You are reading this probably because you are aware of the importance of machine learning and advanced analytics, such as predictive analytics. While there is an increasing demand for people all over the world who possess these skill sets, there is a real scarcity of data scientists who are skilled enough to deliver applications that involve machine learning and advanced analytics and can create real value from the available data.
The reason for this scarcity is because the field of machine learning and data mining used to be the realm of PhDs and experts in subjects such as math, statistics, and programming combined. It's really difficult to find such unicorns. Again, tasks such as predictive analytics have historically been so difficult that even experts, even if they don't exactly struggle, don't find it easy either. This means that years of experience are needed for newcomers to to get on with it.
In this modern age, predictive analytics is on the verge of being industrialized as it is the key to sustaining and promoting the growth of a business. While the scarcity of "unicorn" data scientists doesn't seem to be ending, organizations are now finding solutions to get over this problem. A leading IT research firm, Gartner, suggests that, in the coming days, a new breed of professionals will emerge, referred to as citizen data scientists. Their emergence may bring about such a change that they may soon outnumber unicorn data scientists by a ratio of 5:1.
You might be wondering now, who are these citizen data scientists and where have they come from? They are existing developers, people from the business analyst community, and, possibly, new graduates as well, who are data-savvy, passionate about advanced analytics, and determined to stretch themselves and go in-depth into data science concepts. They will democratize data science and enable the industrialization of advanced analytics.
All this is happening and will continue to happen because of one reason: the arrival of new tools and platforms that make advanced analytics so easy and present data science as a commodity. While this brings huge opportunities for such vendors, it also bring good news for organizations and professionals who are picking it up. There is no doubt that Azure Machine Learning is a leader in this field and Microsoft offers this to organizations, strategically.
Microsoft's corporate vice president, Joseph Sirosh, who is in charge of Azure Machine Learning, describes Azure Machine Learning, as published in CITEworld: "This is the fastest way to build predictive models and deploy them. Very few tools exist today if you're going to build solution on the cloud and create applications. This way you can build intelligent applications from data, then publish as APIs so you can hook them up very easily from any enterprise application—and even from mobile. We're building it simple enough for a high schooler to be able to use it."
This book is an attempt to extend this vision; driven by simplicity, it sets the mission to develop the necessary skills to get started with Microsoft Azure Machine Learning as quickly as possible. The book assumes no prerequisites other than high school math!
Chapter 1, Introduction, sets the context for the book, and it introduces machine learning, predictive analytics, and Azure ML as a whole. It describes a predictive analytics project through its life cycle.
On your mark: do the background work
Chapter 2, ML Studio Inside Out, explains the ML Studio in detail—the development environment of Azure ML.
Chapter 3, Data Exploration and Visualization, familiarizes you with the concepts related to data exploration and visualizations in the first part of this chapter, and then demonstrates the same using ML Studio.
Chapter 4, Getting Data in and out of ML Studio, describes the different options available for data input and output inside ML Studio.
Chapter 5, Data Preparation, familiarizes you with the different options for data preparation in ML Studio, such as data cleaning, transformation, feature selection, and so on.
Get Set: build and deploy predictive models
Chapter 6, Regression Models, familiarizes you with the different regression algorithms available, and demonstrates the building of different regression models with step-by-step tutorials.
Chapter 7, Classification Models, familiarizes you with the different classification algorithms available and demonstrates the building of different classification models with step-by-step tutorials.
Chapter 8, Clustering, explains clustering and then builds a model using ML Studio and the K-means clustering algorithm.
Chapter 9, A Recommender System, introduces you to the concepts of a recommendation system and also the options available in ML Studio for you to build your own recommender system. It then walks you through building a recommendation system with a simple example.
Chapter 10, Extensibility with R and Python, introduces you to integrating your code in ML Studio using R and Python scripting.
Chapter 11, Publishing a Model as a Web Service, explores how easily you can publish a model in an experiment and make it available as a Web service API for others to consume.
Go: apply your learnings to real-world problems
Chapter 12, Case Study Exercise I, presents a classification problem as a case study exercise.
Chapter 13, Case Study Exercise II, presents a regression problem as a case study exercise.
To learn and practice the concepts along with the book, you need the following:
An account in Azure and (ideally) a subscription. You can access the Azure ML service even without a subscription for a few days.
A browser, Internet Explorer, IE 10, or later versions.
Lastly, an Internet connection, of course!
This book is intended for those who want to learn how to use Azure Machine Learning. Perhaps you already know a bit about machine learning, but have never used ML Studio in Azure, or perhaps, you are an absolute newbie. In either case, this book will get you up and running quickly. Any advanced math, statistics or programming knowledge is not a prerequisite; only high school math is good enough!
In this book, you will find a number of text styles that distinguish between different kinds of information. Here are some examples of these styles and an explanation of their meaning.
Code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles are shown as follows: "This means that the azureml_main entry point function can import these modules directly."
A block of code is set as follows:
def azureml_main(dataframe1 = None, dataframe2 = None):
#Get all the columns
cols = dataframe1.columns.tolist()
#Select columns with name starting with letter 'm'
dataframe1=dataframe1[[col for col in cols if col.startswith('m')]]
#Return the modified dataset
return dataframe1New terms and important words are shown in bold. Words that you see on the screen, for example, in menus or dialog boxes, appear in the text like this: "The Filter Based Feature Selection module can identify the most important features in a dataset."
Feedback from our readers is always welcome. Let us know what you think about this book—what you liked or disliked. Reader feedback is important for us as it helps us develop titles that you will really get the most out of.
To send us general feedback, simply e-mail <[email protected]>, and mention the book's title in the subject of your message.
If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, see our author guide at www.packtpub.com/authors.
Now that you are the proud owner of a Packt book, we have a number of things to help you to get the most from your purchase.
We also provide you with a PDF file that has color images of the screenshots/diagrams used in this book. The color images will help you better understand the changes in the output. You can download this file from https://www.packtpub.com/sites/default/files/downloads/Microsoft_Azure_Machine_Learning_ColorImages.pdf.
Although we have taken every care to ensure the accuracy of our content, mistakes do happen. If you find a mistake in one of our books—maybe a mistake in the text or the code—we would be grateful if you could report this to us. By doing so, you can save other readers from frustration and help us improve subsequent versions of this book. If you find any errata, please report them by visiting http://www.packtpub.com/submit-errata, selecting your book, clicking on the Errata Submission Form link, and entering the details of your errata. Once your errata are verified, your submission will be accepted and the errata will be uploaded to our website or added to any list of existing errata under the Errata section of that title.
To view the previously submitted errata, go to https://www.packtpub.com/books/content/support and enter the name of the book in the search field. The required information will appear under the Errata section.
Piracy of copyrighted material on the Internet is an ongoing problem across all media. At Packt, we take the protection of our copyright and licenses very seriously. If you come across any illegal copies of our works in any form on the Internet, please provide us with the location address or website name immediately so that we can pursue a remedy.
Please contact us at <[email protected]> with a link to the suspected pirated material.
We appreciate your help in protecting our authors and our ability to bring you valuable content.
If you have a problem with any aspect of this book, you can contact us at <[email protected]>, and we will do our best to address the problem.