Big data
Projektowanie aplikacji LLM. Holistyczne podejście do dużych modeli językowych
Suhas Pai
Duże modele językowe przeniknęły do wielu dziedzin techniki uważa się je za skuteczne narzędzia do rozwiązywania szerokiej gamy problemów. Coraz więcej przedsiębiorstw korzysta z ich potencjału w celu własnego rozwoju. Jednak przekształcenie prototypów w funkcjonalne aplikacje bywa złożone i skomplikowane. To wyjątkowe opracowanie zawiera wszystkie ważne koncepcje w dziedzinie LLM! Madhav Singhal, CEO, AutoComputer W tej praktycznej książce opisano wszelkie niezbędne narzędzia, techniki i rozwiązania, których potrzebujesz do tworzenia użytecznych produktów wykorzystujących potęgę modeli językowych. Na początku zdobędziesz wiedzę o budowie modelu językowego. Następnie poznasz różne sposoby zastosowania modeli językowych, czy to poprzez bezpośrednie zapytania do modelu, czy też poprzez jego dostrajanie. Zrozumiesz ograniczenia LLM, takie jak halucynacje i problemy z rozumowaniem, a także dowiesz się, jak sobie z nimi poradzić. Znajdziesz tu również omówienie paradygmatów zastosowań, takich jak generowanie wspomagane wyszukiwaniem (RAG) czy agenty. Z tą książką: przygotujesz zbiory danych do treningu i dostrajania modeli zrozumiesz architekturę transformera zaadaptujesz wstępnie wytrenowane modele do własnych potrzeb poznasz skuteczne techniki optymalizacji i adaptacji dziedzinowej dowiesz się, jak integrować modele językowe z zewnętrznymi środowiskami i źródłami danych Gorąco polecam tę książkę! Megan Risdal, Kaggle (Google) To mistrzowski kurs budowania zaawansowanych systemów AI! Jay Alammar, autor książek
Projektowanie głosowych interfejsów użytkownika. Zasady doświadczeń konwersacyjnych
Cathy Pearl
Możliwość porozmawiania ze swoim komputerem od lat rozpalała wyobraźnię inżynierów, użytkowników i... artystów. Jak się okazało, sprawa nie jest - i nigdy nie była - oczywista: rozumienie naturalnej mowy to skomplikowany proces. Języki, którymi posługują się ludzie, są bowiem przepełnione subtelnościami i niejednoznacznością, a ich zrozumienie wymaga znajomości kontekstu. Intensywny rozwój technologii VUI doprowadził do tego, że komputer wykonujący polecenia głosowe nie jest niczym nadzwyczajnym. Wciąż jednak sporo można w tej dziedzinie poprawić. Szczególnie ważne wydaje się wzięcie pod uwagę wrażeń użytkownika: interfejs VUI, który jest uciążliwy dla odbiorcy, nie podaje potrzebnych informacji lub podaje zupełnie nieprzydatne, będzie użytkowany z niechęcią albo wcale. W tym przewodniku znajdziesz przegląd najważniejszych zasad projektowania interfejsów głosowych, a także opis narzędzi służących do tego celu. Poza najbardziej podstawowymi informacjami o mechanizmach rozpoznawania głosu omówiono złożone strategie rozumienia języka naturalnego, analizę nastroju, zbieranie danych oraz techniki przekształcania tekstu w mowę. W książce wyczerpująco opisano zagadnienia wydajności interfejsu VUI: dowiesz się, co na tę wydajność wpływa i w jaki sposób można ją podnieść. Przedstawiono również problematykę systemów sterowanych głosowo, takich jak asystenty domowe czy interfejsy projektowane dla samochodów. Z przewodnika skorzystają zarówno menedżerowie oraz projektanci biznesowi, jak i projektanci interfejsów VUI, niezależnie od tego, czy samodzielnie piszą swoje VUI, czy korzystają z istniejących platform. W książce: kluczowe koncepcje projektów interfejsów głosowych wizualne reprezentacje interfejsów głosowych technologie rozpoznawania mowy metody testowania aplikacji głosowych poprawa wydajności aplikacji głosowych rzeczywiste przykłady interfejsów głosowych
John Arundel
A revolution is happening in web operations. Configuration management tools can build servers in seconds, and automate your entire network. Tools like Puppet are essential to taking full advantage of the power of cloud computing, and building reliable, scalable, secure, high-performance systems. More and more systems administration and IT jobs require some knowledge of configuration management, and specifically Puppet.Puppet 3 Cookbook takes you beyond the basics to explore the full power of Puppet, showing you in detail how to tackle a variety of real-world problems and applications. At every step it shows you exactly what commands you need to type, and includes full code samples for every recipe.The book takes the reader from a basic knowledge of Puppet to a complete and expert understanding of Puppet's latest and most advanced features, community best practices, writing great manifests, scaling and performance, and extending Puppet by adding your own providers and resources. It starts with guidance on how to set up and expand your Puppet infrastructure, then progresses through detailed information on the language and features, external tools, reporting, monitoring, and troubleshooting, and concludes with many specific recipes for managing popular applications.The book includes real examples from production systems and techniques that are in use in some of the world's largest Puppet installations, including a distributed Puppet architecture based on the Git version control system. You'll be introduced to powerful tools that work with Puppet such as Hiera. The book also explains managing Ruby applications and MySQL databases, building web servers, load balancers, high-availability systems with Heartbeat, and many other state-of-the-art techniques
Denny Lee, Tomasz Drabas
Apache Spark is an open source framework for efficient cluster computing with a strong interface for data parallelism and fault tolerance. The PySpark Cookbook presents effective and time-saving recipes for leveraging the power of Python and putting it to use in the Spark ecosystem.You’ll start by learning the Apache Spark architecture and how to set up a Python environment for Spark. You’ll then get familiar with the modules available in PySpark and start using them effortlessly. In addition to this, you’ll discover how to abstract data with RDDs and DataFrames, and understand the streaming capabilities of PySpark. You’ll then move on to using ML and MLlib in order to solve any problems related to the machine learning capabilities of PySpark and use GraphFrames to solve graph-processing problems. Finally, you will explore how to deploy your applications to the cloud using the spark-submit command.By the end of this book, you will be able to use the Python API for Apache Spark to solve any problems associated with building data-intensive applications.
Python 3 and Data Analytics Pocket Primer. A Quick Guide to NumPy, Pandas, and Data Visualization
Mercury Learning and Information, Oswald Campesato
This book, part of the best-selling Pocket Primer series, introduces readers to the fundamental concepts of data analytics using Python 3. The course begins with a concise introduction to Python, covering essential programming constructs and data manipulation techniques. This foundation sets the stage for deeper dives into data analytics, emphasizing the importance of data cleaning, a critical step in any data analysis process.Following the Python basics, the course explores powerful libraries such as NumPy and Pandas for efficient data handling and manipulation. It then delves into statistical concepts, providing the necessary background for understanding data distributions and analytical methods. The course culminates in data visualization techniques using Matplotlib and Seaborn, demonstrating how to effectively communicate insights through graphical representations.Throughout the course, numerous code samples and practical examples are provided, reinforcing learning and offering hands-on experience. Companion files with source code and figures are available online, supporting the learning journey. This comprehensive guide equips both beginners and seasoned professionals with the skills needed to excel in data analytics.
Python 3 and Data Visualization. Mastering Graphics and Data Manipulation with Python
Mercury Learning and Information, Oswald Campesato
Python 3 and Data Visualization provides an in-depth exploration of Python 3 programming and data visualization techniques. The course begins with an introduction to Python, covering essential topics from basic data types and loops to advanced constructs such as dictionaries and matrices. This foundation prepares readers for the next section, which focuses on NumPy and its powerful array operations, seamlessly leading into data visualization using prominent libraries like Matplotlib.Chapter 6 delves into Seaborn's rich visualization tools, providing insights into datasets like Iris and Titanic. The appendix covers additional visualization tools and techniques, including SVG graphics and D3 for dynamic visualizations. The companion files include numerous Python code samples and figures, enhancing the learning experience.From foundational Python concepts to advanced data visualization techniques, this course serves as a comprehensive resource for both beginners and seasoned professionals, equipping them with the necessary skills to effectively visualize data.
Mercury Learning and Information, Oswald Campesato
This book bridges the gap between theoretical knowledge and practical application in Python programming, machine learning, and using ChatGPT-4 in data science. It starts with an introduction to Pandas for data manipulation and analysis. The book then explores various machine learning classifiers, from kNN to SVMs. Later chapters cover GPT-4's capabilities, enhancing linear regression analysis, and using ChatGPT in data visualization, including AI apps, GANs, and DALL-E.The journey begins with mastering Pandas and machine learning fundamentals. It progresses to applying GPT-4 in linear regression and machine learning classifiers. The final chapters focus on using ChatGPT for data visualization, making complex results accessible and understandable.Understanding these concepts is crucial for modern data scientists. This book transitions readers from basic Python programming to advanced applications of ChatGPT-4 in data science. Companion files with source code, datasets, and figures enhance learning, making this an essential resource for mastering Python, machine learning, and AI-driven data visualization.
Mercury Learning and Information, Oswald Campesato
This book teaches Python 3 programming and data visualization, exploring cutting-edge techniques with ChatGPT/GPT-4 for generating compelling visuals. It starts with Python essentials, covering basic data types, loops, functions, and advanced constructs like dictionaries and matrices. The journey progresses to NumPy's array operations and data visualization using libraries such as Matplotlib and Seaborn. The book also covers tools like SVG graphics and D3 for dynamic visualizations.The course begins with foundational Python concepts, moves into NumPy and data visualization with Pandas, Matplotlib, and Seaborn. Advanced chapters explore ChatGPT and GPT-4, demonstrating their use in creating data visualizations from datasets like the Titanic. Each chapter builds on the previous one, ensuring a comprehensive understanding of Python and visualization techniques.These concepts are crucial for Python practitioners, data scientists, and anyone in data analytics. This book transitions readers from basic Python programming to advanced data visualization, blending theoretical knowledge with practical skills. Companion files with code, datasets, and figures enhance learning, making this an essential resource for mastering Python and data visualization.
Mercury Learning and Information, Oswald Campesato
This book teaches Python 3 programming and data visualization, exploring cutting-edge techniques with ChatGPT/GPT-4 for generating compelling visuals. It starts with Python essentials, covering basic data types, loops, functions, and advanced constructs like dictionaries and matrices. The journey progresses to NumPy's array operations and data visualization using libraries such as Matplotlib and Seaborn. The book also covers tools like SVG graphics and D3 for dynamic visualizations.The course begins with foundational Python concepts, moves into NumPy and data visualization with Pandas, Matplotlib, and Seaborn. Advanced chapters explore ChatGPT and GPT-4, demonstrating their use in creating data visualizations from datasets like the Titanic. Each chapter builds on the previous one, ensuring a comprehensive understanding of Python and visualization techniques.These concepts are crucial for Python practitioners, data scientists, and anyone in data analytics. This book transitions readers from basic Python programming to advanced data visualization, blending theoretical knowledge with practical skills. Companion files with code, datasets, and figures enhance learning, making this an essential resource for mastering Python and data visualization.
Python 3 for Machine Learning. Harness the Power of Python for Advanced Machine Learning Projects
Mercury Learning and Information, Oswald Campesato
This book introduces basic Python 3 programming concepts related to machine learning. The first four chapters provide a fast-paced introduction to Python 3, NumPy, and Pandas. The fifth chapter covers fundamental machine learning concepts. The sixth chapter dives into machine learning classifiers, such as logistic regression, k-NN, decision trees, random forests, and SVMs. The final chapter includes material on natural language processing (NLP) and reinforcement learning (RL). Keras-based code samples supplement the theoretical discussion.The course begins with Python basics, including conditional logic, loops, functions, and collections. It then explores data manipulation with NumPy and Pandas. The journey continues with an introduction to machine learning, focusing on essential concepts and classifiers. Advanced topics like NLP and RL are covered, ensuring a comprehensive understanding of machine learning.These concepts are crucial for developing machine learning applications. This book transitions readers from basic Python programming to advanced machine learning techniques, blending theory with practical skills. Appendices for regular expressions, Keras, and TensorFlow 2, along with companion files, enhance learning, making this an essential resource for mastering Python and machine learning.
Giuseppe Bonaccorso, Armando Fandango, Rajalingappaa Shanmugamani
This Learning Path is your complete guide to quickly getting to grips with popular machine learning algorithms. You'll be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this Learning Path will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries. You'll bring the use of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Next, you'll learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF clusters, deploy production models with TensorFlow Serving. You'll implement different techniques related to object classification, object detection, image segmentation, and more. By the end of this Learning Path, you'll have obtained in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problemsThis Learning Path includes content from the following Packt products:• Mastering Machine Learning Algorithms by Giuseppe Bonaccorso• Mastering TensorFlow 1.x by Armando Fandango• Deep Learning for Computer Vision by Rajalingappaa Shanmugamani
Dr. Joshua Eckroth
Artificial Intelligence (AI) is the newest technology that’s being employed among varied businesses, industries, and sectors. Python Artificial Intelligence Projects for Beginners demonstrates AI projects in Python, covering modern techniques that make up the world of Artificial Intelligence.This book begins with helping you to build your first prediction model using the popular Python library, scikit-learn. You will understand how to build a classifier using an effective machine learning technique, random forest, and decision trees. With exciting projects on predicting bird species, analyzing student performance data, song genre identification, and spam detection, you will learn the fundamentals and various algorithms and techniques that foster the development of these smart applications. In the concluding chapters, you will also understand deep learning and neural network mechanisms through these projects with the help of the Keras library.By the end of this book, you will be confident in building your own AI projects with Python and be ready to take on more advanced projects as you progress
Robert Dempsey, Stefan Urbanek, Saurabh Chhajed
The amount of data produced by businesses and devices is going nowhere but up. In this scenario, the major advantage of Python is that it's a general-purpose language and gives you a lot of flexibility in data structures. Python is an excellent tool for more specialized analysis tasks, and is powered with related libraries to process data streams, to visualize datasets, and to carry out scientific calculations. Using Python for business intelligence (BI) can help you solve tricky problems in one go.Rather than spending day after day scouring Internet forums for “how-to” information, here you’ll find more than 60 recipes that take you through the entire process of creating actionable intelligence from your raw data, no matter what shape or form it’s in. Within the first 30 minutes of opening this book, you’ll learn how to use the latest in Python and NoSQL databases to glean insights from data just waiting to be exploited.We’ll begin with a quick-fire introduction to Python for BI and show you what problems Python solves. From there, we move on to working with a predefined data set to extract data as per business requirements, using the Pandas library and MongoDB as our storage engine.Next, we will analyze data and perform transformations for BI with Python. Through this, you will gather insightful data that will help you make informed decisions for your business. The final part of the book will show you the most important task of BI—visualizing data by building stunning dashboards using Matplotlib, PyTables, and iPython Notebook.
Python Data Analysis Cookbook. Clean, scrape, analyze, and visualize data with the power of Python!
Ivan Idris
Data analysis is a rapidly evolving field and Python is a multi-paradigm programming language suitable for object-oriented application development and functional design patterns. As Python offers a range of tools and libraries for all purposes, it has slowly evolved as the primary language for data science, including topics on: data analysis, visualization, and machine learning.Python Data Analysis Cookbook focuses on reproducibility and creating production-ready systems. You will start with recipes that set the foundation for data analysis with libraries such as matplotlib, NumPy, and pandas. You will learn to create visualizations by choosing color maps and palettes then dive into statistical data analysis using distribution algorithms and correlations. You’ll then help you find your way around different data and numerical problems, get to grips with Spark and HDFS, and then set up migration scripts for web mining.In this book, you will dive deeper into recipes on spectral analysis, smoothing, and bootstrapping methods. Moving on, you will learn to rank stocks and check market efficiency, then work with metrics and clusters. You will achieve parallelism to improve system performance by using multiple threads and speeding up your code.By the end of the book, you will be capable of handling various data analysis techniques in Python and devising solutions for problem scenarios.
Python Data Analysis. Data manipulation and complex data analysis with Python - Second Edition
Armando Fandango, Ivan Idris
Data analysis techniques generate useful insights from small and large volumes of data. Python, with its strong set of libraries, has become a popular platform to conduct various data analysis and predictive modeling tasks. With this book, you will learn how to process and manipulate data with Python for complex analysis and modeling. We learn data manipulations such as aggregating, concatenating, appending, cleaning, and handling missing values, with NumPy and Pandas. The book covers how to store and retrieve data from various data sources such as SQL and NoSQL, CSV fies, and HDF5. We learn how to visualize data using visualization libraries, along with advanced topics such as signal processing, time series, textual data analysis, machine learning, and social media analysis.The book covers a plethora of Python modules, such as matplotlib, statsmodels, scikit-learn, and NLTK. It also covers using Python with external environments such as R, Fortran, C/C++, and Boost libraries.
Avinash Navlani, Armando Fandango, Ivan Idris
Data analysis enables you to generate value from small and big data by discovering new patterns and trends, and Python is one of the most popular tools for analyzing a wide variety of data. With this book, you’ll get up and running using Python for data analysis by exploring the different phases and methodologies used in data analysis and learning how to use modern libraries from the Python ecosystem to create efficient data pipelines.Starting with the essential statistical and data analysis fundamentals using Python, you’ll perform complex data analysis and modeling, data manipulation, data cleaning, and data visualization using easy-to-follow examples. You’ll then understand how to conduct time series analysis and signal processing using ARMA models. As you advance, you’ll get to grips with smart processing and data analytics using machine learning algorithms such as regression, classification, Principal Component Analysis (PCA), and clustering. In the concluding chapters, you’ll work on real-world examples to analyze textual and image data using natural language processing (NLP) and image analytics techniques, respectively. Finally, the book will demonstrate parallel computing using Dask.By the end of this data analysis book, you’ll be equipped with the skills you need to prepare data for analysis and create meaningful data visualizations for forecasting values from data.
Martin Czygan, Phuong Vo.T.H, Ashish Kumar, Kirthi...
You will start the course with an introduction to the principles of data analysis and supported libraries, along with NumPy basics for statistics and data processing. Next, you will overview the Pandas package and use its powerful features to solve data-processing problems. Moving on, you will get a brief overview of the Matplotlib API .Next, you will learn to manipulate time and data structures, and load and store data in a file or database using Python packages. You will learn how to apply powerful packages in Python to process raw data into pure and helpful data using examples. You will also get a brief overview of machine learning algorithms, that is, applying data analysis results to make decisions or building helpful products such as recommendations and predictions using Scikit-learn. After this, you will move on to a data analytics specialization—predictive analytics. Social media and IOT have resulted in an avalanche of data. You will get started with predictive analytics using Python. You will see how to create predictive models from data. You will get balanced information on statistical and mathematical concepts, and implement them in Python using libraries such as Pandas, scikit-learn, and NumPy. You’ll learn more about the best predictive modeling algorithms such as Linear Regression, Decision Tree, and Logistic Regression. Finally, you will master best practices in predictive modeling.After this, you will get all the practical guidance you need to help you on the journey to effective data visualization. Starting with a chapter on data frameworks, which explains the transformation of data into information and eventually knowledge, this path subsequently cover the complete visualization process using the most popular Python libraries with working examplesThis Learning Path combines some of the best that Packt has to offer in one complete, curated package. It includes content from the following Packt products:? Getting Started with Python Data Analysis, Phuong Vo.T.H &Martin Czygan•Learning Predictive Analytics with Python, Ashish Kumar•Mastering Python Data Visualization, Kirthi Raman
Maria Zervou
Professionals face several challenges in effectively leveraging data in today's data-driven world. One of the main challenges is the low quality of data products, often caused by inaccurate, incomplete, or inconsistent data. Another significant challenge is the lack of skills among data professionals to analyze unstructured data, leading to valuable insights being missed that are difficult or impossible to obtain from structured data alone.To help you tackle these challenges, this book will take you on a journey through the upstream data pipeline, which includes the ingestion of data from various sources, the validation and profiling of data for high-quality end tables, and writing data to different sinks. You’ll focus on structured data by performing essential tasks, such as cleaning and encoding datasets and handling missing values and outliers, before learning how to manipulate unstructured data with simple techniques. You’ll also be introduced to a variety of natural language processing techniques, from tokenization to vector models, as well as techniques to structure images, videos, and audio.By the end of this book, you’ll be proficient in data cleaning and preparation techniques for both structured and unstructured data.
Michael Walker
Getting clean data to reveal insights is essential, as directly jumping into data analysis without proper data cleaning may lead to incorrect results. This book shows you tools and techniques that you can apply to clean and handle data with Python. You'll begin by getting familiar with the shape of data by using practices that can be deployed routinely with most data sources. Then, the book teaches you how to manipulate data to get it into a useful form. You'll also learn how to filter and summarize data to gain insights and better understand what makes sense and what does not, along with discovering how to operate on data to address the issues you've identified. Moving on, you'll perform key tasks, such as handling missing values, validating errors, removing duplicate data, monitoring high volumes of data, and handling outliers and invalid dates. Next, you'll cover recipes on using supervised learning and Naive Bayes analysis to identify unexpected values and classification errors, and generate visualizations for exploratory data analysis (EDA) to visualize unexpected values. Finally, you'll build functions and classes that you can reuse without modification when you have new data. By the end of this Python book, you'll be equipped with all the key skills that you need to clean data and diagnose problems within it.
Michael Walker
Jumping into data analysis without proper data cleaning will certainly lead to incorrect results. The Python Data Cleaning Cookbook - Second Edition will show you tools and techniques for cleaning and handling data with Python for better outcomes.Fully updated to the latest version of Python and all relevant tools, this book will teach you how to manipulate and clean data to get it into a useful form. he current edition focuses on advanced techniques like machine learning and AI-specific approaches and tools for data cleaning along with the conventional ones. The book also delves into tips and techniques to process and clean data for ML, AI, and NLP models. You will learn how to filter and summarize data to gain insights and better understand what makes sense and what does not, along with discovering how to operate on data to address the issues you've identified. Next, you’ll cover recipes for using supervised learning and Naive Bayes analysis to identify unexpected values and classification errors and generate visualizations for exploratory data analysis (EDA) to identify unexpected values. Finally, you’ll build functions and classes that you can reuse without modification when you have new data.By the end of this Data Cleaning book, you'll know how to clean data and diagnose problems within it.
Alberto Boschetti, Luca Massaron
Fully expanded and upgraded, the latest edition of Python Data Science Essentials will help you succeed in data science operations using the most common Python libraries. This book offers up-to-date insight into the core of Python, including the latest versions of the Jupyter Notebook, NumPy, pandas, and scikit-learn.The book covers detailed examples and large hybrid datasets to help you grasp essential statistical techniques for data collection, data munging and analysis, visualization, and reporting activities. You will also gain an understanding of advanced data science topics such as machine learning algorithms, distributed computing, tuning predictive models, and natural language processing. Furthermore, You’ll also be introduced to deep learning and gradient boosting solutions such as XGBoost, LightGBM, and CatBoost.By the end of the book, you will have gained a complete overview of the principal machine learning algorithms, graph analysis techniques, and all the visualization and deployment instruments that make it easier to present your results to an audience of both data science experts and business users
Python Data Science Essentials. Learn the fundamentals of Data Science with Python - Second Edition
Alberto Boschetti, Luca Massaron
Fully expanded and upgraded, the second edition of Python Data Science Essentials takes you through all you need to know to suceed in data science using Python. Get modern insight into the core of Python data, including the latest versions of Jupyter notebooks, NumPy, pandas and scikit-learn. Look beyond the fundamentals with beautiful data visualizations with Seaborn and ggplot, web development with Bottle, and even the new frontiers of deep learning with Theano and TensorFlow. Dive into building your essential Python 3.5 data science toolbox, using a single-source approach that will allow to to work with Python 2.7 as well. Get to grips fast with data munging and preprocessing, and all the techniques you need to load, analyse, and process your data. Finally, get a complete overview of principal machine learning algorithms, graph analysis techniques, and all the visualization and deployment instruments that make it easier to present your results to an audience of both data science experts and business users.