Java · Data Science Made Easy by Grigorev, Alexey -- Read -- Imperial Library of Trantor

Index

Preface

What this learning path covers What you need for this learning path Who this learning path is for Conventions Reader feedback Customer support

Downloading the example code Downloading the color images of this book Errata Piracy Questions

Module 1 Getting Started with Data Science

Problems solved using data science Understanding the data science problem - solving approach

Using Java to support data science

Acquiring data for an application The importance and process of cleaning data Visualizing data to enhance understanding The use of statistical methods in data science Machine learning applied to data science Using neural networks in data science Deep learning approaches Performing text analysis Visual and audio analysis Improving application performance using parallel techniques Assembling the pieces Summary

Data Acquisition

Understanding the data formats used in data science applications

Overview of CSV data Overview of spreadsheets Overview of databases Overview of PDF files Overview of JSON Overview of XML Overview of streaming data Overview of audio/video/images in Java

Data acquisition techniques

Using the HttpUrlConnection class Web crawlers in Java

Creating your own web crawler Using the crawler4j web crawler

Web scraping in Java Using API calls to access common social media sites

Using OAuth to authenticate users Handing Twitter Handling Wikipedia Handling Flickr Handling YouTube

Searching by keyword

Summary

Data Cleaning

Handling data formats

Handling CSV data Handling spreadsheets

Handling Excel spreadsheets

Handling PDF files Handling JSON

Using JSON streaming API Using the JSON tree API

The nitty gritty of cleaning text

Using Java tokenizers to extract words

Java core tokenizers Third-party tokenizers and libraries

Transforming data into a usable form

Simple text cleaning Removing stop words

Finding words in text

Finding and replacing text

Data imputation Subsetting data Sorting text Data validation

Validating data types Validating dates Validating e-mail addresses Validating ZIP codes Validating names

Cleaning images

Changing the contrast of an image Smoothing an image Brightening an image Resizing an image Converting images to different formats

Summary

Data Visualization

Understanding plots and graphs

Visual analysis goals

Creating index charts Creating bar charts

Using country as the category Using decade as the category

Creating stacked graphs Creating pie charts Creating scatter charts Creating histograms Creating donut charts Creating bubble charts Summary

Statistical Data Analysis Techniques

Working with mean, mode, and median

Calculating the mean

Using simple Java techniques to find mean Using Java 8 techniques to find mean Using Google Guava to find mean Using Apache Commons to find mean

Calculating the median

Using simple Java techniques to find median Using Apache Commons to find the median

Calculating the mode

Using ArrayLists to find multiple modes Using a HashMap to find multiple modes Using a Apache Commons to find multiple modes

Standard deviation Sample size determination Hypothesis testing Regression analysis

Using simple linear regression Using multiple regression

Summary

Machine Learning

Supervised learning techniques

Decision trees

Decision tree types Decision tree libraries Using a decision tree with a book dataset Testing the book decision tree

Support vector machines

Using an SVM for camping data Testing individual instances

Bayesian networks

Using a Bayesian network

Unsupervised machine learning

Association rule learning

Using association rule learning to find buying relationships

Reinforcement learning Summary

Neural Networks

Training a neural network

Getting started with neural network architectures

Understanding static neural networks

A basic Java example

Understanding dynamic neural networks

Multilayer perceptron networks

Building the model Evaluating the model Predicting other values Saving and retrieving the model

Learning vector quantization Self-Organizing Maps

Using a SOM Displaying the SOM results

Additional network architectures and algorithms

The k-Nearest Neighbors algorithm Instantaneously trained networks Spiking neural networks Cascading neural networks Holographic associative memory Backpropagation and neural networks

Summary

Deep Learning

Deeplearning4j architecture

Acquiring and manipulating data

Reading in a CSV file

Configuring and building a model

Using hyperparameters in ND4J Instantiating the network model

Training a model Testing a model

Deep learning and regression analysis

Preparing the data Setting up the class Reading and preparing the data Building the model Evaluating the model

Restricted Boltzmann Machines

Reconstruction in an RBM Configuring an RBM

Deep autoencoders

Building an autoencoder in DL4J

Configuring the network Building and training the network Saving and retrieving a network Specialized autoencoders

Convolutional networks

Building the model Evaluating the model

Recurrent Neural Networks Summary

Text Analysis

Implementing named entity recognition

Using OpenNLP to perform NER Identifying location entities

Classifying text

Word2Vec and Doc2Vec Classifying text by labels Classifying text by similarity

Understanding tagging and POS

Using OpenNLP to identify POS Understanding POS tags

Extracting relationships from sentences

Using OpenNLP to extract relationships

Sentiment analysis

Downloading and extracting the Word2Vec model Building our model and classifying text

Summary

Visual and Audio Analysis

Text-to-speech

Using FreeTTS Getting information about voices Gathering voice information

Understanding speech recognition

Using CMUPhinx to convert speech to text Obtaining more detail about the words

Extracting text from an image

Using Tess4j to extract text

Identifying faces

Using OpenCV to detect faces

Classifying visual data

Creating a Neuroph Studio project for classifying visual images Training the model

Summary

Mathematical and Parallel Techniques for Data Analysis

Implementing basic matrix operations

Using GPUs with DeepLearning4j

Using map-reduce

Using Apache's Hadoop to perform map-reduce Writing the map method Writing the reduce method Creating and executing a new Hadoop job

Various mathematical libraries

Using the jblas API Using the Apache Commons math API Using the ND4J API

Using OpenCL Using Aparapi

Creating an Aparapi application Using Aparapi for matrix multiplication

Using Java 8 streams

Understanding Java 8 lambda expressions and streams Using Java 8 to perform matrix multiplication Using Java 8 to perform map-reduce

Summary

Bringing It All Together

Defining the purpose and scope of our application Understanding the application's architecture Data acquisition using Twitter Understanding the TweetHandler class

Extracting data for a sentiment analysis model Building the sentiment model Processing the JSON input Cleaning data to improve our results Removing stop words Performing sentiment analysis Analysing the results

Other optional enhancements Summary

Module 2 Data Science Using Java

Data science

Machine learning

Supervised learning Unsupervised learning

Clustering Dimensionality reduction

Natural Language Processing

Data science process models

CRISP-DM A running example

Data science in Java

Data science libraries

Data processing libraries Math and stats libraries Machine learning and data mining libraries Text processing

Summary

Data Processing Toolbox

Standard Java library

Collections Input/Output

Reading input data Writing ouput data

Streaming API

Extensions to the standard library

Apache Commons

Commons Lang Commons IO Commons Collections Other commons modules

Google Guava AOL Cyclops React

Accessing data

Text data and CSV Web and HTML JSON Databases DataFrames

Search engine - preparing data Summary

Exploratory Data Analysis

Exploratory data analysis in Java

Search engine datasets Apache Commons Math Joinery

Interactive Exploratory Data Analysis in Java

JVM languages

Interactive Java

Joinery shell

Summary

Supervised Learning - Classification and Regression

Classification

Binary classification models

Smile JSAT LIBSVM and LIBLINEAR Encog

Evaluation

Accuracy Precision, recall, and F1 ROC and AU ROC (AUC) Result validation K-fold cross-validation Training, validation, and testing

Case study - page prediction Regression

Machine learning libraries for regression

Smile JSAT Other libraries

Evaluation

MSE MAE

Case study - hardware performance Summary

Unsupervised Learning - Clustering and Dimensionality Reduction

Dimensionality reduction

Unsupervised dimensionality reduction Principal Component Analysis Truncated SVD Truncated SVD for categorical and sparse data

Random projection

Cluster analysis

Hierarchical methods K-means

Choosing K in K-Means DBSCAN

Clustering for supervised learning

Clusters as features Clustering as dimensionality reduction Supervised learning via clustering

Evaluation

Manual evaluation Supervised evaluation Unsupervised Evaluation

Summary

Working with Text - Natural Language Processing and Information Retrieval

Natural Language Processing and information retrieval

Vector Space Model - Bag of Words and TF-IDF

Vector space model implementation

Indexing and Apache Lucene Natural Language Processing tools

Stanford CoreNLP

Customizing Apache Lucene

Machine learning for texts

Unsupervised learning for texts

Latent Semantic Analysis Text clustering Word embeddings

Supervised learning for texts Text classification Learning to rank for information retrieval

Reranking with Lucene

Summary

Extreme Gradient Boosting

Gradient Boosting Machines and XGBoost

Installing XGBoost

XGBoost in practice

XGBoost for classification

Parameter tuning Text features Feature importance

XGBoost for regression XGBoost for learning to rank

Summary

Deep Learning with DeepLearning4J

Neural Networks and DeepLearning4J

ND4J - N-dimensional arrays for Java Neural networks in DeepLearning4J Convolutional Neural Networks

Deep learning for cats versus dogs

Reading the data Creating the model Monitoring the performance Data augmentation Running DeepLearning4J on GPU

Summary

Scaling Data Science

Apache Hadoop

Hadoop MapReduce Common Crawl

Apache Spark Link prediction

Reading the DBLP graph Extracting features from the graph Node features Negative sampling Edge features Link Prediction with MLlib and XGBoost Link suggestion

Summary

Deploying Data Science Models

Microservices

Spring Boot Search engine service

Online evaluation

A/B testing Multi-armed bandits

Summary

Bibliography

← Prev
Back
Next →

← Prev
Back
Next →