HANDS-ON MACHINE LEARNING WITH PYTHON : implement neural network solutions with scikit-learn and... pytorch

Here is the perfect comprehensive guide for readers with basic to intermediate level knowledge of machine learning and deep learning. It introduces tools such as NumPy for numerical processing, Pandas for panel data analysis, Matplotlib for visualization, Scikit-learn for machine learning, and Pytorch for deep learning with Python. It also serves as a long-term reference manual for the practitioners who will find solutions to commonly occurring scenarios. The book is divided into three sections. The first section introduces you to number crunching and data analysis tools using Python with in-depth explanation on environment configuration, data loading, numerical processing, data analysis, and visualizations. The second section covers machine learning basics and Scikit-learn library. It also explains supervised learning, unsupervised learning, implementation, and classification of regression algorithms, and ensemble learning methods in an easy manner with theoretical and practical lessons. The third section explains complex neural network architectures with details on internal working and implementation of convolutional neural networks. The final chapter contains a detailed end-to-end solution with neural networks in Pytorch. After completing Hands-on Machine Learning with Python , you will be able to implement machine learning and neural network solutions and extend them to your advantage. What You'll Learn Review data structures in NumPy and Pandas Demonstrate machine learning techniques and algorithm Understand supervised learning and unsupervised learning Examine convolutional neural networks and Recurrent neural networks Get acquainted with scikit-learn and PyTorch Predict sequences in recurrent neural networks and long short term memory Who This Book Is For Data scientists, machine learning engineers, and software professionals with basic skills in Python programming. Table of Contents About the Authors About the Technical Reviewer Acknowledgments Introduction Section 1: Python for Machine Learning Chapter 1: Getting Started with Python 3 and Jupyter Notebook Python 3 Programming Language History of Python Programming Language Philosophy of Python Programming Language Where Python Is Used Installing Python Python on Linux Distributions Python on macOS Python Modes Interactive Mode Script Mode Pip3 Utility Scientific Python Ecosystem Python Implementations and Distributions Anaconda Summary Chapter 2: Getting Started with NumPy Getting Started with NumPy Multidimensional Ndarrays Indexing of Ndarrays Ndarray Properties NumPy Constants Summary Chapter 3: Introduction to Data Visualization NumPy Routines for Ndarray Creation Matplotlib Data Visualization Summary Chapter 4: Introduction to Pandas Pandas Basics Series in Pandas Properties of Series Pandas Dataframes Visualizing the Data in Dataframes Summary Section 2: Machine Learning Approaches Chapter 5: Introduction to Machine Learning with Scikit-learn Learning from Data Supervised Learning Classification Regression Unsupervised Learning Structure of a Machine Learning System Problem Understanding Data Collection Data Annotation and Data Preparation Data Wrangling Model Development, Training, and Evaluation Model Deployment Scikit-Learn Installing Scikit-Learn Understanding the API Your First Scikit-learn Experiment Summary Chapter 6: Preparing Data for Machine Learning Types of Data Variables Nominal Data Ordinal Data Interval Data Ratio Data Transformation Transforming Nominal Attributes Transforming Ordinal Attributes Normalization Min-Max Scaling Standard Scaling Preprocessing Text Preparing NLTK Five-Step NLP Pipeline 1. Segmentation 2. Tokenization Stemming and Lemmatization Removing Stopwords Preparing Word Vectors Preprocessing Images Summary Chapter 7: Supervised Learning Methods: Part 1 Linear Regression Finding the Regression Line Linear Regression Using Python Visualizing What We Learned Evaluating Linear Regression Logistic Regression Line vs. Curve for Expression Probability Learning the Parameters Logistic Regression Using Python Visualizing the Decision Boundary Decision Trees Building a Decision Tree Picking the Splitting Attribute Decision Tree in Python Pruning the Trees Interpreting Decision Trees Summary Chapter 8: Tuning Supervised Learners Training and Testing Processes Measures of Performance Confusion Matrix Recall Precision Accuracy F-Measure Performance Metrics in Python Classification Report Cross Validation Why Cross Validation? Cross Validation in Python ROC Curve Overfitting and Regularization Bias and Variance Regularization L1 and L2 Regularization Hyperparameter Tuning Effect of Hyperparameters Grid Search Random Search Summary Chapter 9: Supervised Learning Methods: Part 2 Naive Bayes Bayes Theorem Conditional Probability How Naive Bayes Works Multinomial Naive Bayes Naive Bayes in Python Support Vector Machines How SVM Works Nonlinear Classification Kernel Trick in SVM Support Vector Machines in Python Summary Chapter 10: Ensemble Learning Methods Bagging and Random Forest Random Forest in Python Boosting Boosting in Python Stacking Ensemble Stacking in Python Summary Chapter 11: Unsupervised Learning Methods Dimensionality Reduction Understanding the Curse of Dimensionality Principal Component Analysis Principal Component Analysis in Python Clustering Clustering Using K-Means K-Means in Python What Is the Right K? Clustering for Image Segmentation Clustering Using DBSCAN Frequent Pattern Mining Market Basket Analysis Frequent Pattern Mining in Python Summary Section 3: Neural Networks and Deep Learning Chapter 12: Neural Network and PyTorch Basics Installing PyTorch PyTorch Basics Creating a Tensor Tensor Operations Perceptron Perceptron in Python Artificial Neural Networks Summary Chapter 13: Feedforward Neural Networks Feedforward Neural Network Training Neural Networks Gradient Descent Backpropagation Loss Functions Mean Squared Error (MSE) Mean Absolute Error Negative Log Likelihood Loss Cross Entropy Loss Hinge Loss ANN for Regression Activation Functions ReLU Activation Function Sigmoid Activation Function Tanh Activation Function Multilayer ANN NN Class in PyTorch Overfitting and Dropouts Classifying Handwritten Digits Summary Chapter 14: Convolutional Neural Networks Convolution Operation Structure of a CNN Padding and Stride CNN in PyTorch Image Classification Using CNN What Did the Model Learn? Deep Networks of CNN Summary Chapter 15: Recurrent Neural Networks Recurrent Unit Types of RNN One to One One to Many Many to One Many to Many RNN in Python Long Short-Term Memory LSTM Cell Time Series Prediction Gated Recurrent Unit Summary Chapter 16: Bringing It All Together Data Science Life Cycle CRISP-DM Process Phase 1: Business Understanding Phase 2: Data Understanding Phase 3: Data Preparation Phase 4: Modelling Phase 5: Evaluation Phase 6: Deployment How ML Applications Are Served Learning with an Example Defining the Problem Data Preparing the Model Serializing for Future Predictions Hosting the Model Hello World in Flask What’s Next Index Here is the perfect comprehensive guide for readers with basic to intermediate level knowledge of machine learning and deep learning. It introduces tools such as NumPy for numerical processing, Pandas for panel data analysis, Matplotlib for visualization, Scikit-learn for machine learning, and Pytorch for deep learning with Python. It also serves as a long-term reference manual for the practitioners who will find solutions to commonly occurring scenarios. The book is divided into three sections. The first section introduces you to number crunching and data analysis tools using Python with in-depth explanation on environment configuration, data loading, numerical processing, data analysis, and visualizations. The second section covers machine learning basics and Scikit-learn library. It also explains supervised learning, unsupervised learning, implementation, and classification of regression algorithms, and ensemble learning methods in an easy manner with theoretical and practical lessons. The third section explains complex neural network architectures with details on internal working and implementation of convolutional neural networks. The final chapter contains a detailed end-to-end solution with neural networks in Pytorch. After completing Hands-on Machine Learning with Python, you will be able to implement machine learning and neural network solutions and extend them to your advantage. You will: Review data structures in NumPy and Pandas Demonstrate machine learning techniques and algorithm Understand supervised learning and unsupervised learning Examine convolutional neural networks and Recurrent neural networks Get acquainted with scikit-learn and PyTorch Predict sequences in recurrent neural networks and long short term memory .