Data Science with Java by Michael R. Brzustowicz, PhD -- Read -- Imperial Library of Trantor

Index

Preface

Who Should Read This Book Why I Wrote This Book A Word on Data Science Today Navigating This Book Conventions Used in This Book Using Code Examples O’Reilly Safari How to Contact Us Acknowledgments

1. Data I/O

What Is Data, Anyway? Data Models

Univariate Arrays Multivariate Arrays Data Objects Matrices and Vectors JSON

Dealing with Real Data

Nulls Blank Spaces Parse Errors Outliers

Managing Data Files

Understanding File Contents First Reading from a Text File

Parsing big strings Parsing delimited strings Parsing JSON strings

Reading from a JSON File Reading from an Image File Writing to a Text File

Mastering Database Operations

Command-Line Clients Structured Query Language

Create Select Insert Update Delete Drop

Java Database Connectivity

Connections Statements Prepared statements Result sets

Visualizing Data with Plots

Creating Simple Plots

Scatter plots Bar charts Plotting multiple series Basic formatting

Plotting Mixed Chart Types Saving a Plot to a File

2. Linear Algebra

Building Vectors and Matrices

Array Storage Block Storage Map Storage Accessing Elements Working with Submatrices Randomization

Operating on Vectors and Matrices

Scaling Transposing Addition and Subtraction Length Distances Multiplication Inner Product Outer Product Entrywise Product Compound Operations Affine Transformation Mapping a Function

Decomposing Matrices

Cholesky Decomposition LU Decomposition QR Decomposition Singular Value Decomposition Eigen Decomposition Determinant Inverse

Solving Linear Systems

3. Statistics

The Probabilistic Origins of Data

Probability Density Cumulative Probability Statistical Moments Entropy Continuous Distributions

Uniform Normal Multivariate normal Log normal Empirical

Discrete Distributions

Bernoulli Binomial Poisson

Characterizing Datasets

Calculating Moments

Sample moments Updating moments

Descriptive Statistics

Count Sum Min Max Mean Median Mode Variance Standard deviation Error on the mean Skewness Kurtosis

Multivariate Statistics Covariance and Correlation

Covariance Pearson’s correlation

Regression

Simple regression Multiple regression

Working with Large Datasets

Accumulating Statistics Merging Statistics Regression

Using Built-in Database Functions

4. Data Operations

Transforming Text Data

Extracting Tokens from a Document Utilizing Dictionaries Vectorizing a Document

Scaling and Regularizing Numeric Data

Scaling Columns

Min-max scaling Centering the data Unit normal scaling

Scaling Rows

L1 regularization L2 regularization

Matrix Scaling Operator

Reducing Data to Principal Components

Covariance Method SVD Method

Creating Training, Validation, and Test Sets

Index-Based Resampling List-Based Resampling Mini-Batches

Encoding Labels

A Generic Encoder One-Hot Encoding

5. Learning and Prediction

Learning Algorithms

Iterative Learning Procedure Gradient Descent Optimizer

Evaluating Learning Processes

Minimizing a Loss Function

Linear loss Quadratic loss Cross-entropy loss

Bernoulli Multinomial Two-Point

Minimizing the Sum of Variances Silhouette Coefficient Log-Likelihood Classifier Accuracy

Unsupervised Learning

k-Means Clustering DBSCAN

Dealing with outliers Optimizing radius of capture and minPoints Inference from DBSCAN

Gaussian Mixtures

Gaussian mixture model Fitting with the EM algorithm Optimizing the number of clusters

Supervised Learning

Naive Bayes

Gaussian Multinomial Bernoulli Iris example

Linear Models

Linear Logistic Softmax Tanh Linear model estimator Iris example

Deep Networks

A network layer Feed forward Back propagation Deep network estimator MNIST example

6. Hadoop MapReduce

Hadoop Distributed File System MapReduce Architecture Writing MapReduce Applications

Anatomy of a MapReduce Job Hadoop Data Types

Writable and WritableComparable types Custom Writable and WritableComparable types

Writable WritableComparable

Mappers

Generic mappers Customizing a mapper

Reducers

Generic reducers Customizing a reducer

The Simplicity of a JSON String as Text Deployment Wizardry

Running a standalone program Deploying a JAR application Including dependencies Simplifying with a BASH script

MapReduce Examples

Word Count Custom Word Count Sparse Linear Algebra

A. Datasets

Anscombe’s Quartet Sentiment Gaussian Mixtures Iris MNIST

Index

← Prev
Back
Next →

← Prev
Back
Next →