EPUB PDF JPG
本書有DRM加密保護,需使用HyRead閱讀軟體開啟
  • Building a recommendation engine with Scala:learn to use Scala to build a recommendation engine from scratch and empower your website users
  • 點閱:6
  • 作者: Saleem Ansari
  • 出版社:Packt Publishing Ltd.
  • 出版年:2016
  • ISBN:9781785282584; 9781785282980
  • 格式:EPUB 流式,PDF,JPG繁簡轉換朗讀

With the growth of the Internet and the widespread adoption of e-commerce and social media, a lot of new services have arrived in recent years. We shop online, we communicate online, we stay up-to-date online, and so on. We have a huge growth of data, and this has made it increasingly tough for service providers to provide only the relevant data. Recommendation engines help us provide only the relevant data to a consumer.

In this book, we will use the Scala programming language and the many tools that are available in its ecosystem, such as Apache Spark, Play Framework, Spray, Kafka,PredictionIO, to build a recommendation engine. We will reach that stage step by step with a real world dataset and a fully functional application that gives readers a hands-on experience. We have discussed the key topics in detail for readers to get started on their own. You will learn the challenges and approaches used to build a recommendation engine.

You must have some understanding of the Scala programming language, SBT, and command-line tools. An understanding of different machine learning and data processing concepts is beneficial but not required. You will learn the tools necessary for writing data-munging programs and experimenting using Scala.

Saleem Ansari is a full-stack developer with over 8 years of industry experience.

He has a special interest in machine learning and information retrieval. Having implemented data ingestion and a processing pipeline in Core Java and Ruby separately, he knows the challenges faced by huge data sets in such systems. He has worked for companies such as Red Hat, Impetus Technologies, Belzabar Software,and Exzeo Software. He is also a passionate member of free and open source software (FOSS) community. He started his journey with FOSS in the year 2004. The very next year, he formed JMILUG—Linux Users Group at Jamia Millia Islamia University, New Delhi. Since then, he has been contributing to FOSS by organizing community activities and contributing code to various projects (for more information, visit http://github.com/tuxdna). He also mentors students about FOSS and its benefits.

In 2015, he reviewed two books related to Apache Mahout, namely Learning Apache Mahout and Apache Mahout Essentials; both the books were produced by Packt Publishing.

  • Preface
  • Chapter 1: Introduction to Scala and Machine Learning
    • Setting up Scala, SBT, and Apache Spark
    • A quick introduction to Scala
    • Machine learning and recommendation engines
    • Summary
  • Chapter 2: Data Processing Pipeline Using Scala
    • Entree – a sample dataset for recommendation systems
    • ETL – extract transform load
    • Extraction and transformation for machine learning
    • Setting up MongoDB and Apache Kafka
    • Data processing pipeline for Entree
    • Summary
  • Chapter 3: Conceptualizing an E-Commerce Store
    • Importance of recommender systems in e-commerce
    • Types of recommendation methods
    • The architecture of the project
    • Summary
  • Chapter 4: Machine Learning Algorithms
    • Hands on with Spark/MLlib
    • Data types
    • Statistics
    • Feature extraction and transformation
    • Classification/regression
    • Clustering
    • Association analysis
    • Summary
  • Chapter 5: Recommendation Engines and Where They Fit in?
    • Populating the Amazon dataset
    • Creating a web app with user/product pages
    • Adding recommendation pages
    • Summary
  • Chapter 6: Collaborative Filtering versus Content-Based Recommendation Engines
    • Content-based recommendation
    • Content-based recommendation steps
    • Collaborative filtering based recommendation
    • What is ALS?
    • Content-based versus collaborative filtering
    • Summary
  • Chapter 7: Enhancing the User Experience
    • Adding product search
    • Adding recommendation listings
    • Understanding recommendation behavior
    • Summary
  • Chapter 8: Learning from User Feedback
    • Introducing PredictionIO
    • Unified recommender
    • Summary
  • Index
紙本書 NT$ 1120
單本電子書
NT$ 896

還沒安裝 HyRead 3 嗎?馬上免費安裝~
QR Code