Book Image

Mastering Java for Data Science

By : Alexey Grigorev
Book Image

Mastering Java for Data Science

By: Alexey Grigorev

Overview of this book

Java is the most popular programming language, according to the TIOBE index, and it is a typical choice for running production systems in many companies, both in the startup world and among large enterprises. Not surprisingly, it is also a common choice for creating data science applications: it is fast and has a great set of data processing tools, both built-in and external. What is more, choosing Java for data science allows you to easily integrate solutions with existing software, and bring data science into production with less effort. This book will teach you how to create data science applications with Java. First, we will revise the most important things when starting a data science application, and then brush up the basics of Java and machine learning before diving into more advanced topics. We start by going over the existing libraries for data processing and libraries with machine learning algorithms. After that, we cover topics such as classification and regression, dimensionality reduction and clustering, information retrieval and natural language processing, and deep learning and big data. Finally, we finish the book by talking about the ways to deploy the model and evaluate it in production settings.
Table of Contents (17 chapters)
Title Page
About the Author
About the Reviewers
Customer Feedback

Cluster analysis

Clustering, or cluster analysis, is another family of unsupervised learning algorithms. The goal of clustering is to organize data into clusters such that the similar items end up in the same cluster, and dissimilar items in different ones.

There are many different algorithm families for performing clustering, and they differ in how they group elements.

The most common families are as follows:

  • Hierarchical: This organizes the dataset into a hierarchy, for example, agglomerative and divisive clustering. The result is typically a dendrogram.
  • Partitioning: This splits the dataset into K disjoint classes--K is often specified in advance--for example, K-means.
  • Density-based: This organizes the items based on density regions; if there are many items in some dense regions, they form a cluster, for example, DBSCAN.
  • Graph-based: This represents the relations between items as a graph and applies grouping algorithms from the graph theory, for example, connected components and minimal spanning...