Mastering Machine Learning with scikit-learn - Second Edition电子书

Title Page

Copyright

Mastering Machine Learning with scikit-learn

Second Edition

Credits

About the Author

About the Reviewer

www.PacktPub.com

Why subscribe?

Customer Feedback

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Downloading the example code

Errata

Piracy

Questions

The Fundamentals of Machine Learning

Defining machine learning

Learning from experience

Machine learning tasks

Training data, testing data, and validation data

Bias and variance

An introduction to scikit-learn

Installing scikit-learn

Installing using pip

Installing on Windows

Installing on Ubuntu 16.04

Installing on Mac OS

Installing Anaconda

Verifying the installation

Installing pandas, Pillow, NLTK, and matplotlib

Summary

Simple Linear Regression

Simple linear regression

Evaluating the fitness of the model with a cost function

Solving OLS for simple linear regression

Evaluating the model

Summary

Classification and Regression with k-Nearest Neighbors

K-Nearest Neighbors

Lazy learning and non-parametric models

Classification with KNN

Regression with KNN

Scaling features

Summary

Feature Extraction

Extracting features from categorical variables

Standardizing features

Extracting features from text

The bag-of-words model

Stop word filtering

Stemming and lemmatization

Extending bag-of-words with tf-idf weights

Space-efficient feature vectorizing with the hashing trick

Word embeddings

Extracting features from images

Extracting features from pixel intensities

Using convolutional neural network activations as features

Summary

From Simple Linear Regression to Multiple Linear Regression

Multiple linear regression

Polynomial regression

Regularization

Applying linear regression

Exploring the data

Fitting and evaluating the model

Gradient descent

Summary

From Linear Regression to Logistic Regression

Binary classification with logistic regression

Spam filtering

Binary classification performance metrics

Accuracy

Precision and recall

Calculating the F1 measure

ROC AUC

Tuning models with grid search

Multi-class classification

Multi-class classification performance metrics

Multi-label classification and problem transformation

Multi-label classification performance metrics

Summary

Naive Bayes

Bayes' theorem

Generative and discriminative models

Naive Bayes

Assumptions of Naive Bayes

Naive Bayes with scikit-learn

Summary

Nonlinear Classification and Regression with Decision Trees

Decision trees

Training decision trees

Selecting the questions

Information gain

Gini impurity

Decision trees with scikit-learn

Advantages and disadvantages of decision trees

Summary

From Decision Trees to Random Forests and Other Ensemble Methods

Bagging

Boosting

Stacking

Summary

The Perceptron

The perceptron

Activation functions

The perceptron learning algorithm

Binary classification with the perceptron

Document classification with the perceptron

Limitations of the perceptron

Summary

From the Perceptron to Support Vector Machines

Kernels and the kernel trick

Maximum margin classification and support vectors

Classifying characters in scikit-learn

Classifying handwritten digits

Classifying characters in natural images

Summary

From the Perceptron to Artificial Neural Networks

Nonlinear decision boundaries

Feed-forward and feedback ANNs

Multi-layer perceptrons

Training multi-layer perceptrons

Backpropagation

Training a multi-layer perceptron to approximate XOR

Training a multi-layer perceptron to classify handwritten digits

Summary

K-means

Clustering

K-means

Local optima

Selecting K with the elbow method

Evaluating clusters

Image quantization

Clustering to learn features

Summary

Dimensionality Reduction with Principal Component Analysis

Principal component analysis

Variance, covariance, and covariance matrices

Eigenvectors and eigenvalues

Performing PCA

Visualizing high-dimensional data with PCA

Face recognition with PCA

Summary