Learn Pyspark: Build Python-Based Machine Learning and Deep Learning Models (Paperback)

No of pages -15

This chapter covers Spark’s core architecture, APIs and gets readers set up with the development environment.The chapter doubles up as an introduction to the book’s format, including an explanation of formatting practices, pointers to the book’s accompanying codebase online, and support contact information. 

Sub -Topics

? What is Spark

? Configuring your development environment

? Configuring a cloud development environment

? Installing required libraries

Chapter 2: Big Data Processing

No of pages: 20

The chapter would cover basic to advanced big data processing techniques using PySpark which includes data ingestion, cleaning and transformations. This chapter walks through multiple approaches to solve a data processing task like creating features from clickstream data

Sub - Topics

? Understanding data ingestion

? Exploratory data analysis

? Understanding data processing

Chapter 3: Streaming Data Processing

No of pages : 20

This chapter showcases the highly technical and complex process of building pipelines for streaming data for processing and making it ready to be used for various analysis or Machine Learning.

Sub - Topics:

? What is streaming data

? Spark streaming Vs Storm Vs Flink

? Create your own streaming application

Chapter 4: PySpark with Airflow

This chapter is devoted to the process of using Airflow with PySpark and building pipelines for scheduling various PySpark jobs for data processing and machine learning. It also draws the comparison between various alternatives such as Pinball, Azkaban and Luigi

Sub - Topics:

? Introduction to Airflow

? PySpark jobs with Airflow

? Business use case

Chapter 5: Introduction to PySpark MLlib

No of pages:15

This chapter serves as an introduction to our core theme of the book: Machine Learning & Deep Learning using PySpark.The chapter begins with covering various components of Spark’s MLlib library and offers information on the usage of MLlib APIs to build traditional as well as Deep Learning models

Sub - Topics:

? Introduction to machine learning

? Explore Spark MLlib in Depth

? Introduction to deep learning with PySpark

Chapter 6: Supervised Machine Learning

No of pages: 25

This chapter focuses on industrial applications of Supervised Machine Learning models along with implementation in PySpark. This chapter also demonstrates various techniques like hyperparameter tuning and workflows for building Supervised Machine learning models

Sub - Topics:

? Linear regression in the business context

? Use logistic regression for real

? Applying Decision trees & Random Forests

Chapter 7: Unsupervised Machine Learning using MLlib

No of pages:15

This chapter covers the Unsupervised Machine learning techniques and showcases the implementation of clustering based on user’s web behavior / online activity data. The chapter includes the complex steps to do feature engineering for clustering and highlights the limitation of traditional clustering algorithms.

Sub - Topics:

? Hierarchical Clustering

? K Means

Chapter 8: Deep Learning models with PySpark

No of pages:25

This chapter offers a detailed view of Deep Learning models for various applications such as Forecasting ,Image recognition and Multi classification. The chapter also introduces optimization approaches and the techniques for hyperparameter tuning . Finally, the chapter covers the workflows to build deep learning models using PySpark

Sub - Topics:

? Introduction to Deep Learning

? Introducing hyperparameter optimization

? Build deep learning models with PySpark

Chapter 9: Analysis using GraphFrames

No of pages:30

This chapter would focus on understanding the core of Graph algorithms and doing graph analytics using Spark’s Graphframe library on the industrial dataset. It showcases the use of Graphframe to uncover the underlying relationships and visualize the insights.

Sub ? Topics:

? Introduction to Graph Algorithms

? Applying Graphframe for Graph Analytics

? The business Use case of Graphframe

Pramod Singh (지은이)    정보 더보기

분야의 베스트셀러 >