Python Machine Learning

Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition 3rd Edition

Applied machine learning with a solid foundation in theory. Revised and expanded for TensorFlow 2, GANs, and reinforcement learning.

Key Features

• Third edition of the bestselling, widely acclaimed Python machine learning book
• Clear and intuitive explanations take you deep into the theory and practice of Python machine learning
• Fully updated and expanded to cover TensorFlow 2, Generative Adversarial Network models, reinforcement learning, and best practices

Book Description

Python Machine Learning, Third Edition is a comprehensive guide to machine learning and deep learning with Python. It acts as both a step-by-step tutorial, and a reference you'll keep coming back to as you build your machine learning systems.

Packed with clear explanations, visualizations, and working examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, with this machine learning book, Raschka and Mirjalili teach the principles behind machine learning, allowing you to build models and applications for yourself.

Updated for TensorFlow 2.0, this new third edition introduces readers to its new Keras API features, as well as the latest additions to scikit-learn. It's also expanded to cover cutting-edge reinforcement learning techniques based on deep learning, as well as an introduction to GANs. Finally, this book also explores a subfield of natural language processing (NLP) called sentiment analysis, helping you learn how to use machine learning algorithms to classify documents.

This book is your companion to machine learning with Python, whether you're a Python developer new to machine learning or want to deepen your knowledge of the latest developments.

What you will learn

• Master the frameworks, models, and techniques that enable machines to 'learn' from data
• Use scikit-learn for machine learning and TensorFlow for deep learning
• Apply machine learning to image classification, sentiment analysis, intelligent web applications, and more
• Build and train neural networks, GANs, and other models
• Discover best practices for evaluating and tuning models
• Predict continuous target outcomes using regression analysis
• Dig deeper into textual and social media data using sentiment analysis

Who this book is for

If you know some Python and you want to use machine learning and deep learning, pick up this book. Whether you want to start from scratch or extend your machine learning knowledge, this is an essential resource. Written for developers and data scientists who want to create practical machine learning and deep learning code, this book is ideal for anyone who wants to teach computers how to learn from data.

Table of Contents

1. Giving Computers the Ability to Learn from Data
2. Training Simple Machine Learning Algorithms for Classification
3. A Tour of Machine Learning Classifiers Using scikit-learn
4. Building Good Training Datasets – Data Preprocessing
5. Compressing Data via Dimensionality Reduction
6. Learning Best Practices for Model Evaluation and Hyperparameter Tuning
7. Combining Different Models for Ensemble Learning
8. Applying Machine Learning to Sentiment Analysis
9. Embedding a Machine Learning Model into a Web Application
10. Predicting Continuous Target Variables with Regression Analysis
11. Working with Unlabeled Data – Clustering Analysis
12. Implementing a Multilayer Artificial Neural Network from Scratch
13. Parallelizing Neural Network Training with TensorFlow

Data Visualization

Data visualization is the representation of data in a graphical or visual format to help people understand and interpret the information more easily. It is a crucial tool in data analysis, as it can reveal patterns, trends, and insights that might be difficult to discern from raw data. 

Data visualization serves various purposes, such as:

• Exploration: It helps analysts and data scientists explore datasets to identify patterns, anomalies, and relationships.
• Communication: It enables the effective communication of complex data and insights to non-technical stakeholders, making it easier for them to grasp the information.
• Analysis: Data visualization aids in making data-driven decisions by providing a clear visual representation of the data.
• Storytelling: It can be used to tell a compelling data-driven story, making it more engaging and understandable for a broader audience.

There are various types of data visualizations, including:

• Charts and Graphs: These include bar charts, line charts, scatter plots, pie charts, and more, which are used to represent numerical data.
• Maps: Geographic data can be visualized using maps, helping to display information spatially.
• Infographics: These combine text and visuals to convey information in a concise and engaging way.
• Dashboards: Interactive displays that provide an overview of key metrics and allow users to explore data.
• Heatmaps: These visualize data density using color gradients.
• Tree diagrams: Useful for displaying hierarchical data or decision trees.
• Network diagrams: Show relationships between data points in a network or graph format.

Data visualization tools and libraries, such as Tableau, Microsoft Power BI, Python's Matplotlib and Seaborn, R's ggplot2, and D3.js, are commonly used to create visualizations. The choice of tool depends on the specific requirements and the data at hand.

Effective data visualization should consider factors like the target audience, the type of data being visualized, the story or message you want to convey, and best practices for creating clear and informative visuals. It's essential to avoid common pitfalls like misrepresenting data or creating overly complex visuals that can confuse rather than clarify information.

Image segmentation

Image segmentation is a computer vision and image processing technique that involves partitioning an image into multiple regions or segments, each of which corresponds to a meaningful object or part of the image. The goal of image segmentation is to separate the objects or regions of interest from the background or from each other in an image. This technique is widely used in various applications, including object recognition, image editing, medical imaging, and autonomous driving, among others.

There are several methods and approaches for image segmentation, including:

• Thresholding: This is one of the simplest segmentation techniques, where pixels are separated into two groups based on a specified threshold value. Pixels with intensities above the threshold are considered part of one segment, while those below it belong to another.
• Edge-based segmentation: Edge detection techniques, such as the Canny edge detector, locate boundaries between objects in an image. These edges can be used as the basis for segmentation.
• Region-based segmentation: This approach groups pixels into regions based on their similarities in terms of color, texture, or other image attributes. Common methods include region growing and region splitting.
• Clustering: Clustering algorithms like k-means or hierarchical clustering can be used to group pixels with similar characteristics into segments.
• Watershed segmentation: The watershed transform treats the image as a topographic surface, and it floods the surface from the lowest points, separating regions at ridges.
• Deep Learning: Convolutional neural networks (CNNs), especially fully convolutional networks (FCNs) and U-Net, have proven to be very effective for image segmentation tasks. These models can learn to segment objects based on labeled training data.
• Graph-based segmentation: This approach represents an image as a graph, with pixels as nodes and edges connecting neighboring pixels. Segmentation is achieved by finding the best cuts in the graph.
• Active contours (Snakes): Active contours are deformable models that can be iteratively adjusted to locate object boundaries in an image.
• Markov Random Fields (MRF): MRF models consider the relationships between neighboring pixels and use probabilistic models to segment images.

The choice of segmentation method depends on the specific problem and the characteristics of the images you are working with. Some methods work better for natural scenes, while others may be more suitable for medical images or other domains. Deep learning approaches have gained popularity due to their ability to learn features and adapt to various image types, but they often require large labeled datasets for training.

Image segmentation is a fundamental step in many computer vision tasks, such as object detection, image recognition, and image understanding, and it plays a crucial role in extracting meaningful information from images.

Thresholding

Thresholding is a fundamental technique in image processing and signal processing used to separate objects or features of interest from the background in an image or a signal. It involves setting a threshold value, which is a predefined intensity or value, and then categorizing each pixel or data point in the image or signal as either being part of the foreground or background based on whether its value is above or below the threshold.

Thresholding is commonly used for tasks such as:

• Image Segmentation: In image processing, thresholding can be used to separate objects or regions of interest from the rest of the image. This is especially useful for applications like object detection, character recognition, and medical image analysis.
• Binary Image Creation: By thresholding a grayscale image, you can convert it into a binary image, where pixels that meet a certain condition are set to one (foreground) and those that don't are set to zero (background). This simplifies further processing.
• Noise Reduction: Thresholding can be used to reduce noise in an image or signal by categorizing values above a threshold as signal and values below as noise. This is especially useful in applications where noise needs to be removed or reduced.

There are different methods of thresholding, including:

1. Global Thresholding: In global thresholding, a single threshold value is applied to the entire image or signal. Pixels or data points with values above the threshold are classified as foreground, while those below are classified as background.
2. Local or Adaptive Thresholding: Local thresholding involves using different threshold values for different parts of an image or signal. This can be especially useful in cases where the illumination varies across the image, making a global threshold ineffective. Adaptive thresholding adjusts the threshold value based on the local characteristics of the data.
3. Otsu's Method: Otsu's method is an automatic thresholding technique that calculates an optimal threshold value based on the variance of pixel intensities. It aims to maximize the separability between the foreground and background.
4. Hysteresis Thresholding: Hysteresis thresholding is commonly used in edge detection, where there are two threshold values, a high and a low threshold. Pixels with values above the high threshold are considered edge pixels, and those below the low threshold are discarded. Pixels between the two thresholds are included if they are connected to the edge pixels.

The choice of thresholding method and the threshold value depends on the specific application and the characteristics of the data. Proper thresholding can greatly enhance the quality of extracted information from images or signals.

Natural Language Processing

Natural Language Processing (NLP) is a subfield of artificial intelligence (AI) that focuses on the interaction between computers and human language. It involves the development of algorithms and models that enable computers to understand, interpret, and generate human language in a way that is both meaningful and useful. NLP is a multidisciplinary field that draws upon techniques from linguistics, computer science, machine learning, and cognitive psychology.

Key components and tasks within NLP include:

• Text Analysis: NLP involves various text analysis tasks, such as tokenization (breaking text into words or phrases), part-of-speech tagging (identifying the grammatical category of each word), and syntactic parsing (analyzing sentence structure).
• Named Entity Recognition (NER): Identifying and classifying entities in text, such as names of people, organizations, locations, dates, and more.
• Sentiment Analysis: Determining the sentiment or emotional tone expressed in a piece of text, often used for social media monitoring and customer feedback analysis.
• Machine Translation: Automatically translating text from one language to another, as seen in applications like Google Translate.
• Speech Recognition: Converting spoken language into text, which is used in voice assistants like Siri and Alexa.
• Text Generation: Creating human-like text, which can be used for chatbots, content generation, or creative writing.
• Question Answering: Building systems that can answer questions posed in natural language, such as IBM's Watson.
• Text Summarization: Generating concise summaries of longer texts, which is useful for news aggregation and document summarization.
• Language Modeling: Developing models that can predict the likelihood of a word or phrase given its context, such as the GPT (Generative Pre-trained Transformer) models developed by OpenAI.
• Information Retrieval: Finding relevant documents or information in a large corpus of text, often used in search engines.
• Text Classification: Assigning categories or labels to text, such as spam detection, sentiment classification, or content categorization.

NLP leverages machine learning and deep learning techniques, including recurrent neural networks (RNNs), convolutional neural networks (CNNs), and transformers, to process and analyze language data. These models learn patterns and relationships in language from large datasets, enabling them to perform a wide range of language-related tasks.

NLP has a broad range of applications, including chatbots, virtual assistants, sentiment analysis, recommendation systems, language translation, medical diagnosis, and more. As the field continues to advance, NLP is becoming increasingly important in making human-computer interactions more natural and effective.

Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems 1st Edition

Many books and courses tackle natural language processing (NLP) problems with toy use cases and well-defined datasets. But if you want to build, iterate, and scale NLP systems in a business setting and tailor them for particular industry verticals, this is your guide. Software engineers and data scientists will learn how to navigate the maze of options available at each step of the journey.

Through the course of the book, authors Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta, and Harshit Surana will guide you through the process of building real-world NLP solutions embedded in larger product setups. Youâ??ll learn how to adapt your solutions for different industry verticals such as healthcare, social media, and retail.

With this book, your all:

• Understand the wide spectrum of problem statements, tasks, and solution approaches within NLP
• Implement and evaluate different NLP applications using machine learning and deep learning methods
• Fine-tune your NLP solution based on your business problem and industry vertical
• Evaluate various algorithms and approaches for NLP product tasks, datasets, and stages
• Produce software solutions following best practices around release, deployment, and DevOps for NLP systems
• Understand best practices, opportunities, and the roadmap for NLP from a business and product leaders perspective

Digital Photography Complete Course: Learn Everything You Need to Know in 20 Weeks (DK Complete Courses)

Grab your camera and learn everything you need to know to improve your photography in just 20 weeks.

Introducing Digital Photography Compete Course - the perfect beginner’s learning program for any aspiring photographer, this photography book aims to teach you everything you need to know about photography in just 20 weeks, through easy-to-understand tutorials. 

It’s time to start using your camera to its full potential, and this photography book for beginners can help you do just that. Combining tutorials, step-by-step photo shoots, practical assignments, and fun Q&As, this brilliant book on photography can help you untangle photographic jargon such as aperture, exposure, shutter speed, and depth-of-field; teach you top tips and tricks surrounding the range of modes on bridge and system cameras, and help you to master composition for that perfect photo!

Become a photography expert in no time, as you explore:

• Review, practice and experiment sections to put photography knowledge to the test 
• Technical concepts are broken down and explained in simple, accessible language 
• Easy-to-read diagrams and illustrations to highlight key theories
• The latest technological and creative developments in digital photography and image manipulation

DK’s Digital Photography Complete Course is a must-have book for photography lovers of all ages, whether you’re a photography or art student seeking to learn more about the subject, or a photography beginner looking to improve your own digital photography techniques. Doubling up as the perfect photography gift book for beginners, Digital Photography Compete Course will help you use your camera to its full potential so that you don’t just take good pictures – you take great ones!

Python for Data Analysis: Data Wrangling with pandas, NumPy, and Jupyter 3rd Edition

Get the definitive handbook for manipulating, processing, cleaning, and crunching datasets in Python. Updated for Python 3.10 and pandas 1.4, the third edition of this hands-on guide is packed with practical case studies that show you how to solve a broad set of data analysis problems effectively. You'll learn the latest versions of pandas, NumPy, and Jupyter in the process.

Written by Wes McKinney, the creator of the Python pandas project, this book is a practical, modern introduction to data science tools in Python. It's ideal for analysts new to Python and for Python programmers new to data science and scientific computing.

 

Data files and related material are available on GitHub.

• Use the Jupyter notebook and IPython shell for exploratory computing
• Learn basic and advanced features in NumPy
• Get started with data analysis tools in the pandas library
• Use flexible tools to load, clean, transform, merge, and reshape data
• Create informative visualizations with matplotlib
• Apply the pandas groupby facility to slice, dice, and summarize datasets
• Analyze and manipulate regular and irregular time series data
• Learn how to solve real-world data analysis problems with thorough, detailed examples