1. Install R language Environment
Su-c ' RPM-UVH http://download.fedoraproject.org/pub/epel/6/i386/epel-release-6-8.noarch.rpm '
Su-c ' yum install foo '
Yum List r-\*
Yum Install R
2. Install Rstudio Desktop and server
Desktop is the RPM package, double-click Execute
Server installation command:
Yum Install openssl098e # Required only for Redhat/centos 6 and 7
wget http://download2.rstudio.org/rstudio-server-0.98.1091-x86_64.rpm
Yum Install--nogpgcheck rstudio-server-0.98.1091-x86_64.rpm
Add R-user User
3. Install GCC, git, pkg-config
Yum install gcc git pkg-config
4, Installation thrift0.9.0
Yum Install Automake Libtool Flex Bison pkgconfig gcc-c++ boost-devel libevent-devel zlib-devel python-devel ruby-devel
To compile the installation steps:
Update the System
???? Yum-y Update
Install The Platform development Tools
???? Yum-y Groupinstall "Development Tools"
Upgrade Autoconf/automake/bison
???? Yum install-y wget
Upgrade autoconf
???? wget http://ftp.gnu.org/gnu/autoconf/autoconf-2.69.tar.gz
???? Tar xvf autoconf-2.69.tar.gz
???? CD autoconf-2.69
????. /configure--PREFIX=/USR
???? Make
???? Make install
Upgrade Automake
???? wget http://ftp.gnu.org/gnu/automake/automake-1.14.tar.gz
???? Tar xvf automake-1.14.tar.gz
???? CD automake-1.14
????. /configure--PREFIX=/USR
???? Make
???? Make install
Upgrade Bison
???? wget http://ftp.gnu.org/gnu/bison/bison-2.5.1.tar.gz
???? Tar xvf bison-2.5.1.tar.gz
???? CD bison-2.5.1
????. /configure--PREFIX=/USR
???? Make
???? Make install
Install C + + Lib Dependencies
???? Yum-y Install Libevent-devel zlib-devel openssl-devel
Upgrade Boost
???? wget http://sourceforge.net/projects/boost/files/boost/1.55.0/boost_1_55_0.tar.gz
???? Tar xvf boost_1_55_0.tar.gz
???? CD Boost_1_55_0
????. /bootstrap.sh
????. /B2 Install
Build and Install the Apache Thrift IDL Compiler
???? git clone https://git-wip-us.apache.org/repos/asf/thrift.git
???? CD Thrift
????. /bootstrap.sh
????. /configure--with-lua=no
???? Modify/THRIFT-0.9.1/LIB/CPP/THRIFT.PC's Includedir=${prefix}/include/thrift
???? Make
???? Make install
Update Pkg_config_path:
???? Export Pkg_config_path= $PKG _config_path:/usr/local/lib/pkgconfig/
Verifiy pkg-config path is correct:
???? Pkg-config--cflags Thrift
???? Returns
???? -i/usr/local/include/thrift
Copy files to Lib folder
???? cp/usr/local/lib/libthrift-1.0.0-dev.so/usr/lib/
5. Setting Linux Environment variables
Export Hadoop_prefix=/usr/lib/hadoop
Export Hadoop_cmd=/usr/lib/hadoop/bin/hadoop
Export Hadoop_streaming=/usr/lib/hadoop-mapreduce/hadoop-streaming.jar
6, the root user to open the R Environment installation dependency package
Install.packages (C ("Rjava", "Rcpp", "Rjsonio", "Bitops", "Digest",
????????????????????" Functional "," Stringr "," Plyr "," Reshape2 "," Dplyr ",
????????????????????" R.methodss3 "," Catools "," Hmisc "," data.table "," memoise "))
7, the root user to open the R environment installation Rhadoop package
Install.packages ("/root/rhadoop/rhdfs_1.0.8.tar.gz", Repos=null, type= "source")
Install.packages ("/root/rhadoop/rmr2_3.3.0.tar.gz", Repos=null, type= "source")
Install.packages ("/root/rhadoop/plyrmr_0.5.0.tar.gz", Repos=null, type= "source")
Install.packages ("/root/rhadoop/rhbase_1.2.1.tar.gz", Repos=null, type= "source")
8. Configuring Ant and Maven
Export maven_home=/root/apache-maven-3.2.5
Export Path=/root/apache-maven-3.2.5/bin: $PATH
Export ant_home=/root/apache-ant-1.9.4
Export path= $ANT _home/bin: $PATH
9. Test Rhadoop
Sys.setenv ("Hadoop_prefix" = "/usr/lib/hadoop")
Sys.setenv ("hadoop_cmd" = "/usr/lib/hadoop/bin/hadoop")
Sys.setenv ("hadoop_streaming" = "/usr/lib/hadoop-mapreduce/hadoop-streaming.jar")
?
???? Library (RMR2)
???? bp = rmr.options ("Backend.parameters")
???? Trans <-list (d= "mapreduce.map.java.opts=-xmx400m",
???????????????? D= "mapreduce.reduce.java.opts=-xmx400m",
???????????????? D= "mapreduce.map.memory.mb=4096",
???????????????? D= "mapreduce.reduce.memory.mb=4096",
???????????????? D= "mapreduce.task.io.sort.mb=100")
???? bp <-list (Hadoop=trans)
???? # # # # # # no code started #######################
???? bp$hadoop[1]= "mapreduce.map.java.opts=-xmx400m"
???? bp$hadoop[2]= "mapreduce.reduce.java.opts=-xmx400m"
???? bp$hadoop[3]= "mapreduce.map.memory.mb=1024"
???? bp$hadoop[4]= "mapreduce.reduce.memory.mb=2048"
???? bp$hadoop[5]= "Mapreduce.task.io.sort.mb=100"
???? # # # # no end of code used #######################
???? Rmr.options (backend.parameters = BP)
???? Rmr.options ("Backend.parameters")
???? # # Map function
???? Map <-Function (k,lines) {
???????? Words.list <-Strsplit (lines, ' \\s ')
???????? Words <-unlist (words.list)
???????? Return (Keyval (words, 1))
????}
???? # # Reduce function
???? Reduce <-function (Word, counts) {
???????? Keyval (Word, sum (counts))
????}
???? WordCount <-function (input, output=null) {
???????? MapReduce (Input=input, Output=output, input.format= "text",
Map=map, Reduce=reduce)
????}
?
???? # # Delete previous result if any
???? System ("/usr/lib/hadoop/bin/hadoop fs-rm-r/tmp/zhengcong/out")
????
???? # # Submit Job
???? Hdfs.root <-'/tmp/zhengcong '
???? Hdfs.data <-File.path (hdfs.root, ' HP ')
???? Hdfs.out <-File.path (hdfs.root, ' out ')
???? Out <-WordCount (Hdfs.data, Hdfs.out)
?
???? # # Fetch results from HDFS
???? Results <-From.dfs (out)
?
???? # # Check Top frequent words
???? RESULTS.DF <-As.data.frame (results, stringsasfactors=f)
???? Colnames (RESULTS.DF) <-C (' word ', ' count ')
???? Head (Results.df[order (Results.df$count, decreasing=t),], 30)
?
10. Error resolution
???? Rjava cannot load, the root user runs R CMD javareconf-e
???? Add Export ld_library_path= $JAVA _home/lib/amd64: $JAVA _home/jre/lib/amd64/server
Example of configuring Rhadoop and running WordCount