I am new to the rstudio community (but not to rstudio, of course:)). I am writing this post to get some perspectives from you people on the deployment of R machine learning/predictive models in a production envi.
In previous releases of Microsoft R Server, parcel installation required downloading two pre-built parcel files. The 9.1 release improves upon this experience by providing a parcel generator script generate_mrs_parcel.sh to generate a single MRS-9.1.0-*.parcel file. Here are the complete instructions to install MRS Parcel in Cloudera Cluster.
In this article we will look into how to make RStudio Server (both Open and Commercial) work with MRS 9.1.0 Parcel Installation in Cloudera. RStudio Server has an open source license as well as commercial license. You can view the differences here. RStudio Server with commercial license is also called RStudio Server Pro.
The following steps assume that you already have a Cloudera Cluster with MRS-9.1.0 parcel installed and activated. These steps can be run on edgenode/gateway node of the cluster.
- Download and install RStudio Server Pro from here (OR) RStudio Server Open Source License from here.
RStudio Server Open Source License :
RStudio Server Pro :
- We need to set some environment variables at the start of R session. This can be achieved using Renviron file. Append the following lines to /opt/cloudera/parcels/MRS/lib64/R/etc/Renviron
- Create libjvm.so symlink
- Copy RevoHadoopEnvVars.site file from home directory into hadoop directory. (NOTE: If .RevoHadoopEnvVars.site file is not present in the home directory , just run R command once - this will generate site file in home directory)
![R Studio Für Machine R Studio Für Machine](/uploads/1/2/5/7/125788531/171415083.png)
- Restart RStudio Server
- RStudio Server will be available in the following url : http://<nodename>:8787. (Make sure port 8787 is open)
Let us run Microsoft R Server Examples on Local, Hadoop and Spark Compute Context using RStudio Server :
![R studio for machine learning R studio for machine learning](http://devopspy.com/wp-content/uploads/2018/06/r-install6.png)