Use RSparkling in Windows Environments

Prepare Spark Environment

Initially, please follow the tutorial of running Use Sparkling Water in Windows Environments. The configurations applies to RSparkling as well.

Prepare R Environment

Please follow the RSparkling Documentation in order to properly set up R packages and environment.

Test the Functionality

Use the following script below to test if you have any RSparkling issues.

The script will check that you can:

  1. Connect to Spark

  2. Start H2O

  3. Copy a R dataframe from R to a Spark DataFrame.

library(sparklyr)
library(rsparkling)

# Set spark connection
sc <- spark_connect(master = "local", version = "2.4.5")

# Create H2O Context
h2o_context(sc)

# Copy R dataset to Spark
library(dplyr)
mtcars_tbl <- copy_to(sc, mtcars, overwrite = TRUE)
mtcars_tbl

Troubleshooting

  • Error from running h2o_context

    Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 3 in stage 2.0 failed 1 times, most recent failure: Lost task 3.0 in stage 2.0 (TID 13, localhost): java.lang.NullPointerException
           at java.lang.ProcessBuilder.start(ProcessBuilder.java:1012)
           at org.apache.hadoop.util.Shell.runCommand(Shell.java:483)
           at org.apache.hadoop.util.Shell.run(Shell.java:456)
           at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:722)
           at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:873)
           at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:853)
           at org.apache.spark.util.Utils$.fetchFile(Utils.scala:471)
    

    This is caused because HADOOP_HOME environment variable is not explicitly set. Set the HADOOP_HOME environment to %SPARK_HOME%/tmp/hadoop or location where bin\winutils.exe is located.

    Download winutils.exe binary from https://github.com/steveloughran/winutils repository.

    NOTE: You need to select correct Hadoop version which is compatible with your Spark distribution. Hadoop version is often encoded in spark download name, for example, spark-2.4.5-bin-hadoop2.7.tgz.

  • Error from running copy_to

    Error: java.lang.reflect.InvocationTargetException
            at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
            at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
            at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
            at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
            at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:258)
            at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:359)
            at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:263)
            at org.apache.spark.sql.hive.HiveSharedState.metadataHive$lzycompute(HiveSharedState.scala:39)
    

    This is caused because there are no permissions to the folder: file:///tmp/hive. You can run a command in the command prompt which will change the permissions of the /tmp/hive directory. It will change the permissions of the /tmp/hive directory so that all three users (Owner, Group, and Public) can Read, Write, and Execute.

    In order to change the permissions, go to the command prompt and write: \path\to\winutils\Winutils.exe chmod 777 \tmp\hive

    You can also create a file hive-site.xml in %HADOOP_HOME%\conf and modify location of default Hive scratch dir (which is /tmp/hive):

    <configuration>
      <property>
        <name>hive.exec.scratchdir</name>
        <value>/Users/michal/hive/</value>
        <description>Scratch space for Hive jobs</description>
      </property>
    </configuration>
    

    In this case, do not forget to set the variable HADOOP_CONF_DIR:

    SET HADOOP_CONF_DIR=%HADOOP_HOME%\conf
    

    If the previous does not work, you can delete the metastore_db folder in your R working directory.