Bøker i Addison-Wesley Data & Analytics Series-serien

Deep learning is one of today's hottest fields. This approach to machine learning is achieving breakthrough results in some of today's highest profile applications, in organizations ranging from Google to Tesla, Facebook to Apple. Thousands of technical professionals and students want to start leveraging its power, but previous books on deep learning have often been non-intuitive, inaccessible, and dry. In Deep Learning Illustrated, three world-class instructors and practitioners present a uniquely visual, intuitive, and accessible high-level introduction to the techniques and applications of deep learning. Packed with vibrant, full-color illustrations, it abstracts away much of the complexity of building deep learning models, making the field more fun to learn and accessible to a far wider audience. Part I's high-level overview explains what Deep Learning is, why it has become so ubiquitous, and how it relates to concepts and terminology such as Artificial Intelligence, Machine Learning, Artificial Neural Networks, and Reinforcement Learning. These opening chapters are replete with vivid illustrations, easy-to-grasp analogies, and character-focused narratives. Building on this foundation, the authors then offer a practical reference and tutorial for applying a wide spectrum of proven deep learning techniques. Essential theory is covered with as little mathematics as possible and is illuminated with hands-on Python code. Theory is supported with practical "run-throughs" available in accompanying Jupyter notebooks, delivering a pragmatic understanding of all major deep learning approaches and their applications: machine vision, natural language processing, image generation, and videogaming. To help readers accomplish more in less time, the authors feature several of today's most widely used and innovative deep learning libraries, including TensorFlow and its high-level API, Keras; PyTorch; and the recently released, high-level Coach, a TensorFlow API that abstracts away the complexity typically associated with building Deep Reinforcement Learning algorithms. Ideal for software developers, data scientists, and analysts at all levels of experience Teaches through simple visuals, accessible Python code examples, character-driven narratives, and intuitive analogies Covers today's leading applications, including machine vision, natural language processing, image generation, and videogames Introduces four powerful Deep Learning libraries: TensorFlow, Keras, PyTorch, and Coach Carefully designed to minimize mathematical formulae and avoid unnecessary complexity The first full-color, illustrated, hands-on guide to the fundamentals of modern, deep-learning AI: simply the most intuitive, practical way to get started Ideal for software developers, data scientists, and analysts at all levels of experience Teaches through simple visuals, accessible Python code examples, character-driven narratives, and intuitive analogies Covers today's leading applications, including machine vision, natural language processing, image generation, and videogames Introduces four powerful Deep Learning libraries: TensorFlow, Keras, PyTorch, and Coach Carefully designed to minimize mathematical formulae and avoid unnecessary complexity

In just a few years, deep reinforcement learning (DRL) systems such as DeepMinds DQN have yielded remarkable results. This hybrid approach to machine learning shares many similarities with human learning: its unsupervised self-learning, self-discovery of strategies, usage of memory, balance of exploration and exploitation, and its exceptional flexibility. Exciting in its own right, DRL may presage even more remarkable advances in general artificial intelligence. Deep Reinforcement Learning in Python: A Hands-On Introduction is the fastest and most accessible way to get started with DRL. The authors teach through practical hands-on examples presented with their advanced OpenAI Lab framework. While providing a solid theoretical overview, they emphasize building intuition for the theory, rather than a deep mathematical treatment of results. Coverage includes: Components of an RL system, including environment and agents Value-based algorithms: SARSA, Q-learning and extensions, offline learning Policy-based algorithms: REINFORCE and extensions; comparisons with value-based techniques Combined methods: Actor-Critic and extensions; scalability through async methods Agent evaluation Advanced and experimental techniques, and more How to achieve breakthrough machine learning performance by combining deep neural networks with reinforcement learning Reduces the learning curve by relying on the authors' OpenAI Lab framework: requires less upfront theory, math, and programming expertise Provides well-designed, modularized, and tested code examples with complete experimental data sets to illuminate the underlying algorithms Includes case studies, practical tips, definitions, and other aids to learning and mastery Prepares readers for exciting future advances in artificial general intelligenceThe accessible, hands-on, full-color tutorial for building practical deep reinforcement learning solutions How to achieve breakthrough machine learning performance by combining deep neural networks with reinforcement learning Reduces the learning curve by relying on the authors' OpenAI Lab framework: requires less upfront theory, math, and programming expertise Provides well-designed, modularized, and tested code examples with complete experimental data sets to illuminate the underlying algorithms Includes case studies, practical tips, definitions, and other aids to learning and mastery Prepares readers for exciting future advances in artificial general intelligence

Master the Fundamentals of Modern Visual Analytics--and Craft Compelling Visual Narratives in Tableau!   Do you need to persuade or inform people? Do you have data? Then you need to master visual analytics and visual storytelling. Today, the #1 tool for telling visual stories with data is Tableau, and demand for Tableau skills is soaring. In Visual Analytics Fundamentals, renowned visual storyteller and analytics professor Lindy Ryan introduces all the fundamental visual analytics knowledge, cognitive and perceptual concepts, and hands-on Tableau techniques you'll need.   Ryan puts core analytics and visual concepts upfront, so you'll always know exactly what you're trying to accomplish and can apply this knowledge with any tool. Building on this foundation, she presents classroom-proven guided exercises for translating ideas into reality with Tableau 2022. You'll learn how to organize data and structure analysis with stories in mind, embrace exploration and visual discovery, and articulate your findings with rich data, well-curated visualizations, and skillfully crafted narrative frameworks. Ryan's insider tips take you far beyond the basics--and you'll rely on her expert checklists for years to come.   Communicate more powerfully by applying scientific knowledge of the human brainGet started with the Tableau platform and Tableau Desktop 2022Connect data and quickly prepare it for analysisAsk questions that help you keep data firmly in contextChoose the right charts, graphs, and maps for each project--and avoid the wrong onesCraft storyboards that reflect your message and audienceDirect attention to what matters mostBuild data dashboards that guide people towards meaningful outcomesMaster advanced visualizations, including timelines, Likert scales, and lollipop charts   This book has only one prerequisite: your desire to communicate insights from data in ways that are memorable and actionable. It's for executives and professionals sharing important results, students writing reports or presentations, teachers cultivating data literacy, journalists making sense of complex trends. . . . practically everyone! Don't even have Tableau? Download your free trial of Tableau Desktop and let's get started!

Data science and machine learningtwo of the world's hottest fieldsare attracting talent from a wide variety of technical, business, and liberal arts disciplines. Python, the world's #1 programming language, is also the most popular language for data science and machine learning. This is the first guide specifically designed to help students with widely diverse backgrounds learn foundational Python so they can use it for data science and machine learning. This book is catered to introductory-level college courses on data science. Leading data science instructor and practitioner Kennedy Behrman first walks through the process of learning to code for the first time with Python and Jupyter notebook, then introduces key libraries every Python data science programmer needs to master. Once students have learned these foundations, Behrman introduces intermediate and applied Python techniques for real-world problem-solving. Throughout, Foundational Python for Data Science presents hands-on exercises, learning assessments, case studies, and moreall created with Colab (Jupyter compatible) notebooks, so students can execute all coding examples interactively without installing or configuring any software.

In Data Cleaning for Effective Data Science, leading data science trainer David Mertz provides the most systematic guide to cleaning data for any project, using any library or toolset. Mertz introduces many powerful techniques for analyzing, manipulating, and pre-processing data sources. He offers best practices for working with leading data formats such as JSON, CSV, SQL RDBMSes, HDF5, NoSQL databases, files in image formats, binary serialized data structures, and more. Mertz also focuses on crucial issues within the data itself, including missing data, outliers, biasing trends, class imbalance, value imputation, over/under-sampling, normalization and/or randomization, and anomalies. This guide is organized around downloadable datasets, each illuminating specific issues with data integrity or quality. Each chapter explores the best ways to diagnose, analyze, and remediate these issues, offering hands-on practice using tools such as Python, Pandas, sklearn.preprocessing, scipy.stats, R, and Tidyverse. While the examples are demonstrated with widely-used tools, Mertz's concepts are applicable with any toolset. Each chapter also links to additional datasets with more problems, exercises, and solutions. Ancillary resources include Instructor Notes and PowerPoint lecture slides, which will both be downloadable from Pearson.com/us.

This guide shows how to combine data science with social science to gain unprecedented insight into customer behavior, so you can change it. Joanne Rodrigues-Craig bridges the gap between predictive data science and statistical techniques that reveal why important things happen -- why customers buy more, or why they immediately leave your site -- so you can get more behaviors you want and less you don't. Drawing on extensive enterprise experience and deep knowledge of demographics and sociology, Rodrigues-Craig shows how to create better theories and metrics, so you can accelerate the process of gaining insight, altering behavior, and earning business value. You'll learn how to: Develop complex, testable theories for understanding individual and social behavior in web products Think like a social scientist and contextualize individual behavior in today's social environments Build more effective metrics and KPIs for any web product or system Conduct more informative and actionable A/B tests Explore causal effects, reflecting a deeper understanding of the differences between correlation and causation Alter user behavior in a complex web product Understand how relevant human behaviors develop, and the prerequisites for changing them Choose the right statistical techniques for common tasks such as multistate and uplift modeling Use advanced statistical techniques to model multidimensional systems Do all of this in R (with sample code available in a separate code manual) Build better theories and metrics, and drive more of the behaviors you want Model, understand, and alter customer behavior to increase revenue and retention Construct better frameworks for examining why your customers do what they do Develop core metrics for user analytics, and conduct more effective A/B tests Master key techniques that most books ignore, including statistical matching and uplift modeling Use R and this book's many R examples to implement these techniques yourselfUse data science and social science to generate real changes in customer behavior Build better theories and metrics, and drive more of the behaviors you want Model, understand, and alter customer behavior to increase revenue and retention Construct better frameworks for examining why your customers do what they do Develop core metrics for user analytics, and conduct more effective A/B tests Master key techniques that most books ignore, including statistical matching and uplift modeling Use R and this book's many R examples to implement these techniques yourself

Leading instructors Michael Freeman and Joel Ross guide readers through installing and configuring the tools needed to solve professional-level data science problems, including the widely used R language and Git version-control system. They explain how to wrangle data into a form where it can be easily used, analyzed, and visualized so others can see the patterns you've uncovered. Step by step, students will master powerful R programming techniques and troubleshooting skills for probing data in new ways, and at larger scales. Freeman and Ross teach through practical examples and exercises that can be combined into complete data science projects. Everything's focused on real-world application, so students can quickly start analyzing their own data and getting answers they can act upon.

The modules in this book will go beyond the dashboard to communicate business-relevant implications of data analyses using the analytic, visualization, and storytelling capabilities of Tableau, the most popular visualization software in use by businesses world today. Each chapter will split focus between discussing key components of design practice and data visualization and introducing a format for representing information with step-by-step guides for using Tableau. By the end of this book, readers will not only understand how data stories differ from traditional storytelling and how to purposefully craft a compelling data story, but also how to employ the horsepower of Tableau to structure data analysis projects so that they can effectively analyze, visualize, and communicate insights in a way that is meaningful for stakeholders across a variety of communication mediums.

In Expert Hadoop® Administration, leading Hadoop administrator Sam R. Alapati brings together authoritative knowledge for creating, configuring, securing, managing, and optimizing production Hadoop clusters in any environment. Drawing on his experience with large-scale Hadoop administration, Alapati integrates action-oriented advice with carefully researched explanations of both problems and solutions. He covers an unmatched range of topics and offers an unparalleled collection of realistic examples. Alapati demystifies complex Hadoop environments, helping readers understand exactly what happens behind the scenes when they administer their cluster. Students will gain unprecedented insight as they walk through building clusters from scratch and configuring high availability, performance, security, encryption, and other key attributes.

The typical data science task in industry starts with an "ask” from the business. But few data scientists have been taught what to do with that ask. This book shows them how to assess it in the context of the business's goals, reframe it to work optimally for both the data scientist and the employer, and then execute on it. Written by two of the experts who've achieved breakthrough optimizations at BuzzFeed, it's packed with real-world examples that take you from start to finish: from ask to actionable insight. Andrew Kelleher and Adam Kelleher walk you through well-formed, concrete principles for approaching common data science problems, giving you an easy-to-use checklist for effective execution. Using their principles and techniques, you'll gain deeper understanding of your data, learn how to analyze noise and confounding variables so they don't compromise your analysis, and save weeks of iterative improvement by planning your projects more effectively upfront. Once you've mastered their principles, you'll put them to work in two realistic, beginning-to-end site optimization tasks. These extended examples come complete with reusable code examples and recommended open-source solutions designed for easy adaptation to your everyday challenges. They will be especially valuable for anyone seeking their first data science job -- and everyone who's found that job and wants to succeed in it.