Microsoft Azure Machine Learning电子书

Microsoft Azure Machine Learning

Table of Contents

Microsoft Azure Machine Learning

Credits

About the Author

Acknowledgments

About the Reviewers

www.PacktPub.com

Support files, eBooks, discount offers, and more

Why subscribe?

Free access for Packt account holders

Instant updates on new Packt books

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Downloading the color images of this book

Errata

Piracy

Questions

1. Introduction

Introduction to predictive analytics

Problem definition and scoping

Data collection

Data exploration and preparation

Model development

Model deployment

Machine learning

Types of machine learning problems

Classification

Regression

Clustering

Common machine learning techniques/algorithms

Linear regression

Logistic regression

Decision tree-based ensemble models

Neural networks and deep learning

Introduction to Azure Machine Learning

ML Studio

Summary

2. ML Studio Inside Out

Introduction to ML Studio

Getting started with Microsoft Azure

Microsoft account and subscription

Creating and managing ML workspaces

Inside ML Studio

Experiments

Creating and editing an experiment

Running an experiment

Creating and running an experiment – do it yourself

Workspace as a collaborative environment

Summary

3. Data Exploration and Visualization

The basic concepts

The mean

The median

Standard deviation and variance

Understanding a histogram

The box and whiskers plot

The outliers

A scatter plot

Data exploration in ML Studio

Visualizing an automobile price dataset

A histogram

The box and whiskers plot

Comparing features

A snapshot

Do it yourself

Summary

4. Getting Data in and out of ML Studio

Getting data in ML Studio

Uploading data from a PC

The Enter Data module

The Data Reader module

Getting data from the Web

Fetching a public dataset – do it yourself

Getting data from Azure

Data format conversion

Getting data from ML Studio

Saving a dataset on a PC

Saving results in ML Studio

The Writer module

Summary

5. Data Preparation

Data manipulation

Clean Missing Data

Removing duplicate rows

Project columns

The Metadata Editor module

The Add Columns module

The Add Rows module

The Join module

Splitting data

Do it yourself

The Apply SQL Transformation module

Advanced data preprocessing

Removing outliers

Data normalization

The Apply Math Operation module

Feature selection

The Filter Based Feature Selection module

The Fisher Linear Discriminant Analysis module

Data preparation beyond ready-made modules

Summary

6. Regression Models

Understanding regression algorithms

Train, score, and evaluate

The test and train dataset

Evaluating

The mean absolute error

The root mean squared error

The relative absolute error

The relative squared error

The coefficient of determination

Linear regression

Optimizing parameters for a learner – the sweep parameters module

The decision forest regression

The train neural network regression – do it yourself

Comparing models with the evaluate model

Comparing models – the neural network and boosted decision tree

Other regression algorithms

No free lunch

Summary

7. Classification Models

Understanding classification

Evaluation metrics

True positive

False positive

True negative

False negative

Accuracy

Precision

Recall

The F1 score

Threshold

Understanding ROC and AUC

Motivation for the matrix to consider

Training, scoring, and evaluating modules

Classifying diabetes or not

Two-class bayes point machine

Two-class neural network with parameter sweeping

Predicting adult income with decision-tree-based models

Do it yourself – comparing models to choose the best

Multiclass classification

Evaluation metrics – multiclass classification

Multiclass classification with the Iris dataset

Multiclass decision forest

Comparing models – multiclass decision forest and logistic regression

Multiclass classification with the Wine dataset

Multiclass neural network with parameter sweep

Do it yourself – multiclass decision jungle

Summary

8. Clustering

Understanding the K-means clustering algorithm

Creating a K-means clustering model using ML Studio

Do it yourself

Clustering versus classification

Summary

9. A Recommender System

The Matchbox recommender

Types of recommendations

Understanding the recommender modules

The Train Matchbox recommender

The number of traits

The number of recommendation algorithm iterations

The Score Matchbox recommender

The evaluate recommender

Building a recommendation system

Summary

10. Extensibility with R and Python

Introduction to R

Introduction to Python

Why should you extend through R/Python code?

Extending experiments using the Python language

Understanding the Execute Python Script module

Creating visualizations using Python

A simple time series analysis with the Python script

Importing the existing Python code

Do it yourself – Python

Extending experiments using the R language

Understanding the Execute R Script module

A simple time series analysis with the R script

Importing an existing R code

Including an R package

Understanding the Create R Model module

Do it yourself – R

Summary

11. Publishing a Model as a Web Service

Preparing an experiment to be published

Saving a trained model

Creating a scoring experiment

Specifying the input and output of the web service

Publishing a model as a web service

Visually testing a web service

Consuming a published web service

Web service configuration

Updating the web service

Summary

12. Case Study Exercise I

Problem definition and scope

The dataset

Data exploration and preparation

Feature selection

Model development

Model deployment

Summary

13. Case Study Exercise II

Problem definition and scope

The dataset

Data exploration and preparation

Model development

Model deployment

Summary

Index