Data Science Programming Cookbook: A practical approach to data science, machine learning, and LLM with recipes (English Edition)

Data science is transforming modern tech, and mastering it is essential for anyone aiming to analyze data, build predictive models, and deploy cutting-edge AI systems. This Data Science Cookbook is your comprehensive roadmap to understanding core analytics, classical machine learning, and advanced generative AI using a hands-on, practical approach.

This book systematically guides you through the complete data science lifecycle, starting with environment setup, foundational mathematics, exploratory data analysis, and visualization. You will master classical supervised and unsupervised machine learning algorithms, ensemble methods, and neural network architectures. The guide further explores computer vision with OpenCV, natural language processing, transformer mechanics, generative AI, GANs, and parameter-efficient LLM fine-tuning using LoRA and prompt engineering. Backed by 127 recipes, it covers MLOps production deployment with Flask APIs, Azure ML, and model drift monitoring, concluding with capstone projects featuring real-time face detection, GPT-3 chatbots, synthetic image generation, and vector database image comparison.

By the end of this book, you will possess a job-ready understanding of data science, machine learning, and artificial intelligence, equipped with the practical skills needed to build, deploy, and scale real-world applications confidently.

What you will learn

● Perform data processing EDA with Pandas, Seaborn, and web scraping.

● Train classical supervised models using Python and scikit-learn libraries.

● Apply K-means clustering and reduce feature dimensions using PCA.

● Preprocess text, extract embeddings, and implement BERT sentiment classifiers.

● Optimize ensemble models using XGBoost, LightGBM, and hyperparameter tuning.

Who this book is for

Designed for students, software developers, data analysts, and tech professionals aiming to build practical skills in AI. Readers should possess basic computer literacy and fundamental Python knowledge to comfortably navigate the structured hands-on workflows and code recipes.

Table of Contents

1. Introduction to Data Science

2. Getting Started with Python and Data Science

3. Mathematics for Data Science

4. EDA, Data Handling, and Visualization

5. Getting Started with Supervised Machine Learning

6. Getting Started with Unsupervised Machine Learning

7. Intermediate Machine Learning Techniques

8. Deep Learning Fundamentals

9. Advanced Machine Learning

10. Image Processing and Computer Vision

11. LLM and Generative AI

12. Advanced Generative AI and LLM

13. Machine Learning Deployment in Production

14. Projects

Ravi Kore is an AI and data solutions architect with over 20 years of experience in data engineering, analytics, machine learning, and enterprise AI. He specializes in generative AI, LLMs, RAG, MLOps, and cloud-native AI platforms across Azure, Google Cloud, and AWS.Throughout his career, Ravi has designed and delivered large-scale data and AI solutions for global organizations, including leadership roles at Barclays, J.P. Morgan, Publicis Sapient, and UNICC. He has successfully built enterprise AI assistants, intelligent document search platforms, automated summarization systems, and scalable machine learning pipelines.Ravi holds an M.Tech in data engineering and data science from BITS Pilani and is certified as a Google Cloud Professional Data Engineer and Microsoft Azure Data Engineer. He holds professional certifications in Cassandra, Snowflake, and TOGAF(R) 9.2 Enterprise Architecture. As a fractional CTO, AI consultant, and technology leader, Ravi advises startups and enterprises on AI strategy, data modernization, and building production-ready AI products. Through his writing, he aims to bridge the gap between theory and practice by helping readers apply data science and AI techniques to solve real-world business challenges.

Praveen Sahu is a seasoned technology professional with over two decades of experience in the software industry, leading the design, development, and delivery of large-scale enterprise solutions across diverse business domains. Throughout his career, he has played pivotal roles in driving digital transformation initiatives, architecting mission-critical systems, and leading cross-functional teams to successfully deliver complex technology programs. His areas of expertise include Java, microservices, big data, Python, cloud computing (AWS), machine learning, deep learning, data science, and generative AI. He is passionate about leveraging emerging technologies to solve real-world business challenges and build scalable, high-performance solutions. Praveen holds an M.Tech in data science from the Work Integrated Learning Program (WILP) at BITS Pilani. He has also completed the prestigious leadership with AI program from ISB Executive Education. In addition, he holds professional certifications in Java, Cassandra, Internet of Things (IoT), and TOGAF(R) 9.2 Enterprise Architecture. A strong advocate of continuous learning and knowledge sharing, Praveen has conducted several corporate training programs and technical workshops on machine learning, deep learning, Python, microservices, and modern software architecture. He has also been invited as a guest speaker on technology platforms, where he shared insights on Microservices, Python, and artificial intelligence. Over the course of his career, Praveen has worked with leading global organizations, including Oracle Financial Services Software and Barclays. He currently serves as a Principal Engineer at ASCII, where he continues to drive innovation in enterprise technology, cloud-native architectures, data platforms, and AI-powered solutions. Beyond technology, Praveen is passionate about mentoring aspiring professionals and helping organizations embrace the transformative potential of data science, artificial intelligence, and emerging technologies.