book

Machine Learning with Python

Name: Machine Learning with Python
ISBN: 9783110697254

by Tarkeshwar Barua, Kamal Kant Hiran, Ritesh Kumar Jain, Ruchi Doshi

September 2024

Intermediate to advanced

486 pages

13h 46m

English

De Gruyter

Read now

Unlock full access

Chapter 1 Introduction to Machine Learning
1.1 What Is Machine Learning?1.1.1 Definition of Machine Learning1.1.2 Historical Background1.1.3 Types of Machine Learning1.1.4 Applications of Machine Learning1.1.5 Challenges in Machine Learning1.2 Python in the Machine Learning Landscape1.2.1 Why Python for Machine Learning?1.2.2 Popular Python Libraries for ML1.2.3 Python vs Other Programming Languages in ML1.2.4 Community and Resources for Python ML1.3 Setting Up Your Python Environment1.3.1 Installing Python1.3.2 Virtual Environments and Why They’re Important1.3.3 Essential Python Libraries for ML1.3.4 Using Package Managers: Pip and Conda1.3.5 Setting Up Jupyter Notebook1.3.6 Best Practices for Managing ML Projects in PythonSummaryExercise (MCQs)AnswersFill in the BlanksAnswersDescriptive Questions
Chapter 2 Basics of Python Programming
2.1 Why Python?2.1.1 Drawbacks of Python2.1.2 History of Python2.1.3 Major Features of Python2.1.4 Market Demand2.1.5 Why Python in Mobile App Development?2.1.6 Python Versions2.2 Python Syntax and Structure2.2.1 Indentation and Whitespace2.2.2 Comments and Documentation2.3 Data Types and Variables2.3.1 Primitive Data Types2.3.2 Lists and Tuples2.3.3 Dictionaries and Sets2.4 Control Structures2.4.1 Conditional Statements2.4.2 Loops2.5 Functions and Modules2.5.1 Defining Functions2.5.2 Lambda Functions2.5.3 Modules and Packages2.6 Working with Files2.6.1 File I/O2.7 Working with Libraries2.7.1 Importing Libraries2.7.2 Popular Python Libraries Overview2.8 Object-Oriented Programming in Python2.8.1 Classes and Objects2.8.2 Inheritance and PolymorphismSummaryExercise (MCQs)AnswersFill in the BlanksAnswersDescriptive Questions
Chapter 3 Data Preprocessing in Python
3.1 Numerical and Scientific Computing Using NumPy and SciPy3.1.1 Numerical Computations with NumPyCustomizing np.arange() ParametersFloating-Point Values with np.arange()Specifying Data Type with np.arange()Reshaping Arrays Using reshape()Array ManipulationIndexing and SlicingArray ConcatenationTranspositionReshapingSplitting ArraysAdding/Removing ElementsMathematical FunctionsAggregation and ReductionBroadcastingVectorizationUniversal Functions (ufuncs)Array Broadcasting3.1.2 Scientific Computations with SciPy3.2 Loading Data with Pandas3.2.1 DataFrame and Series3.2.2 Data Manipulation with Pandas3.3 Data Cleaning and Transformation3.3.1 Handling Missing Data3.3.2 Data Type Conversions3.4 Feature Engineering3.4.1 Encoding Categorical Variables3.4.2 Feature Scaling3.5 Data Visualization with Matplotlib and Seaborn3.5.1 Basic Plotting with Matplotlib3.5.2 Advanced Visualizations with Seaborn3.6 Handling Imbalanced Data3.6.1 Resampling Techniques3.6.2 Synthetic Data GenerationSummaryExercise (MCQs)AnswersFill in the BlanksAnswersDescriptive Questions
Chapter 4 Foundations of Machine Learning
4.1 Supervised vs Unsupervised LearningTypes of Supervised LearningTypes of Unsupervised Learning4.1.1 Classification vs Regression4.1.2 Clustering vs Association4.2 Overfitting and Regularization4.2.1 Bias-Variance Trade-Off4.2.2 L1 and L2 Regularization4.3 Evaluation Metrics4.3.1 Metrics for Classification4.3.2 Metrics for Regression4.4 Cross-Validation4.4.1 k-Fold Cross-Validation4.4.2 Leave-One-Out and Stratified K-FoldSummaryExercise (MCQs)AnswersFill in the BlanksAnswersDescriptive Questions
Chapter 5 Classic Machine Learning Algorithms
5.1 Linear Regression5.1.1 Simple Linear Regression5.1.2 Multiple Linear Regression5.1.3 Polynomial Regression5.2 Logistic RegressionWorking PrincipleAdvantagesLimitationsApplicationsExampleExample5.2.1 Binary Classification5.2.2 Multiclass Classification5.2.3 Regularization in Logistic Regression5.3 Decision Trees and Random ForestsDecision TreesRandom ForestsApplications5.3.1 Building Decision Trees5.3.2 Entropy and Information Gain5.3.3 Random Forests and Bagging5.4 Support Vector MachinesTypes of Support Vector MachinesWorking PrincipleSteps to Perform SVMscikit-learn (sklearn)numpy (np)matplotlib.pyplot (plt)5.4.1 Linear SVM5.4.2 Kernel SVM5.4.3 Hyperparameter Tuning in SVM5.5 K-Means Clustering5.5.1 Clustering Basics5.5.2 Selecting the Number of Clusters5.6 Principal Component AnalysisMathematical Concepts Employed in PCAEigendecompositionSelecting Principal ComponentsProjectionMathematical Representation5.6.1 Dimensionality Reduction5.6.2 Eigenvectors and Eigenvalues5.7 Naive BayesBayes’ TheoremApplications5.7.1 Gaussian Naive Bayes5.7.2 Multinomial Naive Bayes5.8 Ensemble Methods: Boosting, Bagging5.8.1 Bagging and Boosting Overview5.8.2 AdaBoost and Gradient BoostingSummaryExercise (MCQs)AnswersFill in the BlanksAnswersDescriptive Questions
Chapter 6 Advanced Machine Learning Techniques
6.1 Gradient Boosted Trees: XGBoost and LightGBMHigh AccuracyFlexibilityFaster InterpretabilityQuick ResponsePreprocessing Not RequiredAny Data AcceptedFaster Prediction6.1.1 XGBoost Algorithm6.1.2 LightGBM Versus XGBoost6.2 Kernel MethodsHow the Kernel Method Works?6.2.1 Kernel TricksImportant Points to Remember About Kernel Tricks6.2.2 Radial Basis Function (RBF) Kernel6.2.3 Clustering Techniques Beyond k-MeansHow DBSCAN Works?Where Not to Use DBSCAN?How CLARA Works?Where Not to Use CLARA?How Spectral Clustering Works?Where Should Spectral Clustering Not Be Used?How Mean Shift Works?Where Should Mean Shift Not Be Used?How Do SOMs Work?Where Should SOMs Not Be Used?Choosing the Right Technique6.3 Anomaly Detection6.3.1 Statistical MethodsWhere to Use Z-Score?Where Should Z-Score Not Be Used?Steps to Calculate IQRWhere to Use IQR?Where Should IQR Not Be Used?How Does OCSVM Work?Where Should OCSVM Not Be Used?6.3.2 Distance-Based MethodsWhere Should NN Not Be Used?6.4 Clustering6.4.1 Isolation Forest6.4.2 Density-Based Methods6.4.3 Other TechniquesSummaryExercise (MCQs)Descriptive Type QuestionsFill in the BlanksAnswersTrue and False
Chapter 7 Neural Networks and Deep Learning
7.1 Introduction to Neural NetworksTypes of Neural NetworksBenefits of Neural NetworksChallenges of Neural Networks7.2 Perceptron7.2.1 Structure of Perceptron7.2.2 Function of Perceptron7.2.3 Where to Use Perceptron7.2.4 Where to Use Activation Function7.3 TensorFlow7.3.1 Computational Graph7.3.2 Eager Execution7.3.3 Keras7.3.4 Sessions7.3.5 Common Operations7.4 Implementing Neural Network Using TensorFlow7.5 Building a Neural Network Using Keras Framework7.5.1 Difference between Keras and Tensorflow7.6 Convolutional Neural Network (CNN)7.6.1 Model: "sequential_2"7.6.2 CNN Architecture7.7 Dropout Layers7.8 Recurrent Neural Networks (RNNs)7.8.1 Types of RNNs7.9 Sequence-to-Sequence Models7.10 Transfer Learning7.11 Using Pretrained Models7.12 Fine-Tuning and Feature Extraction7.12.1 Choosing the Right Approach to Fine-Tune7.13 Generative Adversarial Networks (GANs)7.13.1 Architecture of GANs7.13.2 Best Practices of GANs7.13.3 Application of GANs7.14 Regularization and Optimization in Deep Learning7.15 Batch Normalization7.15.1 How BatchNorm Works?7.15.2 Best Practices of BatchNorm7.16 Gradient Clipping7.16.1 Advantages of Gradient ClippingSummaryExercise (MCQs)Answer KeySome Basic QuestionFill in the BlanksAnswers
Chapter 8 Specialized Applications and Case Studies
8.1 Introduction to Natural Language Processing (NLP)8.1.1 Tokenization8.1.2 Word Embeddings8.1.3 Sequence Modeling for NLP8.2 Time-Series Forecasting8.2.1 Autoregressive Integrated Moving Average (ARIMA) Models8.2.2 Prophet and Neural Networks for Time Series8.3 Recommender Systems8.4 Computer Vision Applications8.4.1 Object Detection and Segmentation8.5 Reinforcement Learning8.5.1 Core Elements of Reinforcement Learning8.5.2 Learning Process8.6 Application of Reinforcement Learning8.7 Challenges of Reinforcement Learning8.8 Q-learning8.9 Deep Q Networks8.10 Policy Gradient MethodsSummaryExercise (MCQs)Answers KeySome Basic QuestionFill in the BlanksAnswersReferences
Index

Content preview from Machine Learning with Python

Chapter 6 Advanced Machine Learning Techniques

6.1 Gradient Boosted Trees: XGBoost and LightGBM

In the 1990s, Robert Schapire and Yoav Freund developed a very popular algorithm called AdaBoost, where underfitting and reducing bias were introduced for the first time. AdaBoost is known as a parent of all gradient boosted decision trees. In the same series of algorithm development, the gradient boosted trees (GBTs) are a powerful and versatile machine learning technique that can be used for both regression and classification tasks. GBT is another popular model ensembling method which works by combining multiple weak learners, such as decision trees, with a single strong learner. Each weak learner is trained to improve the predictions of the ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Machine Learning with Python Cookbook, 2nd Edition

Publisher Resources

ISBN: 9783110697254

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Machine Learning with Python

by Tarkeshwar Barua, Kamal Kant Hiran, Ritesh Kumar Jain, Ruchi Doshi

Chapter 6 Advanced Machine Learning Techniques

6.1 Gradient Boosted Trees: XGBoost and LightGBM

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.