Running Spark Python Applications

Setting the Python Path

After the Python packages you want to use are in a consistent location on your cluster, set the appropriate environment variables to the path to your Python executables as follows:

• Specify the Python binary to be used by the Spark driver and executors by setting the PYSPARK_PYTHON environment variable in spark-env.sh. You can also override the driver Python binary path individually using the PYSPARK_DRIVER_PYTHON environment variable. These settings apply regardless of whether you are using yarn-client or yarn-cluster mode.

  Make sure to set the variables using a conditional export statement. For example:

  if [ "${PYSPARK_PYTHON}" = "python" ]; then
    export PYSPARK_PYTHON=<path_to_python_executable>
  fi

  This statement sets the PYSPARK_PYTHON environment variable to <path_to_python_executable> if it is set to python. This is necessary because the pyspark script sets PYSPARK_PYTHON to python if it is not already set to something else. If the user has set PYSPARK_PYTHON to something else, both pyspark and this example preserve their setting.

  Here are some example Python binary paths:

  • Anaconda parcel: /opt/cloudera/parcels/Anaconda/bin/python
  • Virtual environment: /path/to/virtualenv/bin/python
• If you are using yarn-cluster mode, in addition to the above, also set spark.yarn.appMasterEnv.PYSPARK_PYTHON and spark.yarn.appMasterEnv.PYSPARK_DRIVER_PYTHON in spark-defaults.conf (using the safety valve) to the same paths.

In Cloudera Manager, set environment variables in spark-env.sh and spark-defaults.conf as follows:

Minimum Required Role: Configurator (also provided by Cluster Administrator, Full Administrator)

1. Go to the Spark service. If you are using the CDS 2 parcel to run a Spark 2 service, you can set the Python path separately by following these same steps for the Spark 2 service. This is useful if you want to use a different Python version for your Spark 2 service.
2. Click the Configuration tab.
3. Search for Spark Service Advanced Configuration Snippet (Safety Valve) for spark-env.sh.
4. Add the spark-env.sh variables to the property.
5. Search for Spark Client Advanced Configuration Snippet (Safety Valve) for spark-defaults.conf.
6. Add the spark-defaults.conf variables to the property.
7. Click Save Changes to commit the changes.
8. Restart the service.
9. Deploy the client configuration.

Self-Contained Dependencies

In a common situation, a custom Python package contains functionality you want to apply to each element of an RDD. You can use a map() function call to make sure that each Spark executor imports the required package, before calling any of the functions inside that package. The following shows a simple example:

def import_my_special_package(x):
  import my.special.package
  return x

int_rdd = sc.parallelize([1, 2, 3, 4])
int_rdd.map(lambda x: import_my_special_package(x))
int_rdd.collect()

You create a simple RDD of four elements and call it int_rdd. Then you apply the function import_my_special_package to every element of the int_rdd. This function imports my.special.package and then returns the original argument passed to it. Calling this function as part of a map() operation ensures that each Spark executor imports my.special.package when needed.

If you only need a single file inside my.special.package, you can direct Spark to make this available to all executors by using the --py-files option in your spark-submit command and specifying the local path to the file. You can also specify this programmatically by using the sc.addPyFiles() function. If you use functionality from a package that spans multiple files, you can make an egg for the package, because the --py-files flag also accepts a path to an egg file.

If you have a self-contained dependency, you can make the required Python dependency available to your executors in two ways:

• If you depend on only a single file, you can use the --py-files command-line option, or programmatically add the file to the SparkContext with sc.addPyFiles(path) and specify the local path to that Python file.
• If you have a dependency on a self-contained module (a module with no other dependencies), you can create an egg or zip file of that module and use either the --py-files command-line option or programmatically add the module to theSparkContext with sc.addPyFiles(path) and specify the local path to that egg or zip file.

Complex Dependencies

Some operations rely on complex packages that also have many dependencies. For example, the following code snippet imports the Python pandas data analysis library:

def import_pandas(x):
 import pandas
 return x

int_rdd = sc.parallelize([1, 2, 3, 4])
int_rdd.map(lambda x: import_pandas(x))
int_rdd.collect()

pandas depends on NumPy, SciPy, and many other packages. Although pandas is too complex to distribute as a *.py file, you can create an egg for it and its dependencies and send that to executors.

Limitations of Distributing Egg Files

In both self-contained and complex dependency scenarios, sending egg files is problematic because packages that contain native code must be compiled for the specific host on which it will run. When doing distributed computing with industry-standard hardware, you must assume is that the hardware is heterogeneous. However, because of the required C compilation, a Python egg built on a client host is specific to the client CPU architecture. Therefore, distributing an egg for complex, compiled packages like NumPy, SciPy, and pandas often fails. Instead of distributing egg files you should install the required Python packages on each host of the cluster and specify the path to the Python binaries for the worker hosts to use.

Installing and Maintaining Python Environments

Installing and maintaining Python environments can be complex but allows you to use the full Python package ecosystem. Ideally, a sysadmin installs the Anaconda distribution or sets up a virtual environment on every host of your cluster with your required dependencies.

If you are using Cloudera Manager, you can deploy the Anaconda distribution as a parcel as follows:

Minimum Required Role: Cluster Administrator (also provided by Full Administrator)

1. Add the following URL https://repo.anaconda.com/pkgs/misc/parcels/ to the Remote Parcel Repository URLs as described in Parcel Configuration Settings.

2. Download, distribute, and activate the parcel as described in Managing Parcels.

Anaconda is installed in parcel directory/Anaconda, where parcel directory is /opt/cloudera/parcels by default, but can be changed in parcel configuration settings. The Anaconda parcel is supported by Continuum Analytics.

If you are not using Cloudera Manager, you can set up a virtual environment on your cluster by running commands on each host using Cluster SSH, Parallel SSH, or Fabric. Assuming each host has Python and pip installed, use the following commands to set up the standard data stack (NumPy, SciPy, scikit-learn, and pandas) in a virtual environment on a RHEL 6-compatible system:

# Install python-devel:
yum install python-devel

# Install non-Python dependencies required by SciPy that are not installed by default:
yum install atlas atlas-devel lapack-devel blas-devel

# install virtualenv:
pip install virtualenv

# create a new virtualenv:
virtualenv mynewenv

# activate the virtualenv:
source mynewenv/bin/activate

# install packages in mynewenv:
pip install numpy
pip install scipy
pip install scikit-learn
pip install pandas