Navlani / Wijaya Python Data Analysis

Master Python Analytics with Machine Learning, Deep Learning, GenAI, LLMs, and Data Engineering
1. Auflage 2026
ISBN: 978-1-80602-286-1
Verlag: Packt Publishing
Format: EPUB
Kopierschutz: 0 - No protection

E-Book, Englisch, 766 Seiten

Modern data analysis goes beyond cleaning and visualizing data. Today's practitioners need to build scalable data pipelines, apply machine learning, work with text and image data, and understand emerging AI techniques such as Generative AI and Large Language Models (LLMs). This guide shows you how to tackle these challenges using Python's modern data ecosystem.
Unlike books focused on a single library or technique, this book provides an end-to-end approach to Python data analysis. You'll learn how to move from data preparation and exploratory analysis to machine learning, NLP, image analytics, scalable processing, and AI-powered workflows.
Starting with statistical foundations, you'll learn how to clean, transform, wrangle, and visualize data. You'll then explore time series analysis, signal processing, forecasting, and predictive analytics before applying machine learning techniques such as regression, classification, clustering, PCA, probabilistic methods, and Bayesian approaches.
The book also covers graph analytics, sentiment analysis, NLP, image analytics, Generative AI, and LLMs. Finally, you'll learn to scale analytics workflows using Dask, Modin, Ray, and PySpark.
By the end of the book, you'll be able to build end-to-end data analysis pipelines and apply modern data science and AI techniques to solve real-world challenges.

Autoren/Hrsg.

Navlani, Avinash

Wijaya, Cornellius Yudha

Leseproben

Preface

Data analysis has become one of the most important practical skills in modern workflows. Organizations collect more data than ever, but raw data on its own does not create value. Value comes from knowing how to explore, clean, model, interpret, and communicate data results in ways that support real decisions. Python has become one of the most widely used languages for this work because it combines a simple programming model with a rich ecosystem for statistics, visualization, machine learning, and large-scale data processing. This book is written to help you build that practical capability in a structured and progressive way.

Rather than treating data analysis as a collection of disconnected tools, this book approaches it as an end-to-end workflow. We begin with the foundations that every practitioner needs: understanding the data analysis process, setting up a productive Python environment, and building fluency with essential libraries such as NumPy and pandas, along with the statistical and linear algebra concepts that support analytical thinking. These topics provide the base needed not only to write code, but also to reason correctly about data, transformations, and model behavior.

From there, the book moves into the practical work of exploratory analysis and data preparation. You will learn how to visualize data effectively, retrieve it from a variety of sources, clean messy datasets, engineer useful features, and work with time series data. This stage reflects a simple reality of real-world analytics: before we can build useful models, we need to understand the data and make it usable. Strong analytical work depends as much on careful preparation and exploration as it does on modeling itself.

Once these foundations are in place, the book shifts into machine learning. We cover supervised learning, unsupervised learning, ensemble methods, and neural networks to show how different modeling approaches fit various business and analytical problems. The goal is not only to show how models are trained but also to help you understand how to evaluate, compare, and apply them responsibly in practice. By placing these chapters after the earlier chapters on statistics, data cleaning, and feature engineering, the book emphasizes that good machine learning depends on a strong analytical foundation.

In the final part of the book, the scope expands to several of the most relevant applied areas in modern Python-based analytics. We examine textual data, image data, large language models and generative AI, parallel computing with Dask, Modin, and Ray, and large-scale analytics with PySpark. These chapters reflect how the field has evolved. Data analysis today is no longer limited to spreadsheets or structured tables. Practitioners increasingly work across multiple data types, larger computational environments, and new AI-driven workflows. This book is designed to help you build enough breadth to understand that wider landscape while remaining grounded in practical Python implementation.

Across the book, the emphasis is on practical learning. The chapters are designed to move from concept to implementation, so that ideas are reinforced with hands-on examples rather than treated as theory alone. Whether you are analyzing tabular data, forecasting time series, building machine learning models, processing text and images, or exploring modern generative AI tools, the aim is the same: to help you develop a strong and usable foundation in Python for data analysis.

This book is also shaped by the reality that the field continues to change. New tools, new frameworks, and new expectations appear quickly. For that reason, the book focuses not only on specific libraries but also on the patterns of thinking that remain useful across changing tools: understanding data, choosing appropriate methods, evaluating results carefully, and building workflows that are both practical and scalable. In that sense, the goal of this book is not only to teach you how to perform data analysis with Python today, but to help you build habits and understanding that will remain valuable as the field continues to evolve.

Who this book is for

This book is written for students, analysts, data professionals, and developers who want to build practical Python skills for data analysis. It is suitable for readers who want to move beyond simple coding examples and understand how modern data workflows are built, from loading and cleaning data to visualization, modeling, and more advanced topics such as text analysis, image analysis, generative AI, parallel computing, and big data processing.

If you are new to data analysis with Python, the early chapters will help you build a strong foundation. You will be introduced to the data analysis process, the Python environment, NumPy, pandas, statistics, and linear algebra before moving into more advanced analytical and machine learning topics. These chapters are designed to help you develop the core understanding needed to work confidently with data in Python.

If you already have some Python experience and want to strengthen your practical data skills, this book will help you connect the pieces into a more complete workflow. The chapters on data visualization, data retrieval and storage, messy data cleaning, feature engineering, time series analysis, and machine learning are especially useful for readers who want to apply Python to real analytical problems rather than only learn syntax or isolated techniques.

If you are a practitioner who wants broader exposure to modern applied topics, this book also covers areas that increasingly matter in real-world work, including natural language processing, image analysis, large language models, generative AI, parallel computing with Dask, Modin, and Ray, and big data analytics with PySpark. These later chapters are intended to give you both practical entry points and a wider view of the modern Python data ecosystem.

A basic familiarity with Python will be helpful, but the book is structured progressively, allowing readers to build from the fundamentals toward more advanced applications. Whether your goal is to strengthen your foundations, improve your day-to-day data workflow, or expand into newer areas of data and AI, this book is designed to support that journey.

What this book covers

, , introduces the data analysis process, the roles involved in data work, and the core tools for building a productive Python environment for analytics. It establishes the broader context in which Python is used for modern data work.

, , develops the essential skills for working with arrays and tabular data. It covers NumPy arrays, indexing, broadcasting, shape manipulation, pandas DataFrames, joining, grouping, remote data access, and working with dates.

, , provides the statistical foundation for data analysis. It covers data types and attributes, descriptive statistics, probability, correlation, inferential statistics, hypothesis testing, A/B testing, and Bayes’ theorem with practical use cases.

, , introduces the mathematical concepts that support many analytical and machine learning methods. It explores vectors, matrices, matrix operations, decomposition, polynomial fitting, randomness, and practical applications of linear algebra in Python.

, , focuses on creating effective visual representations of data. It covers plotting with Matplotlib, pandas-based visualizations, chart enhancement with Seaborn, interactive visualizations with Plotly, and dashboard development with Dash.

, , examines how data is read from and written to a wide range of sources. It includes structured files, databases, cloud storage, and APIs, helping readers build practical data ingestion and storage workflows.

, , addresses one of the most important parts of real-world analysis. It covers handling missing values, identifying and addressing outliers, enhancing datasets through feature engineering, and exploring how generative AI can support aspects of the cleaning process.

, , introduces the fundamentals of time-dependent data. It covers core time series concepts, statistical modeling approaches, and forecasting and evaluation techniques.

, , explains how supervised machine learning methods are applied to predictive tasks. It focuses on regression analysis, classification techniques, and model evaluation.

, , explores machine learning methods for discovering structure without labeled outcomes. It covers clustering, anomaly detection, and methods for evaluating the resulting models.

, , combines multiple models to improve performance. It compares ensemble approaches, implements simple ensembles, and extends to more advanced techniques.

, , introduces neural networks and deep learning concepts. It covers core components such as activation functions and backpropagation, as well as architectures including CNNs, RNNs, LSTMs, and autoencoders.