Analiza danych
Willem Meints
Cognitive Toolkit is a very popular and recently open sourced deep learning toolkit by Microsoft. Cognitive Toolkit is used to train fast and effective deep learning models. This book will be a quick introduction to using Cognitive Toolkit and will teach you how to train and validate different types of neural networks, such as convolutional and recurrent neural networks.This book will help you understand the basics of deep learning. You will learn how to use Microsoft Cognitive Toolkit to build deep learning models and discover what makes this framework unique so that you know when to use it. This book will be a quick, no-nonsense introduction to the library and will teach you how to train different types of neural networks, such as convolutional neural networks, recurrent neural networks, autoencoders, and more, using Cognitive Toolkit. Then we will look at two scenarios in which deep learning can be used to enhance human capabilities. The book will also demonstrate how to evaluate your models' performance to ensure it trains and runs smoothly and gives you the most accurate results. Finally, you will get a short overview of how Cognitive Toolkit fits in to a DevOps environment
Deep Learning with PyTorch. A practical approach to building neural network models using PyTorch
Vishnu Subramanian
Deep learning powers the most intelligent systems in the world, such as Google Voice, Siri, and Alexa. Advancements in powerful hardware, such as GPUs, software frameworks such as PyTorch, Keras, TensorFlow, and CNTK along with the availability of big data have made it easier to implement solutions to problems in the areas of text, vision, and advanced analytics. This book will get you up and running with one of the most cutting-edge deep learning libraries—PyTorch. PyTorch is grabbing the attention of deep learning researchers and data science professionals due to its accessibility, efficiency and being more native to Python way of development. You'll start off by installing PyTorch, then quickly move on to learn various fundamental blocks that power modern deep learning. You will also learn how to use CNN, RNN, LSTM and other networks to solve real-world problems. This book explains the concepts of various state-of-the-art deep learning architectures, such as ResNet, DenseNet, Inception, and Seq2Seq, without diving deep into the math behind them. You will also learn about GPU computing during the course of the book. You will see how to train a model with PyTorch and dive into complex neural networks such as generative networks for producing text and images. By the end of the book, you'll be able to implement deep learning applications in PyTorch with ease.
Kunal Sawarkar, Dheeraj Arremsetty
Building and implementing deep learning (DL) is becoming a key skill for those who want to be at the forefront of progress.But with so much information and complex study materials out there, getting started with DL can feel quite overwhelming.Written by an AI thought leader, Deep Learning with PyTorch Lightning helps researchers build their first DL models quickly and easily without getting stuck on the complexities. With its help, you’ll be able to maximize productivity for DL projects while ensuring full flexibility – from model formulation to implementation.Throughout this book, you’ll learn how to configure PyTorch Lightning on a cloud platform, understand the architectural components, and explore how they are configured to build various industry solutions. You’ll build a neural network architecture, deploy an application from scratch, and see how you can expand it based on your specific needs, beyond what the framework can provide.In the later chapters, you’ll also learn how to implement capabilities to build and train various models like Convolutional Neural Nets (CNN), Natural Language Processing (NLP), Time Series, Self-Supervised Learning, Semi-Supervised Learning, Generative Adversarial Network (GAN) using PyTorch Lightning.By the end of this book, you’ll be able to build and deploy DL models with confidence.
David Julian
PyTorch is extremely powerful and yet easy to learn. It provides advanced features, such as supporting multiprocessor, distributed, and parallel computation. This book is an excellent entry point for those wanting to explore deep learning with PyTorch to harness its power. This book will introduce you to the PyTorch deep learning library and teach you how to train deep learning models without any hassle. We will set up the deep learning environment using PyTorch, and then train and deploy different types of deep learning models, such as CNN, RNN, and autoencoders. You will learn how to optimize models by tuning hyperparameters and how to use PyTorch in multiprocessor and distributed environments. We will discuss long short-term memory network (LSTMs) and build a language model to predict text.By the end of this book, you will be familiar with PyTorch's capabilities and be able to utilize the library to train your neural networks with relative ease.
Swarna Gupta, Rehan Ali Ansari, Dipayan Sarkar
Deep learning (DL) has evolved in recent years with developments such as generative adversarial networks (GANs), variational autoencoders (VAEs), and deep reinforcement learning. This book will get you up and running with R 3.5.x to help you implement DL techniques.The book starts with the various DL techniques that you can implement in your apps. A unique set of recipes will help you solve binomial and multinomial classification problems, and perform regression and hyperparameter optimization. To help you gain hands-on experience of concepts, the book features recipes for implementing convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Long short-term memory (LSTMs) networks, as well as sequence-to-sequence models and reinforcement learning. You’ll then learn about high-performance computation using GPUs, along with learning about parallel computation capabilities in R. Later, you’ll explore libraries, such as MXNet, that are designed for GPU computing and state-of-the-art DL. Finally, you’ll discover how to solve different problems in NLP, object detection, and action identification, before understanding how to use pre-trained models in DL apps.By the end of this book, you’ll have comprehensive knowledge of DL and DL packages, and be able to develop effective solutions for different DL problems.
Antonio Gulli, Dr. Amita Kapoor, Sujit Pal
Deep Learning with TensorFlow 2 and Keras, Second Edition teaches neural networks and deep learning techniques alongside TensorFlow (TF) and Keras. You’ll learn how to write deep learning applications in the most powerful, popular, and scalable machine learning stack available.TensorFlow is the machine learning library of choice for professional applications, while Keras offers a simple and powerful Python API for accessing TensorFlow. TensorFlow 2 provides full Keras integration, making advanced machine learning easier and more convenient than ever before.This book also introduces neural networks with TensorFlow, runs through the main applications (regression, ConvNets (CNNs), GANs, RNNs, NLP), covers two working example apps, and then dives into TF in production, TF mobile, and using TensorFlow with AutoML.
Deep Learning with TensorFlow. Explore neural networks with Python
Giancarlo Zaccone, Fabrizio Milo, Md. Rezaul Karim
Deep learning is the step that comes after machine learning, and has more advancedimplementations. Machine learning is not just for academics anymore, but is becoming a mainstream practice through wide adoption, and deep learning has taken the front seat. As a data scientist, if you want to explore data abstraction layers, this book will be your guide. This book shows how this can be exploited in the real world with complex raw data using TensorFlow 1.x.Throughout the book, you’ll learn how to implement deep learning algorithms for machine learning systems and integrate them into your product offerings, includingsearch, image recognition, and language processing. Additionally, you’ll learn howto analyze and improve the performance of deep learning models. This can be done bycomparing algorithms against benchmarks, along with machine intelligence, to learnfrom the information and determine ideal behaviors within a specific context.After finishing the book, you will be familiar with machine learning techniques, in particular the use of TensorFlow for deep learning, and will be ready to apply your knowledge to research or commercial projects.
Developer, Advocate!. Conversations on turning a passion for talking about tech into a career
Geertjan Wielenga
What exactly is a developer advocate, and how do they connect developers and companies around the world? Why is the area of developer relations set to explode? Can anybody with a passion for tech become a developer advocate? What are the keys to success on a global scale? How does a developer advocate maintain authenticity when balancing the needs of their company and their tech community? What are the hot topics in areas including Java, JavaScript, tech for good, artificial intelligence, blockchain, the cloud, and open source?These are just a few of the questions addressed by developer advocate and author Geertjan Wielenga in Developer, Advocate!. 32 of the industry's most prominent developer advocates, from companies including Oracle, Microsoft, Google, and Amazon, open up about what it's like to turn a lifelong passion for knowledge sharing about tech into a rewarding career. These advocates run the gamut from working at large software vendors to small start-ups, along with independent developer advocates who work within organizations or for themselves.In Developer, Advocate!, readers will see how developer advocates are actively changing the world, not only for developers, but for individuals and companies navigating the fast-changing tech landscape. More importantly, Developer, Advocate! serves as a rallying cry to inspire and motivate tech enthusiasts and burgeoning developer advocates to get started and take their first steps within their tech community.
Developing Kaggle Notebooks. Pave your way to becoming a Kaggle Notebooks Grandmaster
Gabriel Preda, D. Sculley, Anthony Goldbloom
Developing Kaggle Notebooks introduces you to data analysis, with a focus on using Kaggle Notebooks to simultaneously achieve mastery in this fi eld and rise to the top of the Kaggle Notebooks tier. The book is structured as a sevenstep data analysis journey, exploring the features available in Kaggle Notebooks alongside various data analysis techniques.For each topic, we provide one or more notebooks, developing reusable analysis components through Kaggle's Utility Scripts feature, introduced progressively, initially as part of a notebook, and later extracted for use across future notebooks to enhance code reusability on Kaggle. It aims to make the notebooks' code more structured, easy to maintain, and readable.Although the focus of this book is on data analytics, some examples will guide you in preparing a complete machine learning pipeline using Kaggle Notebooks. Starting from initial data ingestion and data quality assessment, you'll move on to preliminary data analysis, advanced data exploration, feature qualifi cation to build a model baseline, and feature engineering. You'll also delve into hyperparameter tuning to iteratively refi ne your model and prepare for submission in Kaggle competitions. Additionally, the book touches on developing notebooks that leverage the power of generative AI using Kaggle Models.
Bryon Kataoka, James Brennan, Ashish Aggarwal
IBM API Connect enables organizations to drive digital innovation using its scalable and robust API management capabilities across multi-cloud and hybrid environments. With API Connect's security, flexibility, and high performance, you'll be able to meet the needs of your enterprise and clients by extending your API footprint. This book provides a complete roadmap to create, manage, govern, and publish your APIs.You'll start by learning about API Connect components, such as API managers, developer portals, gateways, and analytics subsystems, as well as the management capabilities provided by CLI commands. You’ll then develop APIs using OpenAPI and discover how you can enhance them with logic policies. The book shows you how to modernize SOAP and FHIR REST services as secure APIs with authentication, OAuth2/OpenID, and JWT, and demonstrates how API Connect provides safeguards for GraphQL APIs as well as published APIs that are easy to discover and well documented. As you advance, the book guides you in generating unit tests that supplement DevOps pipelines using Git and Jenkins for improved agility, and concludes with best practices for implementing API governance and customizing API Connect components.By the end of this book, you'll have learned how to transform your business by speeding up the time-to-market of your products and increase the ROI for your enterprise.
Srikumar Nair
Microsoft Dataverse for Teams is a built-in, low-code data platform for Teams and enables everyone to easily build and deploy apps, flows, and intelligent chatbots using Power Apps, Power Automate, and Power Virtual Agents (PVA) embedded in Microsoft Teams.Without learning any coding language, you will be able to build apps with step-by-step explanations for setting up Teams, creating tables to store data, and leverage the data for your digital solutions. With the techniques covered in the book, you’ll be able to develop your first app with Dataverse for Teams within an hour! You’ll then learn how to automate repetitive tasks or build alerts using Power Automate and Power Virtual Agents. As you get to grips with building these digital solutions, you’ll also be able to understand when to consider upgrading from Dataverse for Teams to Dataverse, along with its advanced features. Finally, you’ll explore features for administration and governance and understand the licensing requirements of Microsoft Dataverse for Teams and PowerApps.Having acquired the skills to build and deploy an enterprise-grade digital solution, by the end of the book, you will have become a qualified citizen developer and be ready to lead a digital revolution in your organization.
Distributed Data Systems with Azure Databricks. Create, deploy, and manage enterprise data pipelines
Alan Bernardo Palacio
Microsoft Azure Databricks helps you to harness the power of distributed computing and apply it to create robust data pipelines, along with training and deploying machine learning and deep learning models. Databricks' advanced features enable developers to process, transform, and explore data. Distributed Data Systems with Azure Databricks will help you to put your knowledge of Databricks to work to create big data pipelines. The book provides a hands-on approach to implementing Azure Databricks and its associated methodologies that will make you productive in no time. Complete with detailed explanations of essential concepts, practical examples, and self-assessment questions, you’ll begin with a quick introduction to Databricks core functionalities, before performing distributed model training and inference using TensorFlow and Spark MLlib. As you advance, you’ll explore MLflow Model Serving on Azure Databricks and implement distributed training pipelines using HorovodRunner in Databricks. Finally, you’ll discover how to transform, use, and obtain insights from massive amounts of data to train predictive models and create entire fully working data pipelines. By the end of this MS Azure book, you’ll have gained a solid understanding of how to work with Databricks to create and manage an entire big data pipeline.
Don't Fear the Spreadsheet. A Beginner's Guide to Overcoming Excel's Frustrations
MrExcel's Holy Macro! Books, Tyler Nash, Bill...
This book is written in an easy-to-follow question-and-answer format, specifically designed for complete Excel beginners. Focusing on the extreme basics of using spreadsheets, it avoids overwhelming readers with advanced topics and instead builds a foundational understanding. Readers will quickly gain a passable knowledge of the program, addressing common fears and frustrations through clear explanations and practical examples.The guide answers hundreds of everyday questions, such as Can I delete data without changing formatting? and How do I use text-wrapping? as well as slightly more advanced queries like What is a Macro, and how do I create one? It empowers users by breaking down intimidating concepts into manageable steps, making Excel approachable and useful for even the most inexperienced users. The focus is on helping readers become comfortable with essential tasks, from merging cells and formatting text to understanding formulas and navigating the interface.Aimed at the 40 percent of Excel users who have never entered a formula, this book demystifies the program's tools and functions, transforming confusion into confidence. By the end, readers will feel equipped to use Excel effectively for personal and professional tasks, overcoming barriers to productivity.
Andrew Jones, Kevin Hu
Despite the passage of time and the evolution of technology and architecture, the challenges we face in building data platforms persist. Our data often remains unreliable, lacks trust, and fails to deliver the promised value.With Driving Data Quality with Data Contracts, you’ll discover the potential of data contracts to transform how you build your data platforms, finally overcoming these enduring problems. You’ll learn how establishing contracts as the interface allows you to explicitly assign responsibility and accountability of the data to those who know it best—the data generators—and give them the autonomy to generate and manage data as required. The book will show you how data contracts ensure that consumers get quality data with clearly defined expectations, enabling them to build on that data with confidence to deliver valuable analytics, performant ML models, and trusted data-driven products.By the end of this book, you’ll have gained a comprehensive understanding of how data contracts can revolutionize your organization’s data culture and provide a competitive advantage by unlocking the real value within your data.
Dziennikarstwo danych i data storytelling
Łukasz Żyła
Bez danych jesteś jedynie kolejną osobą z opinią... Dziennikarstwo danych przeżywa dziś prawdziwy rozkwit. Dzieje się tak dlatego, że nasze życie w dużej mierze przeniosło się do internetu, a internet to... dane. Megabajty, gigabajty, terabajty danych. Misją współczesnego dziennikarza jest przedstawiać je społeczeństwu rzetelnie, a równocześnie pięknie, czyli w sposób zrozumiały, łatwy do przyswojenia. Nim się jednak owe dane pięknie zestawi, trzeba je znaleźć. Gdzie szukać? Jak je zdobyć? W jaki sposób opowiedzieć dane? Na takie pytania autor odpowiada w tej książce. Nie przeczytasz w niej o "ładnych wykresach", bo wbrew pozorom to nie one są esencją dziennikarstwa danych i data storytellingu. Dowiesz się natomiast, gdzie biją źródła potrzebnych Ci informacji, jak je przetwarzać i analizować. Znajdziesz tu także wskazówki, w jaki sposób tworzyć dobre wizualizacje za pomocą prostych aplikacji dostępnych za darmo w internecie i jak kreować angażujące odbiorców data stories. Na koniec wejdziesz na wyższy poziom - nauczysz się prezentować dane z wykorzystaniem kodu programistycznego. Kto? Co? Jak? Gdzie? Kiedy? ― odpowiedzi na te podstawowe pytania musi znaleźć każdy dziennikarz, który chce rzetelnie wykonać swoją pracę. Jednocześnie przy zalewie informacji, danych ze źródeł, których weryfikacja jest równie czasochłonna, każdy wykonujący ten piękny zawód coraz bardziej przypomina mitycznego Syzyfa. Przebicie się przez gigabajty informacji, przetworzenie ich i stworzenie materiału, który tłumaczy odbiorcy rzeczywistość, jest dziś działaniem obarczonym ogromnym wysiłkiem i jeszcze większym ryzykiem. Kaskadowy spadek zaufania do instytucji publicznych i prywatnych, z jakim mamy do czynienia od lat, oddziałuje także na media, z jednej strony wystawiane na szereg nacisków biznesowych, politycznych i społecznych, z drugiej ― borykające się z ciągłymi problemami finansowymi. Co warto wiedzieć, dobre dziennikarstwo, jakościowe dziennikarstwo to coś, co wymaga swobodnego poruszania się autorów w przestrzeni internetu i danych, a także poznania podstaw funkcjonowania w tej przestrzeni. Dlatego, jeżeli chcemy mieć przynajmniej cień nadziei na dobrze wykonaną pracę, warto sięgnąć po książkę Łukasza Żyły. W zawodzie zawsze mi powtarzano, że tej profesji człowiek uczy się tylko w praktyce i na pewno nie na studiach. Nadal tak jest, choć czasy, w których media dosłownie pączkują na każdym kroku i angażują coraz młodszych adeptów dziennikarstwa, wymagają, by sięgnąć po informacyjną pigułę, swoisty wykrywacz min, dzięki czemu te pierwsze kroki wspomniany początkujący dziennikarz będzie mógł stawiać względnie bezpiecznie. Dziennikarstwo danych i data storytelling to także pozycja dla osób doświadczonych w tym zawodzie. Powód jest oczywisty, technologia zmieniła dziennikarstwo i w pędzie żywiołu, którym ono jest, łatwo popaść w bezpieczną i przez to złudną rutynę, a wtedy jesteśmy o krok od poważnego błędu. Dzięki książce Łukasza Żyły łatwiejsze do ominięcia będą cyfrowe rafy, którymi sieć jest usłana. Bartosz Kurek, były dziennikarz Polsatu, obecnie menedżer ds. public affairs w Philip Morris Co wy tam tak naprawdę robicie? ― to częste pytanie, kiedy mówię, że pracuję w dziale danych „Wyborczej”. Niektórzy ze znawstwem odpowiadają: „Aaa, czyli robicie analizy wyników sprzedaży gazety?”. Inni zmieniają temat, spodziewając się, że zarzucę ich nudnymi opowieściami o uzupełnianiu tabelek liczbami. Co ciekawe, pytanie o to, jak dokładnie wygląda nasza praca, zadają również dziennikarze. Teraz, zamiast wchodzić w szczegóły, będę mógł zacząć odpowiedź od słów: „Jest taka książka, warto przeczytać…”, bo Łukasz w bardzo przystępny sposób tłumaczy, czym to się je. I myślę, że niezależnie od tego, jaką działką dziennikarstwa się zajmujecie, znajdziecie w niej coś dla siebie. Części dotyczące współpracy z urzędnikami, dostępu do informacji czy opowiadania historii powinien przyswoić każdy, kto będzie pracował w zawodzie. Po te o opracowywaniu danych sięgną ambitniejsi, a może po prostu bardziej przewidujący, bo pisać potrafi wielu, ale zdolność pisania połączona z umiejętnością analizowania, programowania lub wizualizowania robi z dziennikarza człowieka do zadań specjalnych. Kiedy czytałem tę książkę, wiele razy żałowałem, że czegoś takiego nie było, kiedy ja zaczynałem przygodę z danymi. Dzięki niej widzę, ile jeszcze powinienem się w tej dziedzinie nauczyć. Dominik Uhlig, szef BIQdata.pl ― działu danych „Gazety Wyborczej”
Effective Amazon Machine Learning. Expert web services for machine learning on cloud
Alexis Perrier
Predictive analytics is a complex domain requiring coding skills, an understanding of the mathematical concepts underpinning machine learning algorithms, and the ability to create compelling data visualizations. Following AWS simplifying Machine learning, this book will help you bring predictive analytics projects to fruition in three easy steps: data preparation, model tuning, and model selection.This book will introduce you to the Amazon Machine Learning platform and will implement core data science concepts such as classification, regression, regularization, overfitting, model selection, and evaluation. Furthermore, you will learn to leverage the Amazon Web Service (AWS) ecosystem for extended access to data sources, implement realtime predictions, and run Amazon Machine Learning projects via the command line and the Python SDK. Towards the end of the book, you will also learn how to apply these services to other problems, such as text mining, and to more complex datasets.