Essential Data Analytics, Data Science, and AI : A Practical Guide for a Data-Driven World

In today's world, understanding data analytics, data science, and artificial intelligence is not just an advantage but a necessity. This book is your thorough guide to learning these innovative fields, designed to make the learning practical and engaging. The book starts by introducing data analytics, data science, and artificial intelligence. It illustrates real-world applications, and, it addresses the ethical considerations tied to AI. It also explores ways to gain data for practice and real-world scenarios, including the concept of synthetic data. Next, it uncovers Extract, Transform, Load (ETL) processes and explains how to implement them using Python. Further, it covers artificial intelligence and the pivotal role played by machine learning models. It explains feature engineering, the distinction between algorithms and models, and how to harness their power to make predictions. Moving forward, it discusses how to assess machine learning models after their creation, with insights into various evaluation techniques. It emphasizes the crucial aspects of model deployment, including the pros and cons of on-device versus cloud-based solutions. It concludes with real-world examples and encourages embracing AI while dispelling fears, and fostering an appreciation for the transformative potential of these technologies. Whether you're a beginner or an experienced professional, this book offers valuable insights that will expand your horizons in the world of data and AI. What you will learn What are Synthetic data and Telemetry data How to analyze data using programming languages like Python and Tableau. What is feature engineering What are the practical Implications of Artificial Intelligence Who this book is for Data analysts, scientists, and engineers seeking to enhance their skills, explore advanced concepts, and stay up-to-date with ethics. Business leaders and decision-makers across industries are interested in understanding the transformative potential and ethical implications of data analytics and AI in their organizations. Table of Contents About the Author About the Technical Reviewers Foreword Chapter 1: Introduction Data Analytics Data Science Artificial Intelligence The Dream Team What to Expect? Chapter 2: Obtaining Data Understanding the Different Types of Data Structured Data Unstructured Data Quantitative Data Qualitative Data Time Series Data Cross-Sectional Data Spatial Data Ways to Obtain Data Web Scraping: Extracting Data from the Web API: Application Programming Interface Questionnaires and Surveys Popular Sites and Datasets Kaggle Hugging Face Quandl Synthetic Data Telemetry Case Studies and Real-World Examples Obtaining Real-World Data Retail Sales Forecasting Financial Fraud Detection Supply Chain Optimization Obtaining Synthetic Data Preserving Privacy in Healthcare Image Recognition Ethics and Liabilities CCPA: California Consumer Privacy Act GDPR: General Data Protection Regulation HIPAA: Health Insurance Portability and Accountability Act Enhancing Transparency and Understanding Using Dataset Cards Why Are Data Cards Important? Conclusion Chapter 3: ETL Pipeline Introduction to ETL Importance of ETL ETL Tools and Techniques Case Studies and Real-World Examples Retail Analytics Healthcare Data Integration Social Media Fraud Detection in Financial Transactions Smart Home Automation Conclusion Chapter 4: Exploratory Data Analysis Introduction to Exploratory Data Analysis Importance of Exploratory Data Analysis Exploratory Data Analysis Tools and Techniques Python R Tableau Power BI Choosing the Right Visualizations for EDA Use Cases of EDA for Business Retail Industry Healthcare Finance Manufacturing Conclusion Chapter 5: Machine Learning Models Introduction to Machine Learning Models Deep Learning Models Key Concepts and Terminology Importance of Machine Learning Models Healthcare Finance Retail Transportation Marketing Machine Learning Models’ Tools and Techniques Programming Languages Frameworks and Libraries TensorFlow PyTorch Keras scikit-Learn Transformers Integrated Development Environments Jupyter Notebook Google Colab Feature Selection and Engineering Pre-trained vs. Fine-Tuned Models Prompt Engineering Conclusion Chapter 6: Evaluating Models Introduction to Evaluating Models Importance of Evaluating Models Tools and Techniques When Evaluating Models’ Examples with Code Monitoring Your Model Examples Where Machine Learning Models Can Be Useful Conclusion Chapter 7: When to Use Machine Learning Models Introduction to When to Use Machine Learning Models Importance of Understanding When to Use Machine Learning Models Assessing the Necessity and Value of Machine Learning Models Identifying the Right Problems Navigating Open-Ended Challenges Adapting to Change in Dynamic Environments Solving Tough Problems Critical Conditions for Successful Machine Learning Models Critical Conditions for Successful AI Products Enhancing Your Model by Leveraging the Data from Interactions with It Cost Considerations for AI Products When to Consider Alternatives Tools and Techniques of When to Use Machine Learning Models’ Techniques and Tools Examples Where Machine Learning Models Can Be Useful Finance: Fraud Detection Retail: Personalized Recommendations Conclusion Chapter 8: Where Machine Learning Models Live Introduction to Where Machine Learning Models Live Key Considerations to Think About When Deciding Where Your Machine Learning Models Should Live Deciding Where the Machine Learning Should Live Built-In Machine Learning Model Cloud-Based Machine Learning Model Stored Machine Learning Results Mixing Different Approaches Tools and Techniques Cloud Services On-Premise Options Edge Devices Hybrid Systems Examples of Machine Learning Deployment Strategies for Industry Needs Retail: Cloud-Based Recommendation Systems Healthcare: Edge AI for Real-Time Diagnostics Manufacturing: Hybrid Systems for Predictive Maintenance Conclusion Chapter 9: Telemetry Introduction to Telemetry Importance of Telemetry Telemetry Tools and Techniques Data Collection Tools Data Transmission Tools Data Analysis Tools Model Decay, a.k.a. Model Drift Types of Drift Ways to Detect Drift Examples of How Telemetry Can Be Used in the World E-commerce Recommendation Systems Autonomous Vehicles Healthcare Monitoring System Conclusion Chapter 10: Adversaries and Abuse Introduction to Adversaries and Abuse Importance of Understanding Adversaries and Abuse in Machine Learning Impact on Security and Privacy Economic and Operational Implications Trust in Machine Learning Systems Ways Adversarial Attacks Can Be Used Data Poisoning in Autonomous Vehicles Model Inversion in Healthcare Evasion Attacks Using Adversarial Images Mitigating Risk Ethical Considerations Conclusion Chapter 11: Working with Models Introduction The Historical Context of Technological Advancement The Benefits of AI: Transformative Potential Across Industries Healthcare: Improved Diagnostics and Personalized Medicine Education: Personalized Learning Manufacturing: Automation and Predictive Maintenance Everyday Life: Personal Assistants and Smart Home Devices AI Enhancing Human Capabilities Successful AI Integration Healthcare Finance Consumer Goods Addressing Common Fears and Misconceptions AI As a Threat to Privacy: Balancing Innovation with Ethical Considerations The Myth of AI As an Uncontrollable Force Responsible AI Understanding Bias Mitigating Bias – Human in the Loop Approach Ways Humans Can Be in the Loop but Not Limited To Benefits of Humans in the Loop Challenges of Humans in the Loop Mitigating Bias – Why Diversity Matters Building Trust and Transparency – Ethical AI: Ensuring Fairness, Accountability, and Transparency The Role of Education and Public Engagement The Future AI: Opportunities and Challenges Conclusion References Index Roma, estate 1982. Oscar de Flavis, boss di quartiere da anni in carcere, viene ucciso per un regolamento di conti. Da quel giorno suo figlio Ugo lotta tra la scelta di una vita diversa, l'università e l'amore per Nina. Dopo una rissa con un tossico che cerca di rapinarlo, Ugo sente il richiamo della vita violenta, quella incarnata da suo zio, e decide di entrare a ogni costo nel "business" di famiglia. Si arriva al 1989. Una rapina in un supermercato andata storta costringe Ugo a prendere un ostaggio che si rivelerà molto scomodo; l'uomo, infatti, è il fratello di un potente petroliere. Inizia così un saliscendi di vicende criminali e vite nascoste che si intrecciano con interessi politici e i grandi cambiamenti internazionali.Il muro di Berlino crolla, così come il sistema che lo ha sorretto per anni. E niente sarà più come prima. In una palude del mar Piccolo viene rinvenuto il corpo mutilato di una ragazza molto conosciuta. Si scatena una caccia all'uomo, più che altro mediatica, e ne fa le spese il fidanzato della vittima. Le indagini vertono poi su Dragon Town, una setta o un'organizzazione segreta che compie atti di cannibalismo e che rivendica l'omicidio della ragazza e di altri misfatti simili. Un mese dopo il primo omicidio, a Taranto giunge un magnate indiano che ha intenzione di creare in città una sede dell'Università privata di cui è fondatore (e che ha diverse sedi nel mondo). Dragon Town rapisce sua figlia e per salvarla un gruppo di uomini si mette in azione, fino alla conclusione in cui vengono rivelati tutti i retroscena.