Essentials of Python for Artificial Intelligence and Machine Learning

✍ Scribed by Anupam Bagchi, Pramod Gupta

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 524
• Series: Synthesis Lectures on Engineering, Science, and Technology
• Category: Library

✦ Synopsis

This book introduces the essentials of Python for the emerging fields of Machine Learning (ML) and Artificial Intelligence (AI). The authors explore the use of Python’s advanced module features and apply them in probability, statistical testing, signal processing, financial forecasting, and various other applications. This includes mathematical operations with array data structures, Data Manipulation, Data Cleaning, machine learning, Data pipeline, probability density functions, interpolation, visualization, and other high-performance benefits using the core scientific packages NumPy, Pandas, SciPy, Sklearn/Scikit learn and Matplotlib. Readers will gain a deep understanding with problem-solving experience on these powerful platforms when dealing with engineering and scientific problems related to Machine Learning and Artificial Intelligence. Several examples of real problems using these techniques are provided along with examples. The authors also focus on the best practices in the industry on using Python for AI and ML. Deployment on a cloud infrastructure is described in detail (with code) to emphasize real scenarios.

✦ Table of Contents

Foreword
Preface
Key Features
Acknowledgments
Essentials of Python for Artificial Intelligence and Machine Learning
Table of Contents
1 Introduction
1.1 What is Data Science?
1.2 Key Areas of Data Science
1.3 Why is Data Science Important?
1.4 Data Science Applications
1.5 Benefits of Data Science
1.6 Operational Life Cycle of Data Science
1.7 Significance of Data Science Process
1.9 Data Science Technologies, Techniques, and Methods
1.10 Data Science Tools and Platforms
1.11 Why Use Python for ML and AI
1.12 Installation Considerations
1.13 Python Machine Learning Ecosystem
1.14 Magic Commands
1.15 References
2 Statistical Methods and Models
2.1 Introduction
2.2 Statistical terms and definitions
2.3 Statistical distributions
2.4 Non-parametric Statistical Data
2.5 Statistical Tests
2.6 Bayes Theorem and its Applications
2.7 Regression Models for Prediction and Classification
2.8 References:
3 Python Language Basics
3.1 Numbers
3.2 Variables
3.3 Strings
3.4 Control Flow
3.5 Data Structures
3.6 Functions
3.7 References
4 Introduction to NumPy
4.1 Why Use NumPy?
4.2 What is the Relationship Between NumPy, SciPy, Scikit-learn, and Pandas?
4.3 The NumPy ndarrays: A Multidimensional Array
4.4 Reshaping Arrays
4.5 Flattening an Array
4.6 Expanding and Squeezing an Array
4.7 Array Indexing and Slicing
4.8 Stacking and Concatenating Arrays
4.9 Array Math and Universal Functions
4.10 NumPy Broadcasting
4.11 Linear Algebra with NumPy Arrays
4.12 What is Missing in NumPy?
4.13 References
5 Introduction to Pandas
5.1 Key Features of Pandas
5.2 Benefits of Pandas
5.3 The Rise in Popularity of Pandas
5.4 Difference between NumPy and Pandas
5.5 Pandas Data Objects
5.6 Difference between NumPy array and Pandas Series
5.7 Accessing Data from Series
5.8 Series object attributes
5.9 Dealing with missing or null values
5.10 Arithmetic Operations on Series
5.11Pandas DataFrame
5.12 DataFrame metadata
5.13 Get the statistics from DataFrame
5.14 DataFrame Attributes
5.15 DataFrame Selection
5.16 Subset of the columns of a data frame based on dtype
5.17 Data Frame modification
5.18 How to Use where function
5.19 Rename the Columns
5.20 Reverse the row order
5.21 How to split a text column into separate columns
5.22 Sorting
5.23 Refrences
6 Data Manipulation with Pandas
6.1 Data Preparation
6.2 Challenges in Data Preparation
6.3 When to Use Data Preprocessing?
6.4 Feature Aggregation
6.5 Pivot Tables
6.6 Combining and Merging datasets
6.7 Data Cleaning
6.8 What is the difference between data cleaning and data transformation?
6.9 Missing Values
6.10Duplicated Values
6.11Discretization and Binning
6.12 Detecting Outliers
6.13 Computing Dummy Variables
6.14 References
7 Data Visualization with Python
7.1 What is Data Visualization
7.2 What is Good Visualization?
7.3 Why do we need data visualization?
7.4 The advantages and benefits of good data visualization
7.6 How is data visualization used?
7.7 How to choose the right data visualization?
7.8 Comparing reporting and visualization software
7.9 Visualization packages
7.10 Matplotlib
7.11 Summary
7.12 References
8 Machine Learning
8.1 Terminology
8.2 What is Machine Learning?
8.3 What does exactly learning means for a computer?
8.4 Basic Difference in ML and Traditional Programming
8.5 How do machines learn?
8.6 Steps to Apply ML
8.7 Paradigms of Learning
8.8 Type of Problems in Machine Learning:
8.9 Machine Learning in Practice
8.10 Why Use Machine Learning?
8.11 Why Now?
8.12 Classical Tasks for Machine Learning
8.13 Applications of Machine Learning
8.14 Computing Requirements
8.15 What Tools Are Used in Machine Learning?
8.16 Supervised Machine Learning Algorithms
8.17 Unsupervised Machine Learning Algorithms
8.18 Considerations when Choosing an Algorithm
8.19 Usage of Various ML Algorithms
8.20 Scikit-Learn
8.21 Practical Aspects of Machine Learning
8.22 Performance Metrics of ML Algorithms
8.23 Popular ML algorithms
8.24 Machine Leaning Platforms
9 Data Pipelines using Python
9.1 What is a Data Pipeline?
9.2 Where are Data Pipelines used?
9.3 A Data Pipeline’s Destination
9.4 The Components of a Data Pipeline
9.5 Designing and Implementing a Data Pipeline
9.6 Data Analysis while Processing
9.7 Example Project for Streaming Analytics: Log Processing
9.8 Overview of Application
9.9 Batch Analysis of Apache Log data on a Time Series Database
9.10 Tear-Down of AWS Infrastructure
9.11Summary and Conclusion
9.12 References
10 MLOps: Machine Learning Operations
10.1 What is MLOps?
10.2 Why do we need MLOps?
10.3 Comparing DevOps with MLOps
10.4 Production Infrastructure for Machine Learning Projects
10.5 Levels of Automation in MLOps
10.6 MLFlow: Machine Learning Lifecycle Management
10.7 Installation of MLFlow
10.8 Running a Data Science experiment on MLFlow
10.9 Conclusion
10.10 References:
Index