Building Machine Learning Systems with Python - Third edition

This is the code repository for Building Machine Learning Systems with Python - Third edition, published by Packt.

Explore machine learning and deep learning techniques for building intelligent systems using scikit-learn and TensorFlow

What is this book about?

Machine learning allows systems to learn without being explicitly programmed. Python is one of the most popular languages used to develop machine learning applications which take advantage of its extensive library support. This third edition of Building Machine Learning Systems with Python addresses recent developments in the field, by covering the most used datasets and libraries to help you build practical machine learning systems.

This book covers the following exciting features:

• Build a classification system that can be applied to text, image, and sound
• Employ Amazon Web Services (AWS) to run analysis on the cloud
• Solve problems related to regression using TensorFlow
• Recommend products to users based on their past purchases
• Explore the steps required to add collaborative filtering using TensorFlow

If you feel this book is for you, get your copy today!

Instructions and Navigations

All of the code is organized into folders. For example, Chapter01.

The code will look like the following:

 def fetch_posts(fn):
     for line in open(fn, "r"):
         post_id, text = line.split("\t")
         yield int(post_id), text.strip()
 

Following is what you need for this book: Building Machine Learning Systems with Python is for data scientists, machine learning developers, and Python developers who want to learn how to build increasingly complex machine learning systems. You will use Python's machine learning capabilities to develop effective solutions. Prior knowledge of Python programming is expected.

With the following software and hardware list you can run all code files present in the book (Chapter 1-14).

Software and Hardware List

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it.

Related products

• Mastering Machine Learning Algorithms [Packt] [Amazon]

• Machine Learning Solutions [Packt] [Amazon]

Get to Know the Authors

Luis Pedro Coelho is a computational biologist who analyzes DNA from microbial communities to characterize their behavior. He has also worked extensively in bioimage informatics―the application of machine learning techniques for the analysis of images of biological specimens. His main focus is on the processing and integration of large-scale datasets. He has a PhD from Carnegie Mellon University and has authored several scientific publications. In 2004, he began developing in Python and has contributed to several open source libraries. He is currently a faculty member at Fudan University in Shanghai.

Willi Richert has a PhD in machine learning/robotics, where he has used reinforcement learning, hidden Markov models, and Bayesian networks to let heterogeneous robots learn by imitation. Now at Microsoft, he is involved in various machine learning areas, such as deep learning, active learning, or statistical machine translation. Willi started as a child with BASIC on his Commodore 128. Later, he discovered Turbo Pascal, then Java, then C++—only to finally arrive at his true love: Python.

Matthieu Brucher is a computer scientist who specializes in high-performance computing and computational modeling and currently works for JPMorgan in their quantitative research branch. He is also the lead developer of Audio ToolKit, a library for real-time audio signal processing. He has a PhD in machine learning and signals processing from the University of Strasbourg, two Master of Science degrees—one in digital electronics and signal processing and another in automation – from the University of Paris XI and Supelec, as well as a Master of Music degree from Bath Spa University.

Other books by the authors

• Building Machine Learning Systems with Python
• Building Machine Learning Systems with Python - Second Edition

Suggestions and Feedback

Click here if you have any feedback or suggestions.