# The script to run.
script: train.py
# The arguments to the script file.
arguments: []
# The name of the compute target to use for this run.
target: local
# Framework to execute inside. Allowed values are "Python" ,  "PySpark", "CNTK",  "TensorFlow", and "PyTorch".
framework: PySpark
# Communicator for the given framework. Allowed values are "None" ,  "ParameterServer", "OpenMpi", and "IntelMpi".
communicator: None
# Automatically prepare the run environment as part of the run itself.
autoPrepareEnvironment: true
# Maximum allowed duration for the run.
maxRunDurationSeconds:
# Number of nodes to use for running job.
nodeCount: 1
# Environment details.
environment:
# Environment variables set for the run.
  environmentVariables:
    EXAMPLE_ENV_VAR: EXAMPLE_VALUE
# Python details
  python:
# user_managed_dependencies=True indicates that the environmentwill be user managed. False indicates that AzureML willmanage the user environment.
    userManagedDependencies: false
# The python interpreter path
    interpreterPath: python
# Path to the conda dependencies file to use for this run. If a project
# contains multiple programs with different sets of dependencies, it may be
# convenient to manage those environments with separate files.
    condaDependenciesFile: aml_config/conda_dependencies.yml
# Docker details
  docker:
# Set True to perform this run inside a Docker container.
    enabled: true
# Base image used for Docker-based runs.
    baseImage: mcr.microsoft.com/azureml/base:0.2.0
# Set False if necessary to work around shared volume bugs.
    sharedVolumes: true
# Run with NVidia Docker extension to support GPUs.
    gpuSupport: false
# Extra arguments to the Docker run command.
    arguments: []
# Image registry that contains the base image.
    baseImageRegistry:
# DNS name or IP address of azure container registry(ACR)
      address:
# The username for ACR
      username:
# The password for ACR
      password:
# Spark details
  spark:
# List of spark repositories.
    repositories:
    - https://mmlspark.azureedge.net/maven
    packages:
    - group: com.microsoft.ml.spark
      artifact: mmlspark_2.11
      version: '0.12'
    precachePackages: true
# Databricks details
  databricks:
# List of maven libraries.
    mavenLibraries: []
# List of PyPi libraries
    pypiLibraries: []
# List of RCran libraries
    rcranLibraries: []
# List of JAR libraries
    jarLibraries: []
# List of Egg libraries
    eggLibraries: []
# History details.
history:
# Enable history tracking -- this allows status, logs, metrics, and outputs
# to be collected for a run.
  outputCollection: true
# whether to take snapshots for history.
  snapshotProject: true
# Spark configuration details.
spark:
  configuration:
    spark.app.name: Azure ML Experiment
    spark.yarn.maxAppAttempts: 1
# HDI details.
hdi:
# Yarn deploy mode. Options are cluster and client.
  yarnDeployMode: cluster
# Tensorflow details.
tensorflow:
# The number of worker tasks.
  workerCount: 1
# The number of parameter server tasks.
  parameterServerCount: 1
# Mpi details.
mpi:
# When using MPI, number of processes per node.
  processCountPerNode: 1
# data reference configuration details
dataReferences: {}
# Project share datastore reference.
sourceDirectoryDataStore:
# AmlCompute details.
amlcompute:
# VM size of the Cluster to be created.Allowed values are Azure vm sizes.The list of vm sizes is available in 'https://docs.microsoft.com/en-us/azure/cloud-services/cloud-services-sizes-specs
  vmSize:
# VM priority of the Cluster to be created.Allowed values are "dedicated" , "lowpriority".
  vmPriority:
# A bool that indicates if the cluster has to be retained after job completion.
  retainCluster: false
# Name of the cluster to be created. If not specified, runId will be used as cluster name.
  name:
# Maximum number of nodes in the AmlCompute cluster to be created. Minimum number of nodes will always be set to 0.
  clusterMaxNodeCount: 1