languages. Whether you are a technologist, a data scientist, or a beginner to Big Data analytics, this book will provide you with all the skills necessary to perform statistical data analysis, data visualization, predictive modeling, and build scalable data products or solutions using Python, Scala, and R. With ample case studies and real-world examples, Spark for Data Science will help you ensure the successful execution of your data science projects.
Table of Contents (18 chapters)
Spark for Data Science
Credits
Foreword
About the Authors
About the Reviewers
www.PacktPub.com
Preface

Data preparation


The data exploration stage helped us identify all the issues that needed to be fixed before proceeding to the modeling stage. Each individual issue requires careful thought and deliberation to choose the best fix. Here are some common issues and the possible fixes. The best fix is dependent on the problem at hand and/or the business context.

Too many levels in a categorical variable

This is one of the most common issues we face. The treatment of this issue is dependent on multiple factors:

  • If the column is almost always unique, for example, it is a transaction ID or timestamp, then it does not participate in modeling unless you are deriving new features from it. You may safely drop the column without losing any information content. You usually drop it during the data cleansing stage itself.

  • If it is possible to replace the levels with coarser-grained levels (for example, state or country instead of city) that make sense in the current context, then usually that is the best way...