Data Science at the Command Line: Obtain, Scrub, Explore, and Model Data with Unix Power Tools

The book provides a comprehensive guide to leveraging the power of the command line for data science, covering tasks such as data acquisition, cleaning, exploration, modeling, and workflow management. It offers a Docker image with over 80 tools and demonstrates how the command line can be an agile, scalable, and extensible technology for data scientists, analysts, engineers, software and machine learning engineers, and system administrators.

\n Format: Paperback / softback
\n Length: 250 pages
\n Publication date: 27 August 2021
\n Publisher: O'Reilly Media, Inc, USA
\n

This comprehensive guide showcases the remarkable flexibility of the command line, empowering data scientists to enhance their efficiency and productivity. By harnessing the power of small yet powerful command-line tools, you'll learn how to swiftly acquire, cleanse, explore, and model your data. Author Jeroen Janssens, a renowned expert in data science, has created a Docker image containing over 80 indispensable tools, ensuring compatibility across Windows, macOS, and Linux platforms.

Discover the agile, scalable, and extensible nature of the command line as you embark on a journey of efficiency. Even if you're already proficient in Python or R for data processing, this guide will reveal how leveraging the command line can revolutionize your data science workflow.

Ideal for data scientists, analysts, engineers, software and machine learning engineers, and system administrators, this book offers a wealth of knowledge and practical techniques.

Acquire data from websites, APIs, databases, and spreadsheets with ease, utilizing a variety of command-line tools. Conduct scrub operations on diverse file formats, including text, CSV, HTML, XML, and JSON, ensuring data accuracy and cleanliness.

Explore your data with precision, employing powerful command-line tools to compute descriptive statistics, create visualizations, and uncover hidden insights.

Manage your data science workflow efficiently, utilizing command-line tools for task automation, version control, and project organization.

Create reusable command-line tools by leveraging one-liners and existing Python or R code, saving time and effort.

Parallelize and distribute data-intensive pipelines, leveraging the command line's capabilities for high-performance computing.

Model data with dimensionality reduction, clustering, regression, and classification algorithms, utilizing command-line tools for advanced analysis and modeling tasks.

By embracing the power of the command line, you'll unlock new levels of productivity and efficiency in your data science endeavors. This revised guide provides the foundation you need to thrive in the fast-paced world of data science, regardless of your level of experience.

\n Weight: 494g\n
Dimension: 176 x 231 x 20 (mm)\n
ISBN-13: 9781492087915\n
Edition number: 2 New edition\n