[go: up one dir, main page]
Everand Logo

Welcome to Everand!

  • Discover millions of ebooks, audiobooks, and so much more with a free trial

    From $11.99/month after trial. Cancel anytime.

    Just Enough R: Learn Data Analysis with R in a Day
    Just Enough R: Learn Data Analysis with R in a Day
    Just Enough R: Learn Data Analysis with R in a Day
    Ebook250 pages1 hour

    Just Enough R: Learn Data Analysis with R in a Day

    By Sivakumaran Raman

    3.5/5

    ()

    Read preview

    About this ebook

    Because there is so much of a buzz around the R programming language in the data science and analytics world, in health-care and other domains, I wrote a book on R-programming for data analysis. The book aims to teach data analysis using R within a single day to anyone who already knows some programming in any other language. The book has sample code (which can be downloaded as a zip file from the Dropbox link provided in the text of the book) that uses the freely available, CMS-sourced Medicare Physician and Other Supplier Data CY 2014 health-care data-set which was released to the public a few years back and created quite a stir.

    LanguageEnglish
    PublisherSivakumaran Raman
    Release dateMar 23, 2017
    ISBN9781370086894
    Just Enough R: Learn Data Analysis with R in a Day
    Author

    Sivakumaran Raman

    Sivakumaran Raman is a physician who has spent most of his career in Medical Informatics and Analytics. With the experience of leadership positions at several large US health insurance and information technology firms, he has extensive expertise working with medical claims and clinical data using big-data platforms like Hadoop and Spark. He counts R among his favorite programming languages along with Scala and Perl.

    Related to Just Enough R

    Related ebooks

    Information Technology For You

    View More
    View More

    Related podcast episodes

    Related categories

    Reviews for Just Enough R

    3.5/5

    2 ratings0 reviews

    What did you think?

    Tap to rate

    Review must be at least 10 words

      Book preview

      Just Enough R - Sivakumaran Raman

      Whom is This Book For?

      If your job involves working with data in any manner, you cannot afford to ignore the R revolution! If your domain is called data analysis, analytics, informatics, data science, reporting, business intelligence, data management, big data, or visualization, you just have to learn R as this programming language is a game-changing sledgehammer.

      However, if you have looked at a standard text on R or read some of the online discussions, you might feel that there is a steep learning curve of six months or more to grok the language. I will debunk this myth through my book by focusing on practical essentials instead of theory.

      If you have programmed in some language in the past (whether that language be SAS, SPSS, C, C++, C#, Java, Python, Perl, Visual Basic, Ruby, Scala, shell scripts, or plain old SQL), even if you are rusty, this book will get you up and running with R in a single day, writing programs for data analysis and visualization.

      At the end of this book you will be able to:

      - write R programs to execute on the 3 major data-analysis phases.

      - visualize data in an illustrative and interactive manner

      - move on to using R for big data analytics

      R you excited? You should be. Let us charge forward!

      Preface

      R (https://en.wikipedia.org/wiki/R_(programming_language)) is an interpreted, open-source, free, statistical-programming and data-analysis language. It was created by Ross Ihaka and Robert Gentleman. It is a functional language and has all the standard programming features like variables, functions, objects, loops, and data-structures.

      R is perfect for data analysis and visualization. Though R can, in theory, be used for tasks like web programming and building software applications, it is not optimized for these purposes and is not preferred for these tasks. R was created in 1993 and has become very popular because of the rapid growth of the domains of big data, data science, visualization, and analytics.

      The aim of this book is to teach the elements of R programming in a single day. This book is meant for people who already know how to program in at least one language and want to learn R. After completing this book, the reader should be able to write simple R programs for data analysis. Instead of adopting a spoon-feeding approach, I assume that the reader is familiar with standard programming constructs like variables, functions and the like – therefore, I only outline differences in the way R does things. The emphasis is on writing and running programs in R for data analysis and visualization. The book includes a sample data-analysis conducted on freely available CMS-sourced (CMS: Centers for Medicare and Medicaid Services) healthcare data. The book does not aim to teach all the elements of statistics, machine learning or data science – since doing so would expand the scope of the book immensely.

      Unlike many standard texts on R, the book teaches the most effective way to accomplish any specific task in R. No effort is made to teach all the ways in which a particular task can be completed: No TMTOWTDI (https://en.wikipedia.org/wiki/There's_more_than_one_way_to_do_it)!

      All through the text, I provide a lot of Internet links to more information and detail. This is one of the great things about open-source software – it is usually supported by a very active web-based community of users and almost all the answers to questions newbies might have can be found online. The R community is one of the largest and best in this regard. Lastly, instead of laying out all the theory behind R programming (for which there are numerous other sources on the Internet), the emphasis is on learning by doing – the code samples provided throughout the book should be read and understood line by line. The reader should make an effort to complete the practice exercises offered at the ends of certain chapters.

      Preparation to Start

      Computer

      Any Windows® or Linux machine can be used. I would recommend at least 8 GB of Random Access Memory be available on the computer.

      The R programs used in this book were run on two different computers:

      • R version 3.3.2 on a Windows laptop running Windows 10 Pro, Intel(R) Core(TM) i5-2520M CPU @ 2.50 GHz, 8Gb RAM, L3 cache size 3072 KB

      • R version 3.3.3 on a Linux laptop running Ubuntu 14.04, Intel(R) Celeron(R) CPU 1007U @ 1.50GHz, 8Gb RAM, L3 cache size 2048 KB

      R is available for Mac and other platforms as well – interested readers can use these.

      Installation of Java

      Some of the R packages we will be using are wrappers around Java-based libraries and thus require the Java Runtime Environment (JRE) to be installed on the computer. Please install the latest version of the Oracle JRE (http://www.oracle.com/technetwork/java/javase/downloads/index-jsp-138363.html) if you are on Windows. On Linux, you can install either the OpenJDK (http://openjdk.java.net/) Java Runtime (using apt-get or a similar software installation tool) or the Oracle JRE for Linux.

      After installation, ensure that the java executable is in the PATH. This can be tested by running the java -version command at the Linux (bash) shell or Windows command line (cmd.exe or powershell.exe) and seeing if the appropriate message appears:

      Linux bash shell:

      radium@aceraspiredelto:~$ java -version

      java version 1.7.0_121

      OpenJDK Runtime Environment (IcedTea 2.6.8) (7u121-2.6.8-1ubuntu0.14.04.3)

      OpenJDK 64-Bit Server VM (build 24.121-b00, mixed mode)

      Windows cmd.exe shell:

      C:\Users\shiminty\Desktop>java -version

      java version 1.8.0_121

      Java(TM) SE Runtime Environment (build 1.8.0_121-b13)

      Java HotSpot(TM) 64-Bit Server VM (build 25.121-b13, mixed mode)

      If the java executable is not in the PATH, please edit the PATH variable (at the system or user level) and add the path to java (java.exe on Windows) to the PATH variable.

      Installation of R and associated software and packages

      For Windows, R binaries can be downloaded and installed from the R website (https://www.r-project.org/). After installing R on Windows, please edit the PATH variable (at the system or user level) and add the paths to R.exe, Rscript.exe to the variable.

      For installation of R on Linux, it is best to use the software package management tool for your Linux distribution. For Debian and Ubuntu Linux, the tool to use is apt-get. Linux installs of R using tools like apt-get mostly add the paths to the R and Rscript executables to the PATH variable. However, if this is not the case, please modify your PATH variable on Linux.

      After R has been installed, install the R packages we will need by running the install.packages() command within R with a list of supplied package names. First, start up the R interactive-session (also called a Read-Eval-Print-Loop or REPL) by typing R at the command line. Then run the install.packages() command copied from the text-box below with the full list of packages to be installed. Make sure you are connected to the Internet and choose a CRAN (Comprehensive R Archive Network) package repository mirror close to your geographical location. If R warns you about the fact that it is installing the packages in a user-level local repository (since you are running R on the machine without admin or root privileges), it is not a cause for concern: Respond with a Yes to this message, and proceed.

      On Linux, the command line session looks like this (list of R packages included):

      radium@aceraspiredelto:~$ R

      R version 3.3.2 (2016-10-31) -- Sincere Pumpkin Patch

      Copyright (C) 2016 The R Foundation for Statistical Computing

      Platform: x86_64-pc-linux-gnu (64-bit)

      R is free software and comes with ABSOLUTELY NO WARRANTY.

      You are welcome to redistribute it under certain conditions.

      Type 'license()' or 'licence()' for distribution details.

      Natural language support but running in an English locale

      R is a collaborative project with many contributors.

      Type 'contributors()' for more information and

      'citation()' on how to cite R or R packages in publications.

      Type 'demo()' for some demos, 'help()' for on-line help, or

      'help.start()' for an HTML browser interface to help.

      Type 'q()' to quit R.

      > install.packages(c(broom, choroplethr, data.table,

      datacheck, dplyr, dtplyr, ggplot2, ggvis,

      h2o, htmlwidgets, httr, jsonlite, leaflet,

      maps, maptools, OpenStreetMap, plotly,

      randomForest, R2HTML, RDSTK, readr, rjson,

      rpart, RSQLite, scales, sqldf, stargazer,

      svglite, tidyr, tmap, ztable));

      > q()

      Save workspace image? [y/n/c]: n

      radium@aceraspiredelto:~$

      Note: On Linux, some package and software dependencies might crop up while installing the svglite package or other R packages. The svglite package depends on gdtools. But the installation of gdtools first requires the Cairo (https://www.cairographics.org/download/) graphics software developer libraries to be installed using apt-get or similar software package tool on Linux.The way to do it on Ubuntu/Debian Linux is:

      sudo apt-get install libcairo2-dev

      After this, re-running the install.packages() command for svglite within the R REPL should work smoothly:

      radium@aceraspiredelto:~$ R

      R version 3.3.2 (2016-10-31) -- Sincere Pumpkin Patch

      Copyright (C) 2016 The R Foundation for Statistical Computing

      Platform: x86_64-pc-linux-gnu (64-bit)

      R is free software and comes with ABSOLUTELY NO WARRANTY.

      You are welcome to redistribute it under certain conditions.

      Type 'license()' or 'licence()' for

      Enjoying the preview?
      Page 1 of 1